From 12dbc74742b64cd8b72e843335b7de54184ee3ec Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Fri, 31 Jan 2020 10:52:31 -0800 Subject: [PATCH 1/8] New ResNet50 JSD + RandAugment weights --- README.md | 11 +++++++++-- timm/models/resnet.py | 2 +- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index e0f0e863..b6224e6b 100644 --- a/README.md +++ b/README.md @@ -2,13 +2,15 @@ ## What's New +### Jan 31, 2020 +* Update ResNet50 weights with a new 79.038 result from further JSD / AugMix experiments. Full command line for reproduction in training section below. + ### Jan 11/12, 2020 * Master may be a bit unstable wrt to training, these changes have been tested but not all combos * Implementations of AugMix added to existing RA and AA. Including numerous supporting pieces like JSD loss (Jensen-Shannon divergence + CE), and AugMixDataset * SplitBatchNorm adaptation layer added for implementing Auxiliary BN as per AdvProp paper * ResNet-50 AugMix trained model w/ 79% top-1 added * `seresnext26tn_32x4d` - 77.99 top-1, 93.75 top-5 added to tiered experiment, higher img/s than 't' and 'd' -* Command lines/hparams and more AugMix and related model updates for above coming soon... ### Jan 3, 2020 * Add RandAugment trained EfficientNet-B0 weight with 77.7 top-1. Trained by [Michael Klachko](https://github.com/michaelklachko) with this code and recent hparams (see Training section) @@ -140,7 +142,7 @@ I've leveraged the training scripts in this repository to train a few of the mod | mixnet_xl | 80.478 (19.522) | 94.932 (5.068) | 11.90M | bicubic | 224 | | efficientnet_b2 | 80.402 (19.598) | 95.076 (4.924) | 9.11M | bicubic | 260 | | resnext50d_32x4d | 79.674 (20.326) | 94.868 (5.132) | 25.1M | bicubic | 224 | -| resnet50 | 78.994 (21.006) | 94.396 (5.604) | 25.6M | bicubic | 224 | +| resnet50 | 79.038 (20.962) | 94.390 (5.610) | 25.6M | bicubic | 224 | | mixnet_l | 78.976 (21.024 | 94.184 (5.816) | 7.33M | bicubic | 224 | | efficientnet_b1 | 78.692 (21.308) | 94.086 (5.914) | 7.79M | bicubic | 240 | | resnext50_32x4d | 78.512 (21.488) | 94.042 (5.958) | 25M | bicubic | 224 | @@ -292,6 +294,11 @@ Michael Klachko achieved these results with the command line for B2 adapted for `./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-connect 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048` +### ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5 + +Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 79.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. + +`./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce` **TODO dig up some more** diff --git a/timm/models/resnet.py b/timm/models/resnet.py index 18952980..422eb0cb 100644 --- a/timm/models/resnet.py +++ b/timm/models/resnet.py @@ -42,7 +42,7 @@ default_cfgs = { url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet26d-69e92c46.pth', interpolation='bicubic'), 'resnet50': _cfg( - url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50_am-6c502b37.pth', + url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet50_ram-a26f946b.pth', interpolation='bicubic'), 'resnet50d': _cfg( url='', From b18c19901ec83034834b03a6109bc26d5c8ee1c0 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Fri, 31 Jan 2020 10:59:31 -0800 Subject: [PATCH 2/8] Update README.md Typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b6224e6b..dfee0a23 100644 --- a/README.md +++ b/README.md @@ -296,7 +296,7 @@ Michael Klachko achieved these results with the command line for B2 adapted for ### ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5 -Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 79.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. +Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 78.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. `./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce` From 5b7cc16ac915f9c162406ac855b29e6819296e64 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Fri, 31 Jan 2020 11:43:34 -0800 Subject: [PATCH 3/8] Add warning about using sync-bn with zero initialized BN layers. Fixes #54 --- train.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/train.py b/train.py index e3eec357..bfb7568f 100755 --- a/train.py +++ b/train.py @@ -315,7 +315,9 @@ def main(): else: model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model) if args.local_rank == 0: - logging.info('Converted model to use Synchronized BatchNorm.') + logging.info( + 'Converted model to use Synchronized BatchNorm. WARNING: You may have issues if using ' + 'zero initialized BN layers (enabled by default for ResNets) while sync-bn enabled.') except Exception as e: logging.error('Failed to enable Synchronized BatchNorm. Install Apex or Torch >= 1.1') if has_apex: From 82dd60b33ceb2291cd1e737c4702a69e4c5de903 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Fri, 31 Jan 2020 23:00:02 -0800 Subject: [PATCH 4/8] Rename results files for more clarity --- results/{results-all.csv => results-imagenet.csv} | 0 ...hed-frequency.csv => results-imagenetv2-matched-frequency.csv} | 0 2 files changed, 0 insertions(+), 0 deletions(-) rename results/{results-all.csv => results-imagenet.csv} (100%) rename results/{results-inv2-matched-frequency.csv => results-imagenetv2-matched-frequency.csv} (100%) diff --git a/results/results-all.csv b/results/results-imagenet.csv similarity index 100% rename from results/results-all.csv rename to results/results-imagenet.csv diff --git a/results/results-inv2-matched-frequency.csv b/results/results-imagenetv2-matched-frequency.csv similarity index 100% rename from results/results-inv2-matched-frequency.csv rename to results/results-imagenetv2-matched-frequency.csv From 91534522f95d77096c8f275a629b88d4e0059bb1 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Sat, 1 Feb 2020 18:01:14 -0800 Subject: [PATCH 5/8] Add newly added TF ported EfficientNet-B8 weights (RandAugment) --- timm/models/efficientnet.py | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/timm/models/efficientnet.py b/timm/models/efficientnet.py index 6f123187..ae100b69 100644 --- a/timm/models/efficientnet.py +++ b/timm/models/efficientnet.py @@ -124,6 +124,9 @@ default_cfgs = { 'tf_efficientnet_b7': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_b7_ra-6c08e654.pth', input_size=(3, 600, 600), pool_size=(19, 19), crop_pct=0.949), + 'tf_efficientnet_b8': _cfg( + url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_b8_ra-572d5dd9.pth', + input_size=(3, 672, 672), pool_size=(21, 21), crop_pct=0.954), 'tf_efficientnet_b0_ap': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/tf_efficientnet_b0_ap-f262efe1.pth', mean=IMAGENET_INCEPTION_MEAN, std=IMAGENET_INCEPTION_STD, input_size=(3, 224, 224)), @@ -1059,9 +1062,20 @@ def tf_efficientnet_b7(pretrained=False, **kwargs): return model +@register_model +def tf_efficientnet_b8(pretrained=False, **kwargs): + """ EfficientNet-B8. Tensorflow compatible variant """ + # NOTE for train, drop_rate should be 0.5 + kwargs['bn_eps'] = BN_EPS_TF_DEFAULT + kwargs['pad_type'] = 'same' + model = _gen_efficientnet( + 'tf_efficientnet_b8', channel_multiplier=2.2, depth_multiplier=3.6, pretrained=pretrained, **kwargs) + return model + + @register_model def tf_efficientnet_b0_ap(pretrained=False, **kwargs): - """ EfficientNet-B0. Tensorflow compatible variant """ + """ EfficientNet-B0 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1071,7 +1085,7 @@ def tf_efficientnet_b0_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b1_ap(pretrained=False, **kwargs): - """ EfficientNet-B1. Tensorflow compatible variant """ + """ EfficientNet-B1 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1081,7 +1095,7 @@ def tf_efficientnet_b1_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b2_ap(pretrained=False, **kwargs): - """ EfficientNet-B2. Tensorflow compatible variant """ + """ EfficientNet-B2 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1091,7 +1105,7 @@ def tf_efficientnet_b2_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b3_ap(pretrained=False, **kwargs): - """ EfficientNet-B3. Tensorflow compatible variant """ + """ EfficientNet-B3 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1101,7 +1115,7 @@ def tf_efficientnet_b3_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b4_ap(pretrained=False, **kwargs): - """ EfficientNet-B4. Tensorflow compatible variant """ + """ EfficientNet-B4 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1111,7 +1125,7 @@ def tf_efficientnet_b4_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b5_ap(pretrained=False, **kwargs): - """ EfficientNet-B5. Tensorflow compatible variant """ + """ EfficientNet-B5 AdvProp. Tensorflow compatible variant """ kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' model = _gen_efficientnet( @@ -1121,7 +1135,7 @@ def tf_efficientnet_b5_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b6_ap(pretrained=False, **kwargs): - """ EfficientNet-B6. Tensorflow compatible variant """ + """ EfficientNet-B6 AdvProp. Tensorflow compatible variant """ # NOTE for train, drop_rate should be 0.5 kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' @@ -1132,7 +1146,7 @@ def tf_efficientnet_b6_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b7_ap(pretrained=False, **kwargs): - """ EfficientNet-B7. Tensorflow compatible variant """ + """ EfficientNet-B7 AdvProp. Tensorflow compatible variant """ # NOTE for train, drop_rate should be 0.5 kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' @@ -1143,7 +1157,7 @@ def tf_efficientnet_b7_ap(pretrained=False, **kwargs): @register_model def tf_efficientnet_b8_ap(pretrained=False, **kwargs): - """ EfficientNet-B7. Tensorflow compatible variant """ + """ EfficientNet-B8 AdvProp. Tensorflow compatible variant """ # NOTE for train, drop_rate should be 0.5 kwargs['bn_eps'] = BN_EPS_TF_DEFAULT kwargs['pad_type'] = 'same' From 1daa303744763c141a137c589aa6068c174aa669 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Sat, 1 Feb 2020 18:07:32 -0800 Subject: [PATCH 6/8] Add support to Dataset for class id mapping file, clean up a bit of old logic. Add results file arg for validation and update script. --- timm/data/dataset.py | 86 ++++++++++++++++++++++++++------------------ validate.py | 36 +++++++++++++------ 2 files changed, 77 insertions(+), 45 deletions(-) diff --git a/timm/data/dataset.py b/timm/data/dataset.py index fc252d9e..2ce79e7e 100644 --- a/timm/data/dataset.py +++ b/timm/data/dataset.py @@ -20,34 +20,40 @@ def natural_key(string_): def find_images_and_targets(folder, types=IMG_EXTENSIONS, class_to_idx=None, leaf_name_only=True, sort=True): - if class_to_idx is None: - class_to_idx = dict() - build_class_idx = True - else: - build_class_idx = False labels = [] filenames = [] for root, subdirs, files in os.walk(folder, topdown=False): rel_path = os.path.relpath(root, folder) if (root != folder) else '' label = os.path.basename(rel_path) if leaf_name_only else rel_path.replace(os.path.sep, '_') - if build_class_idx and not subdirs: - class_to_idx[label] = None for f in files: base, ext = os.path.splitext(f) if ext.lower() in types: filenames.append(os.path.join(root, f)) labels.append(label) - if build_class_idx: - classes = sorted(class_to_idx.keys(), key=natural_key) - for idx, c in enumerate(classes): - class_to_idx[c] = idx + if class_to_idx is None: + # building class index + unique_labels = set(labels) + sorted_labels = list(sorted(unique_labels, key=natural_key)) + class_to_idx = {c: idx for idx, c in enumerate(sorted_labels)} images_and_targets = zip(filenames, [class_to_idx[l] for l in labels]) if sort: images_and_targets = sorted(images_and_targets, key=lambda k: natural_key(k[0])) - if build_class_idx: - return images_and_targets, classes, class_to_idx + return images_and_targets, class_to_idx + + +def load_class_map(filename, root=''): + class_to_idx = {} + class_map_path = filename + if not os.path.exists(class_map_path): + class_map_path = os.path.join(root, filename) + assert os.path.exists(class_map_path), 'Cannot locate specified class map file (%s)' % filename + class_map_ext = os.path.splitext(filename)[-1].lower() + if class_map_ext == '.txt': + with open(class_map_path) as f: + class_to_idx = {v.strip(): k for k, v in enumerate(f)} else: - return images_and_targets + assert False, 'Unsupported class map extension' + return class_to_idx class Dataset(data.Dataset): @@ -56,19 +62,25 @@ class Dataset(data.Dataset): self, root, load_bytes=False, - transform=None): - - imgs, _, _ = find_images_and_targets(root) - if len(imgs) == 0: + transform=None, + class_map=''): + + class_to_idx = None + if class_map: + class_to_idx = load_class_map(class_map, root) + images, class_to_idx = find_images_and_targets(root, class_to_idx=class_to_idx) + if len(images) == 0: raise(RuntimeError("Found 0 images in subfolders of: " + root + "\n" "Supported image extensions are: " + ",".join(IMG_EXTENSIONS))) self.root = root - self.imgs = imgs + self.samples = images + self.imgs = self.samples # torchvision ImageFolder compat + self.class_to_idx = class_to_idx self.load_bytes = load_bytes self.transform = transform def __getitem__(self, index): - path, target = self.imgs[index] + path, target = self.samples[index] img = open(path, 'rb').read() if self.load_bytes else Image.open(path).convert('RGB') if self.transform is not None: img = self.transform(img) @@ -82,18 +94,17 @@ class Dataset(data.Dataset): def filenames(self, indices=[], basename=False): if indices: if basename: - return [os.path.basename(self.imgs[i][0]) for i in indices] + return [os.path.basename(self.samples[i][0]) for i in indices] else: - return [self.imgs[i][0] for i in indices] + return [self.samples[i][0] for i in indices] else: if basename: - return [os.path.basename(x[0]) for x in self.imgs] + return [os.path.basename(x[0]) for x in self.samples] else: - return [x[0] for x in self.imgs] + return [x[0] for x in self.samples] -def _extract_tar_info(tarfile): - class_to_idx = {} +def _extract_tar_info(tarfile, class_to_idx=None, sort=True): files = [] labels = [] for ti in tarfile.getmembers(): @@ -101,26 +112,31 @@ def _extract_tar_info(tarfile): continue dirname, basename = os.path.split(ti.path) label = os.path.basename(dirname) - class_to_idx[label] = None ext = os.path.splitext(basename)[1] if ext.lower() in IMG_EXTENSIONS: files.append(ti) labels.append(label) - for idx, c in enumerate(sorted(class_to_idx.keys(), key=natural_key)): - class_to_idx[c] = idx + if class_to_idx is None: + unique_labels = set(labels) + sorted_labels = list(sorted(unique_labels, key=natural_key)) + class_to_idx = {c: idx for idx, c in enumerate(sorted_labels)} tarinfo_and_targets = zip(files, [class_to_idx[l] for l in labels]) - tarinfo_and_targets = sorted(tarinfo_and_targets, key=lambda k: natural_key(k[0].path)) - return tarinfo_and_targets + if sort: + tarinfo_and_targets = sorted(tarinfo_and_targets, key=lambda k: natural_key(k[0].path)) + return tarinfo_and_targets, class_to_idx class DatasetTar(data.Dataset): - def __init__(self, root, load_bytes=False, transform=None): + def __init__(self, root, load_bytes=False, transform=None, class_map=''): + class_to_idx = None + if class_map: + class_to_idx = load_class_map(class_map, root) assert os.path.isfile(root) self.root = root with tarfile.open(root) as tf: # cannot keep this open across processes, reopen later - self.imgs = _extract_tar_info(tf) + self.samples, self.class_to_idx = _extract_tar_info(tf, class_to_idx) self.tarfile = None # lazy init in __getitem__ self.load_bytes = load_bytes self.transform = transform @@ -128,7 +144,7 @@ class DatasetTar(data.Dataset): def __getitem__(self, index): if self.tarfile is None: self.tarfile = tarfile.open(self.root) - tarinfo, target = self.imgs[index] + tarinfo, target = self.samples[index] iob = self.tarfile.extractfile(tarinfo) img = iob.read() if self.load_bytes else Image.open(iob).convert('RGB') if self.transform is not None: @@ -138,7 +154,7 @@ class DatasetTar(data.Dataset): return img, target def __len__(self): - return len(self.imgs) + return len(self.samples) class AugMixDataset(torch.utils.data.Dataset): diff --git a/validate.py b/validate.py index 93a82021..7993faaa 100755 --- a/validate.py +++ b/validate.py @@ -45,6 +45,8 @@ parser.add_argument('--interpolation', default='', type=str, metavar='NAME', help='Image resize interpolation type (overrides model)') parser.add_argument('--num-classes', type=int, default=1000, help='Number classes in dataset') +parser.add_argument('--class-map', default='', type=str, metavar='FILENAME', + help='path to class to idx mapping file (default: "")') parser.add_argument('--log-freq', default=10, type=int, metavar='N', help='batch logging frequency (default: 10)') parser.add_argument('--checkpoint', default='', type=str, metavar='PATH', @@ -67,6 +69,8 @@ parser.add_argument('--use-ema', dest='use_ema', action='store_true', help='use ema version of weights if present') parser.add_argument('--torchscript', dest='torchscript', action='store_true', help='convert model torchscript for inference') +parser.add_argument('--results-file', default='', type=str, metavar='FILENAME', + help='Output csv file for validation results (summary)') def validate(args): @@ -104,10 +108,12 @@ def validate(args): criterion = nn.CrossEntropyLoss().cuda() + #from torchvision.datasets import ImageNet + #dataset = ImageNet(args.data, split='val') if os.path.splitext(args.data)[1] == '.tar' and os.path.isfile(args.data): - dataset = DatasetTar(args.data, load_bytes=args.tf_preprocessing) + dataset = DatasetTar(args.data, load_bytes=args.tf_preprocessing, class_map=args.class_map) else: - dataset = Dataset(args.data, load_bytes=args.tf_preprocessing) + dataset = Dataset(args.data, load_bytes=args.tf_preprocessing, class_map=args.class_map) crop_pct = 1.0 if test_time_pool else data_config['crop_pct'] loader = create_loader( @@ -201,9 +207,10 @@ def main(): model_cfgs = [(n, '') for n in model_names] if len(model_cfgs): + results_file = args.results_file or './results-all.csv' logging.info('Running bulk validation on these pretrained models: {}'.format(', '.join(model_names))) - header_written = False - with open('./results-all.csv', mode='w') as cf: + results = [] + try: for m, c in model_cfgs: args.model = m args.checkpoint = c @@ -212,15 +219,24 @@ def main(): result.update(r) if args.checkpoint: result['checkpoint'] = args.checkpoint - dw = csv.DictWriter(cf, fieldnames=result.keys()) - if not header_written: - dw.writeheader() - header_written = True - dw.writerow(result) - cf.flush() + results.append(result) + except KeyboardInterrupt as e: + pass + results = sorted(results, key=lambda x: x['top1'], reverse=True) + if len(results): + write_results(results_file, results) else: validate(args) +def write_results(results_file, results): + with open(results_file, mode='w') as cf: + dw = csv.DictWriter(cf, fieldnames=results[0].keys()) + dw.writeheader() + for r in results: + dw.writerow(r) + cf.flush() + + if __name__ == '__main__': main() From 7c88356682532021860fc19f343b314df518144b Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Sat, 1 Feb 2020 18:10:13 -0800 Subject: [PATCH 7/8] Add update results on ImageNet validation, ImageNetV2, ImageNet-A, and ImageNet-Sketch for all models --- results/results-imagenet-a.csv | 165 +++++++++ results/results-imagenet.csv | 312 ++++++++--------- .../results-imagenetv2-matched-frequency.csv | 320 +++++++++--------- results/results-sketch.csv | 165 +++++++++ 4 files changed, 656 insertions(+), 306 deletions(-) create mode 100644 results/results-imagenet-a.csv create mode 100644 results/results-sketch.csv diff --git a/results/results-imagenet-a.csv b/results/results-imagenet-a.csv new file mode 100644 index 00000000..2592692d --- /dev/null +++ b/results/results-imagenet-a.csv @@ -0,0 +1,165 @@ +model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation +ig_resnext101_32x48d,41.56,58.44,66.5467,33.4533,828.41,224,0.875,bilinear +ig_resnext101_32x32d,39.4267,60.5733,63.7867,36.2133,468.53,224,0.875,bilinear +ig_resnext101_32x16d,36.0,64.0,59.0,41.0,194.03,224,0.875,bilinear +swsl_resnext101_32x8d,32.0133,67.9867,59.44,40.56,88.79,224,0.875,bilinear +tf_efficientnet_b8_ap,29.5867,70.4133,56.9333,43.0667,87.41,672,0.954,bicubic +tf_efficientnet_b8,29.3867,70.6133,57.0533,42.9467,87.41,672,0.954,bicubic +ig_resnext101_32x8d,28.6667,71.3333,52.32,47.68,88.79,224,0.875,bilinear +swsl_resnext101_32x16d,27.9467,72.0533,52.2933,47.7067,194.03,224,0.875,bilinear +tf_efficientnet_b7_ap,27.8267,72.1733,54.7733,45.2267,66.35,600,0.949,bicubic +swsl_resnext101_32x4d,25.3067,74.6933,49.6267,50.3733,44.18,224,0.875,bilinear +tf_efficientnet_b7,25.28,74.72,51.6667,48.3333,66.35,600,0.949,bicubic +tf_efficientnet_b6_ap,24.3467,75.6533,50.44,49.56,43.04,528,0.942,bicubic +tf_efficientnet_b6,20.3733,79.6267,45.48,54.52,43.04,528,0.942,bicubic +tf_efficientnet_b5_ap,19.4667,80.5333,44.7333,55.2667,30.39,456,0.934,bicubic +swsl_resnext50_32x4d,18.04,81.96,41.9733,58.0267,25.03,224,0.875,bilinear +ssl_resnext101_32x16d,17.1867,82.8133,39.9333,60.0667,194.03,224,0.875,bilinear +tf_efficientnet_b5,17.0533,82.9467,41.92,58.08,30.39,456,0.934,bicubic +swsl_resnet50,15.9467,84.0533,38.8533,61.1467,25.56,224,0.875,bilinear +ssl_resnext101_32x8d,15.12,84.88,37.6933,62.3067,88.79,224,0.875,bilinear +tf_efficientnet_b4_ap,13.6667,86.3333,35.9467,64.0533,19.34,380,0.922,bicubic +tf_efficientnet_b4,13.32,86.68,35.5333,64.4667,19.34,380,0.922,bicubic +pnasnet5large,13.0533,86.9467,32.2267,67.7733,86.06,331,0.875,bicubic +nasnetalarge,12.56,87.44,33.4267,66.5733,88.75,331,0.875,bicubic +ssl_resnext101_32x4d,12.1067,87.8933,31.8933,68.1067,44.18,224,0.875,bilinear +gluon_senet154,9.8933,90.1067,26.4267,73.5733,115.09,224,0.875,bicubic +ssl_resnext50_32x4d,9.6533,90.3467,28.4667,71.5333,25.03,224,0.875,bilinear +senet154,9.4667,90.5333,26.44,73.56,115.09,224,0.875,bilinear +efficientnet_b3a,9.2533,90.7467,28.4267,71.5733,12.23,320,1.0,bicubic +efficientnet_b3,8.9733,91.0267,28.2267,71.7733,12.23,300,0.904,bicubic +inception_v4,8.8933,91.1067,24.68,75.32,42.68,299,0.875,bicubic +gluon_seresnext101_64x4d,8.8667,91.1333,27.28,72.72,88.23,224,0.875,bicubic +gluon_xception65,8.44,91.56,25.12,74.88,39.92,299,0.875,bicubic +gluon_resnet152_v1d,8.36,91.64,23.4267,76.5733,60.21,224,0.875,bicubic +inception_resnet_v2,8.1733,91.8267,23.5733,76.4267,55.84,299,0.8975,bicubic +tf_efficientnet_b3_ap,8.1067,91.8933,26.28,73.72,12.23,300,0.904,bicubic +gluon_seresnext101_32x4d,8.04,91.96,24.6933,75.3067,48.96,224,0.875,bicubic +tf_efficientnet_b3,8.0133,91.9867,25.48,74.52,12.23,300,0.904,bicubic +ens_adv_inception_resnet_v2,7.9733,92.0267,23.8667,76.1333,55.84,299,0.8975,bicubic +gluon_resnet152_v1s,7.8533,92.1467,23.1867,76.8133,60.32,224,0.875,bicubic +gluon_resnext101_64x4d,7.72,92.28,23.3067,76.6933,83.46,224,0.875,bicubic +ssl_resnet50,7.04,92.96,23.9067,76.0933,25.56,224,0.875,bilinear +efficientnet_b2a,6.7467,93.2533,23.5067,76.4933,9.11,288,1.0,bicubic +seresnext101_32x4d,6.4,93.6,21.4933,78.5067,48.96,224,0.875,bilinear +efficientnet_b2,6.0933,93.9067,21.96,78.04,9.11,260,0.875,bicubic +gluon_resnext101_32x4d,6.0133,93.9867,21.12,78.88,44.18,224,0.875,bicubic +gluon_resnet101_v1d,5.92,94.08,19.9467,80.0533,44.57,224,0.875,bicubic +gluon_seresnext50_32x4d,5.7867,94.2133,21.4533,78.5467,27.56,224,0.875,bicubic +gluon_inception_v3,5.5067,94.4933,20.0,80.0,23.83,299,0.875,bicubic +mixnet_xl,5.4667,94.5333,21.08,78.92,11.9,224,0.875,bicubic +gluon_resnet101_v1s,5.28,94.72,19.56,80.44,44.67,224,0.875,bicubic +hrnet_w64,5.16,94.84,19.4933,80.5067,128.06,224,0.875,bilinear +dpn107,4.8933,95.1067,17.6133,82.3867,86.92,224,0.875,bicubic +gluon_resnet152_v1c,4.8667,95.1333,17.72,82.28,60.21,224,0.875,bicubic +dla102x2,4.7467,95.2533,18.9067,81.0933,41.75,224,0.875,bilinear +tf_inception_v3,4.7467,95.2533,17.7733,82.2267,23.83,299,0.875,bicubic +adv_inception_v3,4.7333,95.2667,17.56,82.44,23.83,299,0.875,bicubic +hrnet_w48,4.72,95.28,18.4133,81.5867,77.47,224,0.875,bilinear +dpn131,4.6533,95.3467,16.8533,83.1467,79.25,224,0.875,bicubic +gluon_resnet152_v1b,4.5867,95.4133,16.5333,83.4667,60.19,224,0.875,bicubic +dpn92,4.5067,95.4933,18.2133,81.7867,37.67,224,0.875,bicubic +hrnet_w44,4.4933,95.5067,17.36,82.64,67.06,224,0.875,bilinear +resnext50d_32x4d,4.36,95.64,17.7867,82.2133,25.05,224,0.875,bicubic +xception,4.3333,95.6667,16.7867,83.2133,22.86,299,0.8975,bicubic +seresnext50_32x4d,4.28,95.72,17.8133,82.1867,27.56,224,0.875,bilinear +tf_efficientnet_cc_b1_8e,4.24,95.76,15.9467,84.0533,39.72,240,0.882,bicubic +tf_efficientnet_el,4.2267,95.7733,18.1867,81.8133,10.59,300,0.904,bicubic +inception_v3,4.1867,95.8133,16.2933,83.7067,27.16,299,0.875,bicubic +tf_efficientnet_b2_ap,4.16,95.84,18.3467,81.6533,9.11,260,0.89,bicubic +seresnet152,4.1467,95.8533,15.9333,84.0667,66.82,224,0.875,bilinear +resnext101_32x8d,4.1333,95.8667,16.92,83.08,88.79,224,0.875,bilinear +dpn98,4.08,95.92,15.96,84.04,61.57,224,0.875,bicubic +res2net101_26w_4s,4.0,96.0,14.8667,85.1333,45.21,224,0.875,bilinear +efficientnet_b1,3.9733,96.0267,15.7733,84.2267,7.79,240,0.875,bicubic +tf_efficientnet_b2,3.76,96.24,16.5867,83.4133,9.11,260,0.89,bicubic +hrnet_w30,3.68,96.32,15.5733,84.4267,37.71,224,0.875,bilinear +hrnet_w32,3.64,96.36,14.8133,85.1867,41.23,224,0.875,bilinear +seresnext26t_32x4d,3.64,96.36,15.9467,84.0533,16.82,224,0.875,bicubic +hrnet_w40,3.6133,96.3867,15.4267,84.5733,57.56,224,0.875,bilinear +tf_efficientnet_b1_ap,3.5467,96.4533,15.0533,84.9467,7.79,240,0.882,bicubic +dla169,3.4933,96.5067,15.36,84.64,53.99,224,0.875,bilinear +seresnext26tn_32x4d,3.4933,96.5067,15.7733,84.2267,16.81,224,0.875,bicubic +gluon_resnext50_32x4d,3.44,96.56,16.04,83.96,25.03,224,0.875,bicubic +mixnet_l,3.4267,96.5733,15.3067,84.6933,7.33,224,0.875,bicubic +seresnext26d_32x4d,3.4,96.6,16.1867,83.8133,16.81,224,0.875,bicubic +res2net50_26w_8s,3.3333,96.6667,13.9867,86.0133,48.4,224,0.875,bilinear +gluon_resnet101_v1c,3.32,96.68,14.12,85.88,44.57,224,0.875,bicubic +dla102x,3.28,96.72,15.16,84.84,26.77,224,0.875,bilinear +seresnet101,3.2533,96.7467,15.4533,84.5467,49.33,224,0.875,bilinear +dla60_res2next,3.0533,96.9467,14.4533,85.5467,17.33,224,0.875,bilinear +gluon_resnet50_v1d,3.0267,96.9733,14.6667,85.3333,25.58,224,0.875,bicubic +wide_resnet101_2,2.9467,97.0533,13.9733,86.0267,126.89,224,0.875,bilinear +gluon_resnet50_v1s,2.88,97.12,13.1067,86.8933,25.68,224,0.875,bicubic +res2net50_26w_6s,2.8533,97.1467,12.6133,87.3867,37.05,224,0.875,bilinear +tf_efficientnet_b1,2.8533,97.1467,13.48,86.52,7.79,240,0.882,bicubic +efficientnet_b0,2.8267,97.1733,13.8933,86.1067,5.29,224,0.875,bicubic +tf_mixnet_l,2.8133,97.1867,13.0533,86.9467,7.33,224,0.875,bicubic +dpn68b,2.7067,97.2933,12.6933,87.3067,12.61,224,0.875,bicubic +selecsls60b,2.7067,97.2933,13.2267,86.7733,32.77,224,0.875,bicubic +tf_efficientnet_cc_b0_8e,2.68,97.32,12.7867,87.2133,24.01,224,0.875,bicubic +dla60_res2net,2.64,97.36,14.1733,85.8267,21.15,224,0.875,bilinear +gluon_resnet101_v1b,2.6133,97.3867,13.56,86.44,44.55,224,0.875,bicubic +dla60x,2.6,97.4,13.3467,86.6533,17.65,224,0.875,bilinear +mixnet_m,2.5467,97.4533,12.4133,87.5867,5.01,224,0.875,bicubic +resnet152,2.36,97.64,12.2,87.8,60.19,224,0.875,bilinear +swsl_resnet18,2.3467,97.6533,11.2267,88.7733,11.69,224,0.875,bilinear +wide_resnet50_2,2.32,97.68,11.8267,88.1733,68.88,224,0.875,bilinear +hrnet_w18,2.28,97.72,11.84,88.16,21.3,224,0.875,bilinear +seresnext26_32x4d,2.28,97.72,12.44,87.56,16.79,224,0.875,bicubic +dla102,2.2667,97.7333,12.1467,87.8533,33.73,224,0.875,bilinear +resnet50,2.2133,97.7867,11.3067,88.6933,25.56,224,0.875,bicubic +resnext50_32x4d,2.12,97.88,12.3067,87.6933,25.03,224,0.875,bicubic +selecsls60,2.1067,97.8933,12.8533,87.1467,30.67,224,0.875,bicubic +tf_efficientnet_cc_b0_4e,2.0933,97.9067,10.9867,89.0133,13.31,224,0.875,bicubic +res2next50,2.0667,97.9333,11.4133,88.5867,24.67,224,0.875,bilinear +seresnet50,2.0667,97.9333,12.2667,87.7333,28.09,224,0.875,bilinear +densenet161,1.9733,98.0267,10.5733,89.4267,28.68,224,0.875,bicubic +tf_efficientnet_b0_ap,1.96,98.04,10.8,89.2,5.29,224,0.875,bicubic +tf_mixnet_m,1.84,98.16,10.56,89.44,5.01,224,0.875,bicubic +tf_efficientnet_em,1.8133,98.1867,11.6,88.4,6.9,240,0.882,bicubic +res2net50_14w_8s,1.8,98.2,10.3467,89.6533,25.06,224,0.875,bilinear +res2net50_26w_4s,1.7733,98.2267,10.4267,89.5733,25.7,224,0.875,bilinear +tf_efficientnet_b0,1.6933,98.3067,9.7467,90.2533,5.29,224,0.875,bicubic +tv_resnext50_32x4d,1.6933,98.3067,10.6,89.4,25.03,224,0.875,bilinear +resnet101,1.6667,98.3333,9.8,90.2,44.55,224,0.875,bilinear +mobilenetv3_rw,1.6533,98.3467,10.7333,89.2667,5.48,224,0.875,bicubic +mixnet_s,1.5867,98.4133,10.24,89.76,4.13,224,0.875,bicubic +densenet201,1.5467,98.4533,9.6267,90.3733,20.01,224,0.875,bicubic +semnasnet_100,1.5467,98.4533,9.28,90.72,3.89,224,0.875,bicubic +gluon_resnet50_v1c,1.5333,98.4667,10.6533,89.3467,25.58,224,0.875,bicubic +selecsls42b,1.44,98.56,10.4533,89.5467,32.46,224,0.875,bicubic +ssl_resnet18,1.3867,98.6133,8.2,91.8,11.69,224,0.875,bilinear +dla60,1.3333,98.6667,9.4667,90.5333,22.33,224,0.875,bilinear +dpn68,1.32,98.68,8.8267,91.1733,12.61,224,0.875,bicubic +res2net50_48w_2s,1.2933,98.7067,8.9333,91.0667,25.29,224,0.875,bilinear +tf_mixnet_s,1.2667,98.7333,8.7467,91.2533,4.13,224,0.875,bicubic +fbnetc_100,1.24,98.76,8.76,91.24,5.57,224,0.875,bilinear +resnet26d,1.24,98.76,9.32,90.68,16.01,224,0.875,bicubic +tf_mobilenetv3_large_100,1.1867,98.8133,7.9467,92.0533,5.48,224,0.875,bilinear +densenet169,1.1733,98.8267,8.3067,91.6933,14.15,224,0.875,bicubic +gluon_resnet50_v1b,1.16,98.84,9.08,90.92,25.56,224,0.875,bicubic +seresnet34,1.12,98.88,7.4267,92.5733,21.96,224,0.875,bilinear +tf_efficientnet_es,1.12,98.88,8.5867,91.4133,5.44,224,0.875,bicubic +spnasnet_100,1.1067,98.8933,8.2133,91.7867,4.42,224,0.875,bilinear +dla34,1.08,98.92,7.68,92.32,15.78,224,0.875,bilinear +resnet34,1.0,99.0,7.5333,92.4667,21.8,224,0.875,bilinear +gluon_resnet34_v1b,0.8933,99.1067,6.6,93.4,21.8,224,0.875,bicubic +hrnet_w18_small_v2,0.8933,99.1067,7.3867,92.6133,15.6,224,0.875,bilinear +tf_mobilenetv3_large_075,0.88,99.12,6.72,93.28,3.99,224,0.875,bilinear +mnasnet_100,0.8667,99.1333,7.8267,92.1733,4.38,224,0.875,bicubic +tf_mobilenetv3_small_100,0.7467,99.2533,4.6667,95.3333,2.54,224,0.875,bilinear +seresnet18,0.7333,99.2667,6.0267,93.9733,11.78,224,0.875,bicubic +densenet121,0.68,99.32,6.8933,93.1067,7.98,224,0.875,bicubic +tf_mobilenetv3_small_075,0.6533,99.3467,4.1867,95.8133,2.04,224,0.875,bilinear +tv_resnet34,0.6,99.4,5.5333,94.4667,21.8,224,0.875,bilinear +resnet26,0.5867,99.4133,6.8933,93.1067,16.0,224,0.875,bicubic +dla46_c,0.52,99.48,4.1733,95.8267,1.31,224,0.875,bilinear +dla60x_c,0.48,99.52,5.2133,94.7867,1.34,224,0.875,bilinear +tf_mobilenetv3_large_minimal_100,0.48,99.52,4.88,95.12,3.92,224,0.875,bilinear +hrnet_w18_small,0.4533,99.5467,4.84,95.16,13.19,224,0.875,bilinear +dla46x_c,0.4133,99.5867,4.44,95.56,1.08,224,0.875,bilinear +gluon_resnet18_v1b,0.3867,99.6133,4.7867,95.2133,11.69,224,0.875,bicubic +tf_mobilenetv3_small_minimal_100,0.36,99.64,2.8667,97.1333,2.04,224,0.875,bilinear +resnet18,0.2933,99.7067,4.04,95.96,11.69,224,0.875,bilinear +tv_resnet50,0.0,100.0,2.9067,97.0933,25.56,224,0.875,bilinear diff --git a/results/results-imagenet.csv b/results/results-imagenet.csv index e9ba9fb7..d95b1778 100644 --- a/results/results-imagenet.csv +++ b/results/results-imagenet.csv @@ -1,155 +1,165 @@ model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation -ig_resnext101_32x48d,85.442,14.558,97.572,2.428,828.41,224,0.875,bilinear -tf_efficientnet_b8_ap,85.368,14.632,97.294,2.706,87.41,672,0.954,bicubic -tf_efficientnet_b7_ap,85.118,14.882,97.252,2.748,66.35,600,0.949,bicubic -ig_resnext101_32x32d,85.092,14.908,97.436,2.564,468.53,224,0.875,bilinear -tf_efficientnet_b7,84.932,15.068,97.208,2.792,66.35,600,0.949,bicubic -tf_efficientnet_b6_ap,84.786,15.214,97.138,2.862,43.04,528,0.942,bicubic -swsl_resnext101_32x8d,84.294,15.706,97.174,2.826,88.79,224,0.875,bilinear -tf_efficientnet_b5_ap,84.254,15.746,96.976,3.024,30.39,456,0.934,bicubic -ig_resnext101_32x16d,84.176,15.824,97.196,2.804,194.03,224,0.875,bilinear -tf_efficientnet_b6,84.112,15.888,96.884,3.116,43.04,528,0.942,bicubic -tf_efficientnet_b5,83.816,16.184,96.75,3.25,30.39,456,0.934,bicubic -swsl_resnext101_32x16d,83.338,16.662,96.852,3.148,194.03,224,0.875,bilinear -tf_efficientnet_b4_ap,83.248,16.752,96.388,3.612,19.34,380,0.922,bicubic -swsl_resnext101_32x4d,83.234,16.766,96.756,3.244,44.18,224,0.875,bilinear -tf_efficientnet_b4,83.016,16.984,96.298,3.702,19.34,380,0.922,bicubic -pnasnet5large,82.74,17.26,96.04,3.96,86.06,331,0.875,bicubic -ig_resnext101_32x8d,82.688,17.312,96.632,3.368,88.79,224,0.875,bilinear -nasnetalarge,82.558,17.442,96.036,3.964,88.75,331,0.875,bicubic -swsl_resnext50_32x4d,82.18,17.82,96.228,3.772,25.03,224,0.875,bilinear -ssl_resnext101_32x16d,81.836,18.164,96.094,3.906,194.03,224,0.875,bilinear -tf_efficientnet_b3_ap,81.828,18.172,95.624,4.376,12.23,300,0.904,bicubic -tf_efficientnet_b3,81.64,18.36,95.722,4.278,12.23,300,0.904,bicubic -ssl_resnext101_32x8d,81.626,18.374,96.038,3.962,88.79,224,0.875,bilinear -senet154,81.304,18.696,95.498,4.502,115.09,224,0.875,bilinear -gluon_senet154,81.224,18.776,95.356,4.644,115.09,224,0.875,bicubic -swsl_resnet50,81.18,18.82,95.986,4.014,25.56,224,0.875,bilinear -gluon_resnet152_v1s,81.012,18.988,95.416,4.584,60.32,224,0.875,bicubic -ssl_resnext101_32x4d,80.928,19.072,95.728,4.272,44.18,224,0.875,bilinear -gluon_seresnext101_32x4d,80.902,19.098,95.294,4.706,48.96,224,0.875,bicubic -gluon_seresnext101_64x4d,80.89,19.11,95.304,4.696,88.23,224,0.875,bicubic -gluon_resnext101_64x4d,80.602,19.398,94.994,5.006,83.46,224,0.875,bicubic -gluon_resnet152_v1d,80.47,19.53,95.206,4.794,60.21,224,0.875,bicubic -inception_resnet_v2,80.46,19.54,95.31,4.69,55.84,299,0.8975,bicubic -tf_efficientnet_el,80.448,19.552,95.16,4.84,10.59,300,0.904,bicubic -gluon_resnet101_v1d,80.424,19.576,95.02,4.98,44.57,224,0.875,bicubic +ig_resnext101_32x48d,85.428,14.572,97.572,2.428,828.41,224,0.875,bilinear +tf_efficientnet_b8,85.37,14.63,97.39,2.61,87.41,672,0.954,bicubic +tf_efficientnet_b8_ap,85.37,14.63,97.294,2.706,87.41,672,0.954,bicubic +tf_efficientnet_b7_ap,85.12,14.88,97.252,2.748,66.35,600,0.949,bicubic +ig_resnext101_32x32d,85.094,14.906,97.438,2.562,468.53,224,0.875,bilinear +tf_efficientnet_b7,84.936,15.064,97.204,2.796,66.35,600,0.949,bicubic +tf_efficientnet_b6_ap,84.788,15.212,97.138,2.862,43.04,528,0.942,bicubic +swsl_resnext101_32x8d,84.284,15.716,97.176,2.824,88.79,224,0.875,bilinear +tf_efficientnet_b5_ap,84.252,15.748,96.974,3.026,30.39,456,0.934,bicubic +ig_resnext101_32x16d,84.17,15.83,97.196,2.804,194.03,224,0.875,bilinear +tf_efficientnet_b6,84.11,15.89,96.886,3.114,43.04,528,0.942,bicubic +tf_efficientnet_b5,83.812,16.188,96.748,3.252,30.39,456,0.934,bicubic +swsl_resnext101_32x16d,83.346,16.654,96.846,3.154,194.03,224,0.875,bilinear +tf_efficientnet_b4_ap,83.248,16.752,96.392,3.608,19.34,380,0.922,bicubic +swsl_resnext101_32x4d,83.23,16.77,96.76,3.24,44.18,224,0.875,bilinear +tf_efficientnet_b4,83.022,16.978,96.3,3.7,19.34,380,0.922,bicubic +pnasnet5large,82.736,17.264,96.046,3.954,86.06,331,0.875,bicubic +ig_resnext101_32x8d,82.688,17.312,96.636,3.364,88.79,224,0.875,bilinear +nasnetalarge,82.554,17.446,96.038,3.962,88.75,331,0.875,bicubic +swsl_resnext50_32x4d,82.182,17.818,96.23,3.77,25.03,224,0.875,bilinear +efficientnet_b3a,81.866,18.134,95.836,4.164,12.23,320,1,bicubic +ssl_resnext101_32x16d,81.844,18.156,96.096,3.904,194.03,224,0.875,bilinear +tf_efficientnet_b3_ap,81.822,18.178,95.624,4.376,12.23,300,0.904,bicubic +tf_efficientnet_b3,81.636,18.364,95.718,4.282,12.23,300,0.904,bicubic +ssl_resnext101_32x8d,81.616,18.384,96.038,3.962,88.79,224,0.875,bilinear +efficientnet_b3,81.494,18.506,95.716,4.284,12.23,300,0.904,bicubic +senet154,81.31,18.69,95.496,4.504,115.09,224,0.875,bilinear +gluon_senet154,81.234,18.766,95.348,4.652,115.09,224,0.875,bicubic +swsl_resnet50,81.166,18.834,95.972,4.028,25.56,224,0.875,bilinear +gluon_resnet152_v1s,81.016,18.984,95.412,4.588,60.32,224,0.875,bicubic +ssl_resnext101_32x4d,80.924,19.076,95.728,4.272,44.18,224,0.875,bilinear +gluon_seresnext101_32x4d,80.904,19.096,95.294,4.706,48.96,224,0.875,bicubic +gluon_seresnext101_64x4d,80.894,19.106,95.308,4.692,88.23,224,0.875,bicubic +efficientnet_b2a,80.612,19.388,95.318,4.682,9.11,288,1,bicubic +gluon_resnext101_64x4d,80.604,19.396,94.988,5.012,83.46,224,0.875,bicubic +mixnet_xl,80.476,19.524,94.936,5.064,11.9,224,0.875,bicubic +gluon_resnet152_v1d,80.474,19.526,95.206,4.794,60.21,224,0.875,bicubic +inception_resnet_v2,80.458,19.542,95.306,4.694,55.84,299,0.8975,bicubic +tf_efficientnet_el,80.44,19.56,95.164,4.836,10.59,300,0.904,bicubic +gluon_resnet101_v1d,80.414,19.586,95.014,4.986,44.57,224,0.875,bicubic +efficientnet_b2,80.392,19.608,95.076,4.924,9.11,260,0.875,bicubic gluon_resnext101_32x4d,80.334,19.666,94.926,5.074,44.18,224,0.875,bicubic -ssl_resnext50_32x4d,80.328,19.672,95.404,4.596,25.03,224,0.875,bilinear -tf_efficientnet_b2_ap,80.306,19.694,95.028,4.972,9.11,260,0.89,bicubic -gluon_resnet101_v1s,80.3,19.7,95.15,4.85,44.67,224,0.875,bicubic -seresnext101_32x4d,80.236,19.764,95.028,4.972,48.96,224,0.875,bilinear -dpn107,80.164,19.836,94.912,5.088,86.92,224,0.875,bicubic -inception_v4,80.156,19.844,94.974,5.026,42.68,299,0.875,bicubic -mixnet_xl,80.12,19.88,95.022,4.978,11.9,224,0.875,bicubic -tf_efficientnet_b2,80.09,19.91,94.906,5.094,9.11,260,0.89,bicubic -dpn92,80.016,19.984,94.838,5.162,37.67,224,0.875,bicubic -ens_adv_inception_resnet_v2,79.976,20.024,94.946,5.054,55.84,299,0.8975,bicubic -gluon_resnet152_v1c,79.916,20.084,94.842,5.158,60.21,224,0.875,bicubic -gluon_seresnext50_32x4d,79.912,20.088,94.818,5.182,27.56,224,0.875,bicubic -dpn131,79.828,20.172,94.704,5.296,79.25,224,0.875,bicubic -efficientnet_b2,79.752,20.248,94.71,5.29,9.11,260,0.89,bicubic -gluon_resnet152_v1b,79.692,20.308,94.738,5.262,60.19,224,0.875,bicubic -resnext50d_32x4d,79.674,20.326,94.868,5.132,25.05,224,0.875,bicubic -dpn98,79.636,20.364,94.594,5.406,61.57,224,0.875,bicubic -gluon_xception65,79.604,20.396,94.748,5.252,39.92,299,0.875,bicubic -gluon_resnet101_v1c,79.544,20.456,94.586,5.414,44.57,224,0.875,bicubic -hrnet_w64,79.472,20.528,94.65,5.35,128.06,224,0.875,bilinear -dla102x2,79.452,20.548,94.644,5.356,41.75,224,0.875,bilinear -gluon_resnext50_32x4d,79.356,20.644,94.424,5.576,25.03,224,0.875,bicubic -resnext101_32x8d,79.312,20.688,94.526,5.474,88.79,224,0.875,bilinear -hrnet_w48,79.31,20.69,94.52,5.48,77.47,224,0.875,bilinear -gluon_resnet101_v1b,79.304,20.696,94.524,5.476,44.55,224,0.875,bicubic -tf_efficientnet_cc_b1_8e,79.298,20.702,94.364,5.636,39.72,240,0.882,bicubic -tf_efficientnet_b1_ap,79.278,20.722,94.308,5.692,7.79,240,0.882,bicubic -ssl_resnet50,79.228,20.772,94.832,5.168,25.56,224,0.875,bilinear -res2net50_26w_8s,79.21,20.79,94.362,5.638,48.4,224,0.875,bilinear -res2net101_26w_4s,79.196,20.804,94.44,5.56,45.21,224,0.875,bilinear -seresnext50_32x4d,79.076,20.924,94.434,5.566,27.56,224,0.875,bilinear -gluon_resnet50_v1d,79.074,20.926,94.476,5.524,25.58,224,0.875,bicubic -xception,79.048,20.952,94.392,5.608,22.86,299,0.8975,bicubic -mixnet_l,78.976,21.024,94.184,5.816,7.33,224,0.875,bicubic -hrnet_w40,78.934,21.066,94.466,5.534,57.56,224,0.875,bilinear -hrnet_w44,78.894,21.106,94.37,5.63,67.06,224,0.875,bilinear -wide_resnet101_2,78.846,21.154,94.284,5.716,126.89,224,0.875,bilinear -tf_efficientnet_b1,78.832,21.168,94.196,5.804,7.79,240,0.882,bicubic -gluon_inception_v3,78.804,21.196,94.38,5.62,23.83,299,0.875,bicubic -tf_mixnet_l,78.77,21.23,94.004,5.996,7.33,224,0.875,bicubic -gluon_resnet50_v1s,78.712,21.288,94.242,5.758,25.68,224,0.875,bicubic -dla169,78.71,21.29,94.338,5.662,53.99,224,0.875,bilinear -tf_efficientnet_em,78.698,21.302,94.32,5.68,6.9,240,0.882,bicubic -efficientnet_b1,78.692,21.308,94.086,5.914,7.79,240,0.882,bicubic -seresnet152,78.658,21.342,94.374,5.626,66.82,224,0.875,bilinear -res2net50_26w_6s,78.574,21.426,94.126,5.874,37.05,224,0.875,bilinear -resnext50_32x4d,78.51,21.49,94.054,5.946,25.03,224,0.875,bicubic -dla102x,78.508,21.492,94.234,5.766,26.77,224,0.875,bilinear -dla60_res2net,78.472,21.528,94.204,5.796,21.15,224,0.875,bilinear -resnet50,78.47,21.53,94.266,5.734,25.56,224,0.875,bicubic -wide_resnet50_2,78.468,21.532,94.086,5.914,68.88,224,0.875,bilinear -dla60_res2next,78.448,21.552,94.144,5.856,17.33,224,0.875,bilinear -hrnet_w32,78.448,21.552,94.188,5.812,41.23,224,0.875,bilinear -seresnet101,78.396,21.604,94.258,5.742,49.33,224,0.875,bilinear -resnet152,78.312,21.688,94.046,5.954,60.19,224,0.875,bilinear -dla60x,78.242,21.758,94.022,5.978,17.65,224,0.875,bilinear -res2next50,78.242,21.758,93.892,6.108,24.67,224,0.875,bilinear -hrnet_w30,78.196,21.804,94.22,5.78,37.71,224,0.875,bilinear -res2net50_14w_8s,78.152,21.848,93.842,6.158,25.06,224,0.875,bilinear -dla102,78.026,21.974,93.95,6.05,33.73,224,0.875,bilinear +ssl_resnext50_32x4d,80.318,19.682,95.406,4.594,25.03,224,0.875,bilinear +gluon_resnet101_v1s,80.302,19.698,95.16,4.84,44.67,224,0.875,bicubic +tf_efficientnet_b2_ap,80.3,19.7,95.028,4.972,9.11,260,0.89,bicubic +seresnext101_32x4d,80.228,19.772,95.018,4.982,48.96,224,0.875,bilinear +inception_v4,80.168,19.832,94.968,5.032,42.68,299,0.875,bicubic +dpn107,80.156,19.844,94.91,5.09,86.92,224,0.875,bicubic +tf_efficientnet_b2,80.086,19.914,94.908,5.092,9.11,260,0.89,bicubic +dpn92,80.008,19.992,94.836,5.164,37.67,224,0.875,bicubic +ens_adv_inception_resnet_v2,79.982,20.018,94.938,5.062,55.84,299,0.8975,bicubic +gluon_seresnext50_32x4d,79.918,20.082,94.822,5.178,27.56,224,0.875,bicubic +gluon_resnet152_v1c,79.91,20.09,94.84,5.16,60.21,224,0.875,bicubic +dpn131,79.822,20.178,94.71,5.29,79.25,224,0.875,bicubic +gluon_resnet152_v1b,79.686,20.314,94.736,5.264,60.19,224,0.875,bicubic +resnext50d_32x4d,79.676,20.324,94.866,5.134,25.05,224,0.875,bicubic +dpn98,79.642,20.358,94.598,5.402,61.57,224,0.875,bicubic +gluon_xception65,79.588,20.412,94.756,5.244,39.92,299,0.875,bicubic +gluon_resnet101_v1c,79.534,20.466,94.578,5.422,44.57,224,0.875,bicubic +hrnet_w64,79.474,20.526,94.652,5.348,128.06,224,0.875,bilinear +dla102x2,79.448,20.552,94.64,5.36,41.75,224,0.875,bilinear +gluon_resnext50_32x4d,79.354,20.646,94.426,5.574,25.03,224,0.875,bicubic +resnext101_32x8d,79.308,20.692,94.518,5.482,88.79,224,0.875,bilinear +tf_efficientnet_cc_b1_8e,79.308,20.692,94.37,5.63,39.72,240,0.882,bicubic +gluon_resnet101_v1b,79.306,20.694,94.524,5.476,44.55,224,0.875,bicubic +hrnet_w48,79.3,20.7,94.512,5.488,77.47,224,0.875,bilinear +tf_efficientnet_b1_ap,79.28,20.72,94.306,5.694,7.79,240,0.882,bicubic +ssl_resnet50,79.222,20.778,94.832,5.168,25.56,224,0.875,bilinear +res2net50_26w_8s,79.198,20.802,94.368,5.632,48.4,224,0.875,bilinear +res2net101_26w_4s,79.198,20.802,94.432,5.568,45.21,224,0.875,bilinear +seresnext50_32x4d,79.078,20.922,94.436,5.564,27.56,224,0.875,bilinear +gluon_resnet50_v1d,79.074,20.926,94.47,5.53,25.58,224,0.875,bicubic +xception,79.052,20.948,94.392,5.608,22.86,299,0.8975,bicubic +resnet50,79.038,20.962,94.39,5.61,25.56,224,0.875,bicubic +mixnet_l,78.976,21.024,94.182,5.818,7.33,224,0.875,bicubic +hrnet_w40,78.92,21.08,94.47,5.53,57.56,224,0.875,bilinear +hrnet_w44,78.896,21.104,94.368,5.632,67.06,224,0.875,bilinear +wide_resnet101_2,78.856,21.144,94.282,5.718,126.89,224,0.875,bilinear +tf_efficientnet_b1,78.826,21.174,94.198,5.802,7.79,240,0.882,bicubic +gluon_inception_v3,78.806,21.194,94.37,5.63,23.83,299,0.875,bicubic +tf_mixnet_l,78.774,21.226,93.998,6.002,7.33,224,0.875,bicubic +gluon_resnet50_v1s,78.712,21.288,94.238,5.762,25.68,224,0.875,bicubic +tf_efficientnet_em,78.708,21.292,94.314,5.686,6.9,240,0.882,bicubic +efficientnet_b1,78.698,21.302,94.144,5.856,7.79,240,0.875,bicubic +dla169,78.688,21.312,94.336,5.664,53.99,224,0.875,bilinear +seresnet152,78.66,21.34,94.37,5.63,66.82,224,0.875,bilinear +res2net50_26w_6s,78.57,21.43,94.124,5.876,37.05,224,0.875,bilinear +resnext50_32x4d,78.512,21.488,94.042,5.958,25.03,224,0.875,bicubic +dla102x,78.51,21.49,94.228,5.772,26.77,224,0.875,bilinear +wide_resnet50_2,78.478,21.522,94.094,5.906,68.88,224,0.875,bilinear +dla60_res2net,78.464,21.536,94.206,5.794,21.15,224,0.875,bilinear +hrnet_w32,78.45,21.55,94.186,5.814,41.23,224,0.875,bilinear +dla60_res2next,78.44,21.56,94.152,5.848,17.33,224,0.875,bilinear +selecsls60b,78.412,21.588,94.174,5.826,32.77,224,0.875,bicubic +seresnet101,78.382,21.618,94.264,5.736,49.33,224,0.875,bilinear +resnet152,78.312,21.688,94.038,5.962,60.19,224,0.875,bilinear +dla60x,78.246,21.754,94.018,5.982,17.65,224,0.875,bilinear +res2next50,78.246,21.754,93.892,6.108,24.67,224,0.875,bilinear +hrnet_w30,78.206,21.794,94.222,5.778,37.71,224,0.875,bilinear +res2net50_14w_8s,78.15,21.85,93.848,6.152,25.06,224,0.875,bilinear +dla102,78.032,21.968,93.946,6.054,33.73,224,0.875,bilinear gluon_resnet50_v1c,78.012,21.988,93.988,6.012,25.58,224,0.875,bicubic -res2net50_26w_4s,77.946,22.054,93.852,6.148,25.7,224,0.875,bilinear -tf_efficientnet_cc_b0_8e,77.908,22.092,93.656,6.344,24.01,224,0.875,bicubic -tf_inception_v3,77.854,22.146,93.644,6.356,23.83,299,0.875,bicubic -seresnet50,77.636,22.364,93.752,6.248,28.09,224,0.875,bilinear -tv_resnext50_32x4d,77.618,22.382,93.698,6.302,25.03,224,0.875,bilinear -adv_inception_v3,77.58,22.42,93.724,6.276,23.83,299,0.875,bicubic -gluon_resnet50_v1b,77.578,22.422,93.718,6.282,25.56,224,0.875,bicubic -dpn68b,77.514,22.486,93.822,6.178,12.61,224,0.875,bicubic -res2net50_48w_2s,77.514,22.486,93.548,6.452,25.29,224,0.875,bilinear -inception_v3,77.436,22.564,93.476,6.524,27.16,299,0.875,bicubic -resnet101,77.374,22.626,93.546,6.454,44.55,224,0.875,bilinear -densenet161,77.348,22.652,93.648,6.352,28.68,224,0.875,bicubic -tf_efficientnet_cc_b0_4e,77.304,22.696,93.332,6.668,13.31,224,0.875,bicubic -densenet201,77.29,22.71,93.478,6.522,20.01,224,0.875,bicubic -tf_efficientnet_es,77.264,22.736,93.6,6.4,5.44,224,0.875,bicubic -mixnet_m,77.256,22.744,93.418,6.582,5.01,224,0.875,bicubic -seresnext26_32x4d,77.1,22.9,93.31,6.69,16.79,224,0.875,bicubic -tf_efficientnet_b0_ap,77.084,22.916,93.254,6.746,5.29,224,0.875,bicubic -dla60,77.022,22.978,93.308,6.692,22.33,224,0.875,bilinear -tf_mixnet_m,76.95,23.05,93.156,6.844,5.01,224,0.875,bicubic -efficientnet_b0,76.914,23.086,93.206,6.794,5.29,224,0.875,bicubic -tf_efficientnet_b0,76.84,23.16,93.226,6.774,5.29,224,0.875,bicubic -hrnet_w18,76.756,23.244,93.442,6.558,21.3,224,0.875,bilinear -resnet26d,76.68,23.32,93.166,6.834,16.01,224,0.875,bicubic -dpn68,76.306,23.694,92.97,7.03,12.61,224,0.875,bicubic -tv_resnet50,76.13,23.87,92.862,7.138,25.56,224,0.875,bilinear -mixnet_s,75.988,24.012,92.794,7.206,4.13,224,0.875,bicubic -densenet169,75.912,24.088,93.024,6.976,14.15,224,0.875,bicubic -tf_mixnet_s,75.648,24.352,92.636,7.364,4.13,224,0.875,bicubic -mobilenetv3_rw,75.628,24.372,92.708,7.292,5.48,224,0.875,bicubic -tf_mobilenetv3_large_100,75.516,24.484,92.6,7.4,5.48,224,0.875,bilinear -semnasnet_100,75.456,24.544,92.592,7.408,3.89,224,0.875,bicubic +seresnext26t_32x4d,77.998,22.002,93.708,6.292,16.82,224,0.875,bicubic +seresnext26tn_32x4d,77.986,22.014,93.746,6.254,16.81,224,0.875,bicubic +selecsls60,77.982,22.018,93.828,6.172,30.67,224,0.875,bicubic +res2net50_26w_4s,77.964,22.036,93.854,6.146,25.7,224,0.875,bilinear +tf_efficientnet_cc_b0_8e,77.908,22.092,93.654,6.346,24.01,224,0.875,bicubic +tf_inception_v3,77.86,22.14,93.64,6.36,23.83,299,0.875,bicubic +efficientnet_b0,77.698,22.302,93.532,6.468,5.29,224,0.875,bicubic +seresnet50,77.63,22.37,93.748,6.252,28.09,224,0.875,bilinear +tv_resnext50_32x4d,77.62,22.38,93.696,6.304,25.03,224,0.875,bilinear +seresnext26d_32x4d,77.602,22.398,93.608,6.392,16.81,224,0.875,bicubic +adv_inception_v3,77.582,22.418,93.736,6.264,23.83,299,0.875,bicubic +gluon_resnet50_v1b,77.58,22.42,93.716,6.284,25.56,224,0.875,bicubic +res2net50_48w_2s,77.522,22.478,93.554,6.446,25.29,224,0.875,bilinear +dpn68b,77.512,22.488,93.822,6.178,12.61,224,0.875,bicubic +inception_v3,77.438,22.562,93.474,6.526,27.16,299,0.875,bicubic +resnet101,77.374,22.626,93.54,6.46,44.55,224,0.875,bilinear +densenet161,77.358,22.642,93.638,6.362,28.68,224,0.875,bicubic +tf_efficientnet_cc_b0_4e,77.306,22.694,93.334,6.666,13.31,224,0.875,bicubic +densenet201,77.286,22.714,93.478,6.522,20.01,224,0.875,bicubic +mixnet_m,77.26,22.74,93.424,6.576,5.01,224,0.875,bicubic +tf_efficientnet_es,77.258,22.742,93.594,6.406,5.44,224,0.875,bicubic +selecsls42b,77.174,22.826,93.39,6.61,32.46,224,0.875,bicubic +seresnext26_32x4d,77.104,22.896,93.316,6.684,16.79,224,0.875,bicubic +tf_efficientnet_b0_ap,77.086,22.914,93.256,6.744,5.29,224,0.875,bicubic +dla60,77.032,22.968,93.318,6.682,22.33,224,0.875,bilinear +tf_mixnet_m,76.942,23.058,93.152,6.848,5.01,224,0.875,bicubic +tf_efficientnet_b0,76.848,23.152,93.228,6.772,5.29,224,0.875,bicubic +hrnet_w18,76.758,23.242,93.444,6.556,21.3,224,0.875,bilinear +resnet26d,76.696,23.304,93.15,6.85,16.01,224,0.875,bicubic +dpn68,76.318,23.682,92.978,7.022,12.61,224,0.875,bicubic +tv_resnet50,76.138,23.862,92.864,7.136,25.56,224,0.875,bilinear +mixnet_s,75.992,24.008,92.796,7.204,4.13,224,0.875,bicubic +densenet169,75.906,24.094,93.026,6.974,14.15,224,0.875,bicubic +tf_mixnet_s,75.65,24.35,92.63,7.37,4.13,224,0.875,bicubic +mobilenetv3_rw,75.634,24.366,92.708,7.292,5.48,224,0.875,bicubic +tf_mobilenetv3_large_100,75.518,24.482,92.606,7.394,5.48,224,0.875,bilinear +semnasnet_100,75.448,24.552,92.604,7.396,3.89,224,0.875,bicubic resnet26,75.292,24.708,92.57,7.43,16,224,0.875,bicubic -hrnet_w18_small_v2,75.126,24.874,92.416,7.584,15.6,224,0.875,bilinear -fbnetc_100,75.12,24.88,92.386,7.614,5.57,224,0.875,bilinear -resnet34,75.112,24.888,92.288,7.712,21.8,224,0.875,bilinear -seresnet34,74.808,25.192,92.126,7.874,21.96,224,0.875,bilinear -densenet121,74.752,25.248,92.152,7.848,7.98,224,0.875,bicubic -mnasnet_100,74.656,25.344,92.126,7.874,4.38,224,0.875,bicubic -dla34,74.636,25.364,92.064,7.936,15.78,224,0.875,bilinear -gluon_resnet34_v1b,74.58,25.42,91.988,8.012,21.8,224,0.875,bicubic -spnasnet_100,74.08,25.92,91.832,8.168,4.42,224,0.875,bilinear -tf_mobilenetv3_large_075,73.442,26.558,91.352,8.648,3.99,224,0.875,bilinear -tv_resnet34,73.314,26.686,91.42,8.58,21.8,224,0.875,bilinear -swsl_resnet18,73.286,26.714,91.732,8.268,11.69,224,0.875,bilinear -ssl_resnet18,72.6,27.4,91.416,8.584,11.69,224,0.875,bilinear -hrnet_w18_small,72.342,27.658,90.672,9.328,13.19,224,0.875,bilinear -tf_mobilenetv3_large_minimal_100,72.244,27.756,90.636,9.364,3.92,224,0.875,bilinear -seresnet18,71.758,28.242,90.334,9.666,11.78,224,0.875,bicubic -gluon_resnet18_v1b,70.83,29.17,89.756,10.244,11.69,224,0.875,bicubic -resnet18,69.758,30.242,89.078,10.922,11.69,224,0.875,bilinear -tf_mobilenetv3_small_100,67.918,32.082,87.662,12.338,2.54,224,0.875,bilinear -dla60x_c,67.906,32.094,88.434,11.566,1.34,224,0.875,bilinear -dla46x_c,65.98,34.02,86.98,13.02,1.08,224,0.875,bilinear -tf_mobilenetv3_small_075,65.718,34.282,86.136,13.864,2.04,224,0.875,bilinear -dla46_c,64.878,35.122,86.286,13.714,1.31,224,0.875,bilinear -tf_mobilenetv3_small_minimal_100,62.898,37.102,84.23,15.77,2.04,224,0.875,bilinear +fbnetc_100,75.124,24.876,92.386,7.614,5.57,224,0.875,bilinear +hrnet_w18_small_v2,75.114,24.886,92.416,7.584,15.6,224,0.875,bilinear +resnet34,75.11,24.89,92.284,7.716,21.8,224,0.875,bilinear +seresnet34,74.808,25.192,92.124,7.876,21.96,224,0.875,bilinear +densenet121,74.738,25.262,92.15,7.85,7.98,224,0.875,bicubic +mnasnet_100,74.658,25.342,92.114,7.886,4.38,224,0.875,bicubic +dla34,74.63,25.37,92.078,7.922,15.78,224,0.875,bilinear +gluon_resnet34_v1b,74.588,25.412,91.99,8.01,21.8,224,0.875,bicubic +spnasnet_100,74.084,25.916,91.818,8.182,4.42,224,0.875,bilinear +tf_mobilenetv3_large_075,73.438,26.562,91.35,8.65,3.99,224,0.875,bilinear +tv_resnet34,73.312,26.688,91.426,8.574,21.8,224,0.875,bilinear +swsl_resnet18,73.276,26.724,91.734,8.266,11.69,224,0.875,bilinear +ssl_resnet18,72.61,27.39,91.416,8.584,11.69,224,0.875,bilinear +hrnet_w18_small,72.342,27.658,90.678,9.322,13.19,224,0.875,bilinear +tf_mobilenetv3_large_minimal_100,72.248,27.752,90.63,9.37,3.92,224,0.875,bilinear +seresnet18,71.742,28.258,90.334,9.666,11.78,224,0.875,bicubic +gluon_resnet18_v1b,70.836,29.164,89.76,10.24,11.69,224,0.875,bicubic +resnet18,69.748,30.252,89.078,10.922,11.69,224,0.875,bilinear +tf_mobilenetv3_small_100,67.922,32.078,87.664,12.336,2.54,224,0.875,bilinear +dla60x_c,67.892,32.108,88.426,11.574,1.34,224,0.875,bilinear +dla46x_c,65.97,34.03,86.98,13.02,1.08,224,0.875,bilinear +tf_mobilenetv3_small_075,65.716,34.284,86.13,13.87,2.04,224,0.875,bilinear +dla46_c,64.866,35.134,86.292,13.708,1.31,224,0.875,bilinear +tf_mobilenetv3_small_minimal_100,62.906,37.094,84.23,15.77,2.04,224,0.875,bilinear diff --git a/results/results-imagenetv2-matched-frequency.csv b/results/results-imagenetv2-matched-frequency.csv index 3f791d6e..cc6f264c 100644 --- a/results/results-imagenetv2-matched-frequency.csv +++ b/results/results-imagenetv2-matched-frequency.csv @@ -1,155 +1,165 @@ -model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation -ig_resnext101_32x48d,76.87,23.13,93.32,6.68,828.41,224,0.875,bilinear -ig_resnext101_32x32d,76.84,23.16,93.19,6.81,468.53,224,0.875,bilinear -tf_efficientnet_b7_ap,76.09,23.91,92.97,7.03,66.35,600,0.949,bicubic -tf_efficientnet_b8_ap,76.09,23.91,92.73,7.27,87.41,672,0.954,bicubic -ig_resnext101_32x16d,75.71,24.29,92.9,7.1,194.03,224,0.875,bilinear -swsl_resnext101_32x8d,75.45,24.55,92.75,7.25,88.79,224,0.875,bilinear -tf_efficientnet_b6_ap,75.38,24.62,92.44,7.56,43.04,528,0.942,bicubic -tf_efficientnet_b7,74.72,25.28,92.22,7.78,66.35,600,0.949,bicubic -tf_efficientnet_b5_ap,74.59,25.41,91.99,8.01,30.39,456,0.934,bicubic -swsl_resnext101_32x4d,74.15,25.85,91.99,8.01,44.18,224,0.875,bilinear -swsl_resnext101_32x16d,74.01,25.99,92.17,7.83,194.03,224,0.875,bilinear -tf_efficientnet_b6,73.9,26.1,91.75,8.25,43.04,528,0.942,bicubic -ig_resnext101_32x8d,73.66,26.34,92.15,7.85,88.79,224,0.875,bilinear -tf_efficientnet_b5,73.54,26.46,91.46,8.54,30.39,456,0.934,bicubic -tf_efficientnet_b4_ap,72.89,27.11,90.98,9.02,19.34,380,0.922,bicubic -swsl_resnext50_32x4d,72.58,27.42,90.84,9.16,25.03,224,0.875,bilinear -pnasnet5large,72.37,27.63,90.26,9.74,86.06,331,0.875,bicubic -nasnetalarge,72.31,27.69,90.51,9.49,88.75,331,0.875,bicubic -tf_efficientnet_b4,72.28,27.72,90.6,9.4,19.34,380,0.922,bicubic -swsl_resnet50,71.69,28.31,90.51,9.49,25.56,224,0.875,bilinear -ssl_resnext101_32x8d,71.49,28.51,90.47,9.53,88.79,224,0.875,bilinear -ssl_resnext101_32x16d,71.4,28.6,90.55,9.45,194.03,224,0.875,bilinear -tf_efficientnet_b3_ap,70.92,29.08,89.43,10.57,12.23,300,0.904,bicubic -tf_efficientnet_b3,70.62,29.38,89.44,10.56,12.23,300,0.904,bicubic -gluon_senet154,70.6,29.4,88.92,11.08,115.09,224,0.875,bicubic -ssl_resnext101_32x4d,70.5,29.5,89.76,10.24,44.18,224,0.875,bilinear -senet154,70.48,29.52,88.99,11.01,115.09,224,0.875,bilinear -gluon_seresnext101_64x4d,70.44,29.56,89.35,10.65,88.23,224,0.875,bicubic -gluon_resnet152_v1s,70.32,29.68,88.87,11.13,60.32,224,0.875,bicubic -inception_resnet_v2,70.12,29.88,88.68,11.32,55.84,299,0.8975,bicubic -gluon_seresnext101_32x4d,70.01,29.99,88.91,11.09,48.96,224,0.875,bicubic -gluon_resnet152_v1d,69.95,30.05,88.47,11.53,60.21,224,0.875,bicubic -gluon_resnext101_64x4d,69.69,30.31,88.26,11.74,83.46,224,0.875,bicubic -ssl_resnext50_32x4d,69.69,30.31,89.42,10.58,25.03,224,0.875,bilinear -ens_adv_inception_resnet_v2,69.52,30.48,88.5,11.5,55.84,299,0.8975,bicubic -inception_v4,69.35,30.65,88.78,11.22,42.68,299,0.875,bicubic -seresnext101_32x4d,69.34,30.66,88.05,11.95,48.96,224,0.875,bilinear -gluon_resnet152_v1c,69.13,30.87,87.89,12.11,60.21,224,0.875,bicubic -mixnet_xl,69,31,88.19,11.81,11.9,224,0.875,bicubic -gluon_resnet101_v1d,68.99,31.01,88.08,11.92,44.57,224,0.875,bicubic -gluon_xception65,68.98,31.02,88.32,11.68,39.92,299,0.875,bicubic -gluon_resnext101_32x4d,68.96,31.04,88.34,11.66,44.18,224,0.875,bicubic -tf_efficientnet_b2_ap,68.93,31.07,88.34,11.66,9.11,260,0.89,bicubic -gluon_resnet152_v1b,68.81,31.19,87.71,12.29,60.19,224,0.875,bicubic -dpn131,68.76,31.24,87.48,12.52,79.25,224,0.875,bicubic -resnext50d_32x4d,68.75,31.25,88.31,11.69,25.05,224,0.875,bicubic -tf_efficientnet_b2,68.75,31.25,87.95,12.05,9.11,260,0.89,bicubic -gluon_resnet101_v1s,68.72,31.28,87.9,12.1,44.67,224,0.875,bicubic -dpn107,68.71,31.29,88.13,11.87,86.92,224,0.875,bicubic -gluon_seresnext50_32x4d,68.67,31.33,88.32,11.68,27.56,224,0.875,bicubic -hrnet_w64,68.63,31.37,88.07,11.93,128.06,224,0.875,bilinear -dpn98,68.58,31.42,87.66,12.34,61.57,224,0.875,bicubic -ssl_resnet50,68.42,31.58,88.58,11.42,25.56,224,0.875,bilinear -dla102x2,68.34,31.66,87.87,12.13,41.75,224,0.875,bilinear -gluon_resnext50_32x4d,68.28,31.72,87.32,12.68,25.03,224,0.875,bicubic -tf_efficientnet_el,68.18,31.82,88.35,11.65,10.59,300,0.904,bicubic -dpn92,68.01,31.99,87.59,12.41,37.67,224,0.875,bicubic -gluon_resnet50_v1d,67.91,32.09,87.12,12.88,25.58,224,0.875,bicubic -seresnext50_32x4d,67.87,32.13,87.62,12.38,27.56,224,0.875,bilinear -resnext101_32x8d,67.85,32.15,87.48,12.52,88.79,224,0.875,bilinear -efficientnet_b2,67.8,32.2,88.2,11.8,9.11,260,0.89,bicubic -hrnet_w44,67.77,32.23,87.53,12.47,67.06,224,0.875,bilinear -hrnet_w48,67.77,32.23,87.42,12.58,77.47,224,0.875,bilinear -xception,67.67,32.33,87.57,12.43,22.86,299,0.8975,bicubic -dla169,67.61,32.39,87.56,12.44,53.99,224,0.875,bilinear -gluon_inception_v3,67.59,32.41,87.46,12.54,23.83,299,0.875,bicubic -hrnet_w40,67.59,32.41,87.13,12.87,57.56,224,0.875,bilinear -gluon_resnet101_v1c,67.56,32.44,87.16,12.84,44.57,224,0.875,bicubic -efficientnet_b1,67.55,32.45,87.29,12.71,7.79,240,0.882,bicubic -seresnet152,67.55,32.45,87.39,12.61,66.82,224,0.875,bilinear -res2net50_26w_8s,67.53,32.47,87.27,12.73,48.4,224,0.875,bilinear -tf_efficientnet_b1_ap,67.52,32.48,87.77,12.23,7.79,240,0.882,bicubic -tf_efficientnet_cc_b1_8e,67.48,32.52,87.31,12.69,39.72,240,0.882,bicubic -gluon_resnet101_v1b,67.45,32.55,87.23,12.77,44.55,224,0.875,bicubic -res2net101_26w_4s,67.45,32.55,87.01,12.99,45.21,224,0.875,bilinear -seresnet101,67.15,32.85,87.05,12.95,49.33,224,0.875,bilinear -gluon_resnet50_v1s,67.1,32.9,86.86,13.14,25.68,224,0.875,bicubic -dla60x,67.08,32.92,87.17,12.83,17.65,224,0.875,bilinear -dla60_res2net,67.03,32.97,87.14,12.86,21.15,224,0.875,bilinear -resnet152,67.02,32.98,87.57,12.43,60.19,224,0.875,bilinear -dla102x,67,33,86.77,13.23,26.77,224,0.875,bilinear -mixnet_l,66.97,33.03,86.94,13.06,7.33,224,0.875,bicubic -res2net50_26w_6s,66.91,33.09,86.9,13.1,37.05,224,0.875,bilinear -tf_efficientnet_b1,66.89,33.11,87.04,12.96,7.79,240,0.882,bicubic -resnext50_32x4d,66.88,33.12,86.36,13.64,25.03,224,0.875,bicubic -tf_efficientnet_em,66.87,33.13,86.98,13.02,6.9,240,0.882,bicubic -resnet50,66.81,33.19,87,13,25.56,224,0.875,bicubic -hrnet_w32,66.79,33.21,87.29,12.71,41.23,224,0.875,bilinear -tf_mixnet_l,66.78,33.22,86.46,13.54,7.33,224,0.875,bicubic -hrnet_w30,66.76,33.24,86.79,13.21,37.71,224,0.875,bilinear -wide_resnet101_2,66.68,33.32,87.04,12.96,126.89,224,0.875,bilinear -wide_resnet50_2,66.65,33.35,86.81,13.19,68.88,224,0.875,bilinear -dla60_res2next,66.64,33.36,87.02,12.98,17.33,224,0.875,bilinear -adv_inception_v3,66.6,33.4,86.56,13.44,23.83,299,0.875,bicubic -dla102,66.55,33.45,86.91,13.09,33.73,224,0.875,bilinear -gluon_resnet50_v1c,66.54,33.46,86.16,13.84,25.58,224,0.875,bicubic -tf_inception_v3,66.42,33.58,86.68,13.32,23.83,299,0.875,bicubic -seresnet50,66.24,33.76,86.33,13.67,28.09,224,0.875,bilinear -tf_efficientnet_cc_b0_8e,66.21,33.79,86.22,13.78,24.01,224,0.875,bicubic -tv_resnext50_32x4d,66.18,33.82,86.04,13.96,25.03,224,0.875,bilinear -res2net50_26w_4s,66.17,33.83,86.6,13.4,25.7,224,0.875,bilinear -inception_v3,66.12,33.88,86.34,13.66,27.16,299,0.875,bicubic -gluon_resnet50_v1b,66.04,33.96,86.27,13.73,25.56,224,0.875,bicubic -res2net50_14w_8s,66.02,33.98,86.24,13.76,25.06,224,0.875,bilinear -densenet161,65.85,34.15,86.46,13.54,28.68,224,0.875,bicubic -res2next50,65.85,34.15,85.83,14.17,24.67,224,0.875,bilinear -resnet101,65.68,34.32,85.98,14.02,44.55,224,0.875,bilinear -dpn68b,65.6,34.4,85.94,14.06,12.61,224,0.875,bicubic -tf_efficientnet_b0_ap,65.49,34.51,85.55,14.45,5.29,224,0.875,bicubic -res2net50_48w_2s,65.32,34.68,85.96,14.04,25.29,224,0.875,bilinear -densenet201,65.28,34.72,85.67,14.33,20.01,224,0.875,bicubic -tf_efficientnet_es,65.24,34.76,85.54,14.46,5.44,224,0.875,bicubic -dla60,65.22,34.78,85.75,14.25,22.33,224,0.875,bilinear -tf_efficientnet_cc_b0_4e,65.13,34.87,85.13,14.87,13.31,224,0.875,bicubic -seresnext26_32x4d,65.04,34.96,85.65,14.35,16.79,224,0.875,bicubic -hrnet_w18,64.91,35.09,85.75,14.25,21.3,224,0.875,bilinear -densenet169,64.78,35.22,85.25,14.75,14.15,224,0.875,bicubic -mixnet_m,64.69,35.31,85.47,14.53,5.01,224,0.875,bicubic -resnet26d,64.63,35.37,85.12,14.88,16.01,224,0.875,bicubic -efficientnet_b0,64.58,35.42,85.89,14.11,5.29,224,0.875,bicubic -tf_efficientnet_b0,64.29,35.71,85.25,14.75,5.29,224,0.875,bicubic -tf_mixnet_m,64.27,35.73,85.09,14.91,5.01,224,0.875,bicubic -dpn68,64.22,35.78,85.18,14.82,12.61,224,0.875,bicubic -tf_mixnet_s,63.59,36.41,84.27,15.73,4.13,224,0.875,bicubic -resnet26,63.45,36.55,84.27,15.73,16,224,0.875,bicubic -mixnet_s,63.38,36.62,84.71,15.29,4.13,224,0.875,bicubic -tv_resnet50,63.33,36.67,84.65,15.35,25.56,224,0.875,bilinear -mobilenetv3_rw,63.23,36.77,84.52,15.48,5.48,224,0.875,bicubic -semnasnet_100,63.12,36.88,84.53,15.47,3.89,224,0.875,bicubic -densenet121,62.94,37.06,84.26,15.74,7.98,224,0.875,bicubic -seresnet34,62.89,37.11,84.22,15.78,21.96,224,0.875,bilinear -hrnet_w18_small_v2,62.83,37.17,83.97,16.03,15.6,224,0.875,bilinear -resnet34,62.82,37.18,84.12,15.88,21.8,224,0.875,bilinear -swsl_resnet18,62.73,37.27,84.3,15.7,11.69,224,0.875,bilinear -gluon_resnet34_v1b,62.56,37.44,84,16,21.8,224,0.875,bicubic -dla34,62.51,37.49,83.92,16.08,15.78,224,0.875,bilinear -tf_mobilenetv3_large_100,62.47,37.53,83.96,16.04,5.48,224,0.875,bilinear -fbnetc_100,62.43,37.57,83.39,16.61,5.57,224,0.875,bilinear -mnasnet_100,61.91,38.09,83.71,16.29,4.38,224,0.875,bicubic -ssl_resnet18,61.49,38.51,83.33,16.67,11.69,224,0.875,bilinear -spnasnet_100,61.21,38.79,82.77,17.23,4.42,224,0.875,bilinear -tv_resnet34,61.2,38.8,82.72,17.28,21.8,224,0.875,bilinear -tf_mobilenetv3_large_075,60.38,39.62,81.96,18.04,3.99,224,0.875,bilinear -seresnet18,59.81,40.19,81.68,18.32,11.78,224,0.875,bicubic -tf_mobilenetv3_large_minimal_100,59.07,40.93,81.14,18.86,3.92,224,0.875,bilinear -hrnet_w18_small,58.97,41.03,81.34,18.66,13.19,224,0.875,bilinear -gluon_resnet18_v1b,58.32,41.68,80.96,19.04,11.69,224,0.875,bicubic -resnet18,57.18,42.82,80.19,19.81,11.69,224,0.875,bilinear -dla60x_c,56.02,43.98,78.96,21.04,1.34,224,0.875,bilinear -tf_mobilenetv3_small_100,54.51,45.49,77.08,22.92,2.54,224,0.875,bilinear -dla46x_c,53.08,46.92,76.84,23.16,1.08,224,0.875,bilinear -dla46_c,52.2,47.8,75.68,24.32,1.31,224,0.875,bilinear -tf_mobilenetv3_small_075,52.15,47.85,75.46,24.54,2.04,224,0.875,bilinear -tf_mobilenetv3_small_minimal_100,49.53,50.47,73.05,26.95,2.04,224,0.875,bilinear +model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation +ig_resnext101_32x48d,76.87,23.13,93.31,6.69,828.41,224,0.875,bilinear +ig_resnext101_32x32d,76.84,23.16,93.2,6.8,468.53,224,0.875,bilinear +tf_efficientnet_b7_ap,76.09,23.91,92.97,7.03,66.35,600,0.949,bicubic +tf_efficientnet_b8_ap,76.09,23.91,92.73,7.27,87.41,672,0.954,bicubic +ig_resnext101_32x16d,75.72,24.28,92.91,7.09,194.03,224,0.875,bilinear +swsl_resnext101_32x8d,75.43,24.57,92.76,7.24,88.79,224,0.875,bilinear +tf_efficientnet_b6_ap,75.38,24.62,92.44,7.56,43.04,528,0.942,bicubic +tf_efficientnet_b8,74.94,25.06,92.31,7.69,87.41,672,0.954,bicubic +tf_efficientnet_b7,74.72,25.28,92.22,7.78,66.35,600,0.949,bicubic +tf_efficientnet_b5_ap,74.6,25.4,91.99,8.01,30.39,456,0.934,bicubic +swsl_resnext101_32x4d,74.14,25.86,91.99,8.01,44.18,224,0.875,bilinear +swsl_resnext101_32x16d,74.02,25.98,92.16,7.84,194.03,224,0.875,bilinear +tf_efficientnet_b6,73.9,26.1,91.75,8.25,43.04,528,0.942,bicubic +ig_resnext101_32x8d,73.65,26.35,92.19,7.81,88.79,224,0.875,bilinear +tf_efficientnet_b5,73.55,26.45,91.46,8.54,30.39,456,0.934,bicubic +tf_efficientnet_b4_ap,72.89,27.11,90.98,9.02,19.34,380,0.922,bicubic +swsl_resnext50_32x4d,72.56,27.44,90.87,9.13,25.03,224,0.875,bilinear +pnasnet5large,72.38,27.62,90.24,9.76,86.06,331,0.875,bicubic +nasnetalarge,72.32,27.68,90.53,9.47,88.75,331,0.875,bicubic +tf_efficientnet_b4,72.29,27.71,90.59,9.41,19.34,380,0.922,bicubic +swsl_resnet50,71.7,28.3,90.5,9.5,25.56,224,0.875,bilinear +ssl_resnext101_32x8d,71.5,28.5,90.46,9.54,88.79,224,0.875,bilinear +ssl_resnext101_32x16d,71.41,28.59,90.56,9.44,194.03,224,0.875,bilinear +tf_efficientnet_b3_ap,70.92,29.08,89.43,10.57,12.23,300,0.904,bicubic +efficientnet_b3a,70.87,29.13,89.72,10.28,12.23,320,1.0,bicubic +efficientnet_b3,70.76,29.24,89.85,10.15,12.23,300,0.904,bicubic +tf_efficientnet_b3,70.64,29.36,89.44,10.56,12.23,300,0.904,bicubic +gluon_senet154,70.6,29.4,88.92,11.08,115.09,224,0.875,bicubic +ssl_resnext101_32x4d,70.53,29.47,89.76,10.24,44.18,224,0.875,bilinear +senet154,70.5,29.5,89.01,10.99,115.09,224,0.875,bilinear +gluon_seresnext101_64x4d,70.43,29.57,89.35,10.65,88.23,224,0.875,bicubic +gluon_resnet152_v1s,70.29,29.71,88.85,11.15,60.32,224,0.875,bicubic +inception_resnet_v2,70.12,29.88,88.69,11.31,55.84,299,0.8975,bicubic +gluon_seresnext101_32x4d,70.01,29.99,88.9,11.1,48.96,224,0.875,bicubic +gluon_resnet152_v1d,69.96,30.04,88.49,11.51,60.21,224,0.875,bicubic +ssl_resnext50_32x4d,69.71,30.29,89.44,10.56,25.03,224,0.875,bilinear +gluon_resnext101_64x4d,69.68,30.32,88.27,11.73,83.46,224,0.875,bicubic +ens_adv_inception_resnet_v2,69.52,30.48,88.51,11.49,55.84,299,0.8975,bicubic +efficientnet_b2a,69.5,30.5,88.68,11.32,9.11,288,1.0,bicubic +inception_v4,69.36,30.64,88.78,11.22,42.68,299,0.875,bicubic +seresnext101_32x4d,69.36,30.64,88.07,11.93,48.96,224,0.875,bilinear +gluon_resnet152_v1c,69.14,30.86,87.87,12.13,60.21,224,0.875,bicubic +mixnet_xl,69.1,30.9,88.31,11.69,11.9,224,0.875,bicubic +gluon_resnet101_v1d,69.01,30.99,88.1,11.9,44.57,224,0.875,bicubic +efficientnet_b2,68.97,31.03,88.63,11.37,9.11,260,0.875,bicubic +gluon_resnext101_32x4d,68.96,31.04,88.36,11.64,44.18,224,0.875,bicubic +gluon_xception65,68.92,31.08,88.33,11.67,39.92,299,0.875,bicubic +tf_efficientnet_b2_ap,68.92,31.08,88.35,11.65,9.11,260,0.89,bicubic +gluon_resnet152_v1b,68.82,31.18,87.71,12.29,60.19,224,0.875,bicubic +dpn131,68.77,31.23,87.47,12.53,79.25,224,0.875,bicubic +tf_efficientnet_b2,68.75,31.25,87.99,12.01,9.11,260,0.89,bicubic +resnext50d_32x4d,68.74,31.26,88.3,11.7,25.05,224,0.875,bicubic +gluon_resnet101_v1s,68.71,31.29,87.91,12.09,44.67,224,0.875,bicubic +dpn107,68.69,31.31,88.13,11.87,86.92,224,0.875,bicubic +gluon_seresnext50_32x4d,68.67,31.33,88.31,11.69,27.56,224,0.875,bicubic +hrnet_w64,68.64,31.36,88.05,11.95,128.06,224,0.875,bilinear +dpn98,68.59,31.41,87.68,12.32,61.57,224,0.875,bicubic +ssl_resnet50,68.41,31.59,88.56,11.44,25.56,224,0.875,bilinear +dla102x2,68.33,31.67,87.89,12.11,41.75,224,0.875,bilinear +gluon_resnext50_32x4d,68.31,31.69,87.3,12.7,25.03,224,0.875,bicubic +tf_efficientnet_el,68.18,31.82,88.35,11.65,10.59,300,0.904,bicubic +dpn92,67.99,32.01,87.58,12.42,37.67,224,0.875,bicubic +gluon_resnet50_v1d,67.94,32.06,87.13,12.87,25.58,224,0.875,bicubic +resnext101_32x8d,67.86,32.14,87.49,12.51,88.79,224,0.875,bilinear +seresnext50_32x4d,67.84,32.16,87.62,12.38,27.56,224,0.875,bilinear +hrnet_w48,67.77,32.23,87.42,12.58,77.47,224,0.875,bilinear +hrnet_w44,67.74,32.26,87.56,12.44,67.06,224,0.875,bilinear +xception,67.65,32.35,87.57,12.43,22.86,299,0.8975,bicubic +dla169,67.61,32.39,87.59,12.41,53.99,224,0.875,bilinear +gluon_inception_v3,67.59,32.41,87.47,12.53,23.83,299,0.875,bicubic +gluon_resnet101_v1c,67.58,32.42,87.18,12.82,44.57,224,0.875,bicubic +res2net50_26w_8s,67.57,32.43,87.28,12.72,48.4,224,0.875,bilinear +hrnet_w40,67.56,32.44,87.14,12.86,57.56,224,0.875,bilinear +seresnet152,67.52,32.48,87.39,12.61,66.82,224,0.875,bilinear +tf_efficientnet_b1_ap,67.52,32.48,87.76,12.24,7.79,240,0.882,bicubic +gluon_resnet101_v1b,67.46,32.54,87.24,12.76,44.55,224,0.875,bicubic +tf_efficientnet_cc_b1_8e,67.45,32.55,87.31,12.69,39.72,240,0.882,bicubic +res2net101_26w_4s,67.44,32.56,87.01,12.99,45.21,224,0.875,bilinear +resnet50,67.44,32.56,87.42,12.58,25.56,224,0.875,bicubic +efficientnet_b1,67.17,32.83,87.15,12.85,7.79,240,0.875,bicubic +seresnet101,67.16,32.84,87.06,12.94,49.33,224,0.875,bilinear +dla60x,67.1,32.9,87.19,12.81,17.65,224,0.875,bilinear +gluon_resnet50_v1s,67.06,32.94,86.86,13.14,25.68,224,0.875,bicubic +resnet152,67.05,32.95,87.55,12.45,60.19,224,0.875,bilinear +dla60_res2net,67.02,32.98,87.16,12.84,21.15,224,0.875,bilinear +dla102x,67.01,32.99,86.77,13.23,26.77,224,0.875,bilinear +mixnet_l,66.94,33.06,86.91,13.09,7.33,224,0.875,bicubic +res2net50_26w_6s,66.91,33.09,86.86,13.14,37.05,224,0.875,bilinear +tf_efficientnet_b1,66.88,33.12,87.01,12.99,7.79,240,0.882,bicubic +tf_efficientnet_em,66.88,33.12,86.97,13.03,6.9,240,0.882,bicubic +resnext50_32x4d,66.87,33.13,86.34,13.66,25.03,224,0.875,bicubic +hrnet_w30,66.78,33.22,86.8,13.2,37.71,224,0.875,bilinear +tf_mixnet_l,66.78,33.22,86.47,13.53,7.33,224,0.875,bicubic +selecsls60b,66.76,33.24,86.53,13.47,32.77,224,0.875,bicubic +hrnet_w32,66.75,33.25,87.3,12.7,41.23,224,0.875,bilinear +wide_resnet101_2,66.73,33.27,87.03,12.97,126.89,224,0.875,bilinear +adv_inception_v3,66.65,33.35,86.53,13.47,23.83,299,0.875,bicubic +wide_resnet50_2,66.65,33.35,86.8,13.2,68.88,224,0.875,bilinear +dla60_res2next,66.64,33.36,87.03,12.97,17.33,224,0.875,bilinear +gluon_resnet50_v1c,66.56,33.44,86.18,13.82,25.58,224,0.875,bicubic +dla102,66.54,33.46,86.91,13.09,33.73,224,0.875,bilinear +tf_inception_v3,66.41,33.59,86.66,13.34,23.83,299,0.875,bicubic +efficientnet_b0,66.29,33.71,85.96,14.04,5.29,224,0.875,bicubic +seresnet50,66.25,33.75,86.33,13.67,28.09,224,0.875,bilinear +selecsls60,66.21,33.79,86.34,13.66,30.67,224,0.875,bicubic +tv_resnext50_32x4d,66.18,33.82,86.04,13.96,25.03,224,0.875,bilinear +tf_efficientnet_cc_b0_8e,66.17,33.83,86.24,13.76,24.01,224,0.875,bicubic +inception_v3,66.15,33.85,86.33,13.67,27.16,299,0.875,bicubic +res2net50_26w_4s,66.14,33.86,86.6,13.4,25.7,224,0.875,bilinear +gluon_resnet50_v1b,66.07,33.93,86.26,13.74,25.56,224,0.875,bicubic +res2net50_14w_8s,66.02,33.98,86.25,13.75,25.06,224,0.875,bilinear +seresnext26tn_32x4d,65.88,34.12,85.68,14.32,16.81,224,0.875,bicubic +res2next50,65.85,34.15,85.84,14.16,24.67,224,0.875,bilinear +densenet161,65.84,34.16,86.45,13.55,28.68,224,0.875,bicubic +resnet101,65.69,34.31,85.98,14.02,44.55,224,0.875,bilinear +selecsls42b,65.61,34.39,85.81,14.19,32.46,224,0.875,bicubic +seresnext26t_32x4d,65.6,34.4,86.08,13.92,16.82,224,0.875,bicubic +dpn68b,65.57,34.43,85.93,14.07,12.61,224,0.875,bicubic +tf_efficientnet_b0_ap,65.49,34.51,85.58,14.42,5.29,224,0.875,bicubic +seresnext26d_32x4d,65.41,34.59,85.97,14.03,16.81,224,0.875,bicubic +res2net50_48w_2s,65.35,34.65,85.96,14.04,25.29,224,0.875,bilinear +densenet201,65.29,34.71,85.69,14.31,20.01,224,0.875,bicubic +tf_efficientnet_es,65.22,34.78,85.55,14.45,5.44,224,0.875,bicubic +dla60,65.2,34.8,85.76,14.24,22.33,224,0.875,bilinear +tf_efficientnet_cc_b0_4e,65.15,34.85,85.16,14.84,13.31,224,0.875,bicubic +seresnext26_32x4d,65.05,34.95,85.66,14.34,16.79,224,0.875,bicubic +hrnet_w18,64.92,35.08,85.74,14.26,21.3,224,0.875,bilinear +densenet169,64.76,35.24,85.24,14.76,14.15,224,0.875,bicubic +mixnet_m,64.7,35.3,85.45,14.55,5.01,224,0.875,bicubic +resnet26d,64.68,35.32,85.12,14.88,16.01,224,0.875,bicubic +tf_efficientnet_b0,64.31,35.69,85.28,14.72,5.29,224,0.875,bicubic +tf_mixnet_m,64.27,35.73,85.09,14.91,5.01,224,0.875,bicubic +dpn68,64.23,35.77,85.18,14.82,12.61,224,0.875,bicubic +tf_mixnet_s,63.56,36.44,84.27,15.73,4.13,224,0.875,bicubic +resnet26,63.47,36.53,84.26,15.74,16.0,224,0.875,bicubic +mixnet_s,63.39,36.61,84.74,15.26,4.13,224,0.875,bicubic +tv_resnet50,63.33,36.67,84.64,15.36,25.56,224,0.875,bilinear +mobilenetv3_rw,63.22,36.78,84.51,15.49,5.48,224,0.875,bicubic +semnasnet_100,63.15,36.85,84.52,15.48,3.89,224,0.875,bicubic +densenet121,62.94,37.06,84.25,15.75,7.98,224,0.875,bicubic +resnet34,62.87,37.13,84.14,15.86,21.8,224,0.875,bilinear +seresnet34,62.85,37.15,84.21,15.79,21.96,224,0.875,bilinear +hrnet_w18_small_v2,62.8,37.2,83.98,16.02,15.6,224,0.875,bilinear +swsl_resnet18,62.76,37.24,84.3,15.7,11.69,224,0.875,bilinear +gluon_resnet34_v1b,62.57,37.43,83.99,16.01,21.8,224,0.875,bicubic +dla34,62.48,37.52,83.91,16.09,15.78,224,0.875,bilinear +tf_mobilenetv3_large_100,62.46,37.54,83.97,16.03,5.48,224,0.875,bilinear +fbnetc_100,62.44,37.56,83.38,16.62,5.57,224,0.875,bilinear +mnasnet_100,61.9,38.1,83.71,16.29,4.38,224,0.875,bicubic +ssl_resnet18,61.48,38.52,83.3,16.7,11.69,224,0.875,bilinear +spnasnet_100,61.22,38.78,82.79,17.21,4.42,224,0.875,bilinear +tv_resnet34,61.19,38.81,82.71,17.29,21.8,224,0.875,bilinear +tf_mobilenetv3_large_075,60.4,39.6,81.95,18.05,3.99,224,0.875,bilinear +seresnet18,59.8,40.2,81.69,18.31,11.78,224,0.875,bicubic +tf_mobilenetv3_large_minimal_100,59.07,40.93,81.15,18.85,3.92,224,0.875,bilinear +hrnet_w18_small,58.95,41.05,81.34,18.66,13.19,224,0.875,bilinear +gluon_resnet18_v1b,58.34,41.66,80.97,19.03,11.69,224,0.875,bicubic +resnet18,57.17,42.83,80.2,19.8,11.69,224,0.875,bilinear +dla60x_c,56.0,44.0,78.93,21.07,1.34,224,0.875,bilinear +tf_mobilenetv3_small_100,54.53,45.47,77.06,22.94,2.54,224,0.875,bilinear +dla46x_c,53.05,46.95,76.87,23.13,1.08,224,0.875,bilinear +tf_mobilenetv3_small_075,52.16,47.84,75.47,24.53,2.04,224,0.875,bilinear +dla46_c,52.13,47.87,75.69,24.31,1.31,224,0.875,bilinear +tf_mobilenetv3_small_minimal_100,49.5,50.5,73.05,26.95,2.04,224,0.875,bilinear diff --git a/results/results-sketch.csv b/results/results-sketch.csv new file mode 100644 index 00000000..b1a0ea66 --- /dev/null +++ b/results/results-sketch.csv @@ -0,0 +1,165 @@ +model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation +ig_resnext101_32x48d,58.8104,41.1896,81.0765,18.9235,828.41,224,0.875,bilinear +ig_resnext101_32x32d,58.3859,41.6141,80.3808,19.6192,468.53,224,0.875,bilinear +ig_resnext101_32x16d,57.6903,42.3097,79.9053,20.0947,194.03,224,0.875,bilinear +swsl_resnext101_32x16d,57.4584,42.5416,80.3848,19.6152,194.03,224,0.875,bilinear +swsl_resnext101_32x8d,56.4385,43.5615,78.9444,21.0556,88.79,224,0.875,bilinear +ig_resnext101_32x8d,54.9176,45.0824,77.5335,22.4665,88.79,224,0.875,bilinear +swsl_resnext101_32x4d,53.6029,46.3971,76.3466,23.6534,44.18,224,0.875,bilinear +swsl_resnext50_32x4d,50.4372,49.5628,73.3675,26.6325,25.03,224,0.875,bilinear +swsl_resnet50,49.5412,50.4588,72.3339,27.6661,25.56,224,0.875,bilinear +tf_efficientnet_b8_ap,45.7741,54.2259,67.9106,32.0894,87.41,672,0.954,bicubic +tf_efficientnet_b8,42.508,57.492,64.857,35.143,87.41,672,0.954,bicubic +tf_efficientnet_b7,41.4314,58.5686,63.0175,36.9825,66.35,600,0.949,bicubic +tf_efficientnet_b7_ap,41.4294,58.5706,62.8741,37.1259,66.35,600,0.949,bicubic +tf_efficientnet_b5_ap,41.4176,58.5824,62.0841,37.9159,30.39,456,0.934,bicubic +tf_efficientnet_b6_ap,41.0993,58.9007,62.3553,37.6447,43.04,528,0.942,bicubic +tf_efficientnet_b4_ap,40.4842,59.5158,61.7226,38.2774,19.34,380,0.922,bicubic +tf_efficientnet_b5,38.356,61.644,59.9128,40.0872,30.39,456,0.934,bicubic +tf_efficientnet_b3_ap,37.0552,62.9448,57.2403,42.7597,12.23,300,0.904,bicubic +swsl_resnet18,35.8584,64.1416,58.4547,41.5453,11.69,224,0.875,bilinear +ssl_resnext101_32x16d,34.6028,65.3972,55.9315,44.0685,194.03,224,0.875,bilinear +tf_efficientnet_b4,34.0643,65.9357,54.1984,45.8016,19.34,380,0.922,bicubic +ssl_resnext101_32x8d,34.0172,65.9828,55.6014,44.3986,88.79,224,0.875,bilinear +tf_efficientnet_b6,33.9975,66.0025,54.5442,45.4558,43.04,528,0.942,bicubic +tf_efficientnet_b3,32.8598,67.1402,52.9505,47.0495,12.23,300,0.904,bicubic +inception_resnet_v2,32.7379,67.2621,50.6475,49.3525,55.84,299,0.8975,bicubic +gluon_resnet152_v1d,32.734,67.266,51.0877,48.9123,60.21,224,0.875,bicubic +tf_efficientnet_b2_ap,32.6809,67.3191,52.2392,47.7608,9.11,260,0.89,bicubic +nasnetalarge,32.5964,67.4036,49.7789,50.2211,88.75,331,0.875,bicubic +pnasnet5large,32.5296,67.4704,50.1916,49.8084,86.06,331,0.875,bicubic +ens_adv_inception_resnet_v2,32.3724,67.6276,50.4274,49.5726,55.84,299,0.8975,bicubic +gluon_resnet152_v1s,32.3312,67.6688,50.5257,49.4743,60.32,224,0.875,bicubic +gluon_seresnext101_64x4d,32.2054,67.7946,50.3193,49.6807,88.23,224,0.875,bicubic +gluon_seresnext101_32x4d,32.1071,67.8929,51.237,48.763,48.96,224,0.875,bicubic +efficientnet_b3a,31.7318,68.2682,51.3254,48.6746,12.23,320,1,bicubic +efficientnet_b3,31.555,68.445,51.2763,48.7237,12.23,300,0.904,bicubic +resnet50,31.5471,68.4529,50.17,49.83,25.56,224,0.875,bicubic +ssl_resnext101_32x4d,31.4233,68.5767,52.1213,47.8787,44.18,224,0.875,bilinear +inception_v4,31.3781,68.6219,49.2444,50.7556,42.68,299,0.875,bicubic +gluon_resnet101_v1s,31.1148,68.8852,49.7927,50.2073,44.67,224,0.875,bicubic +tf_efficientnet_cc_b0_8e,31.0873,68.9127,50.7615,49.2385,24.01,224,0.875,bicubic +gluon_resnet152_v1c,30.991,69.009,48.9241,51.0759,60.21,224,0.875,bicubic +gluon_resnext101_64x4d,30.9871,69.0129,48.5488,51.4512,83.46,224,0.875,bicubic +tf_efficientnet_cc_b1_8e,30.8986,69.1014,50.0796,49.9204,39.72,240,0.882,bicubic +gluon_resnext101_32x4d,30.877,69.123,48.537,51.463,44.18,224,0.875,bicubic +dpn107,30.6785,69.3215,48.8102,51.1898,86.92,224,0.875,bicubic +gluon_resnet152_v1b,30.6235,69.3765,48.5213,51.4787,60.19,224,0.875,bicubic +ssl_resnext50_32x4d,30.594,69.406,50.6573,49.3427,25.03,224,0.875,bilinear +gluon_resnet101_v1d,30.5233,69.4767,47.9495,52.0505,44.57,224,0.875,bicubic +efficientnet_b2a,30.4349,69.5651,49.6984,50.3016,9.11,288,1,bicubic +tf_efficientnet_b1_ap,30.4211,69.5789,49.5529,50.4471,7.79,240,0.882,bicubic +dpn98,30.0674,69.9326,48.2442,51.7558,61.57,224,0.875,bicubic +tf_efficientnet_b2,30.0261,69.9739,49.5805,50.4195,9.11,260,0.89,bicubic +dpn131,30.0242,69.9758,48.146,51.854,79.25,224,0.875,bicubic +senet154,30.0006,69.9994,48.034,51.966,115.09,224,0.875,bilinear +dpn92,29.9534,70.0466,49.1619,50.8381,37.67,224,0.875,bicubic +gluon_senet154,29.8768,70.1232,47.8944,52.1056,115.09,224,0.875,bicubic +xception,29.865,70.135,48.6864,51.3136,22.86,299,0.8975,bicubic +adv_inception_v3,29.8178,70.1822,47.8473,52.1527,23.83,299,0.875,bicubic +efficientnet_b2,29.6154,70.3846,48.7767,51.2233,9.11,260,0.875,bicubic +gluon_xception65,29.5506,70.4494,47.5054,52.4946,39.92,299,0.875,bicubic +resnext101_32x8d,29.4386,70.5614,48.4859,51.5141,88.79,224,0.875,bilinear +ssl_resnet50,29.4229,70.5771,49.7809,50.2191,25.56,224,0.875,bilinear +gluon_inception_v3,29.1242,70.8758,46.9591,53.0409,23.83,299,0.875,bicubic +hrnet_w64,28.9886,71.0114,47.1418,52.8582,128.06,224,0.875,bilinear +tf_efficientnet_b1,28.8864,71.1136,47.5034,52.4966,7.79,240,0.882,bicubic +gluon_resnet101_v1b,28.8785,71.1215,46.3892,53.6108,44.55,224,0.875,bicubic +gluon_seresnext50_32x4d,28.6506,71.3494,46.4364,53.5636,27.56,224,0.875,bicubic +hrnet_w40,28.6408,71.3592,47.4543,52.5457,57.56,224,0.875,bilinear +resnet152,28.5327,71.4673,47.1182,52.8818,60.19,224,0.875,bilinear +hrnet_w48,28.4128,71.5872,47.5859,52.4141,77.47,224,0.875,bilinear +gluon_resnext50_32x4d,28.3755,71.6245,45.3281,54.6719,25.03,224,0.875,bicubic +tf_efficientnet_b0_ap,28.346,71.654,47.5309,52.4691,5.29,224,0.875,bicubic +tf_efficientnet_cc_b0_4e,28.3146,71.6854,47.3639,52.6361,13.31,224,0.875,bicubic +dla102x2,28.3126,71.6874,46.7606,53.2394,41.75,224,0.875,bilinear +dla169,28.3126,71.6874,47.3914,52.6086,53.99,224,0.875,bilinear +mixnet_xl,28.2871,71.7129,46.7016,53.2984,11.9,224,0.875,bicubic +gluon_resnet50_v1d,28.2458,71.7542,45.8783,54.1217,25.58,224,0.875,bicubic +wide_resnet101_2,28.1082,71.8918,46.401,53.599,126.89,224,0.875,bilinear +gluon_resnet101_v1c,28.1043,71.8957,45.9608,54.0392,44.57,224,0.875,bicubic +densenet161,28.0807,71.9193,46.6407,53.3593,28.68,224,0.875,bicubic +dpn68b,27.8842,72.1158,47.468,52.532,12.61,224,0.875,bicubic +tf_inception_v3,27.7801,72.2199,45.7211,54.2789,23.83,299,0.875,bicubic +res2net101_26w_4s,27.7683,72.2317,45.1787,54.8213,45.21,224,0.875,bilinear +hrnet_w44,27.6209,72.3791,45.837,54.163,67.06,224,0.875,bilinear +inception_v3,27.5561,72.4439,45.2652,54.7348,27.16,299,0.875,bicubic +hrnet_w30,27.3812,72.6188,46.5543,53.4457,37.71,224,0.875,bilinear +hrnet_w32,27.3694,72.6306,45.9942,54.0058,41.23,224,0.875,bilinear +gluon_resnet50_v1s,27.3261,72.6739,45.222,54.778,25.68,224,0.875,bicubic +densenet201,27.2652,72.7348,46.2222,53.7778,20.01,224,0.875,bicubic +res2net50_26w_8s,27.0785,72.9215,44.4281,55.5719,48.4,224,0.875,bilinear +dla102x,27.0609,72.9391,45.4754,54.5246,26.77,224,0.875,bilinear +resnet101,26.9626,73.0374,45.2337,54.7663,44.55,224,0.875,bilinear +resnext50d_32x4d,26.8761,73.1239,44.4359,55.5641,25.05,224,0.875,bicubic +densenet169,26.829,73.171,45.3733,54.6267,14.15,224,0.875,bicubic +seresnext101_32x4d,26.8113,73.1887,43.4966,56.5034,48.96,224,0.875,bilinear +seresnet152,26.6757,73.3243,43.9466,56.0534,66.82,224,0.875,bilinear +tf_efficientnet_el,26.6226,73.3774,44.6482,55.3518,10.59,300,0.904,bicubic +res2net50_26w_6s,26.5951,73.4049,43.9899,56.0101,37.05,224,0.875,bilinear +dla60x,26.5519,73.4481,45.0235,54.9765,17.65,224,0.875,bilinear +tf_efficientnet_b0,26.4851,73.5149,45.6464,54.3536,5.29,224,0.875,bicubic +res2net50_14w_8s,26.4831,73.5169,44.3711,55.6289,25.06,224,0.875,bilinear +gluon_resnet50_v1b,26.436,73.564,44.0351,55.9649,25.56,224,0.875,bicubic +dpn68,26.1294,73.8706,44.2276,55.7724,12.61,224,0.875,bicubic +resnext50_32x4d,26.1157,73.8843,42.9798,57.0202,25.03,224,0.875,bicubic +hrnet_w18,25.986,74.014,44.8132,55.1868,21.3,224,0.875,bilinear +resnet34,25.8877,74.1123,43.982,56.018,21.8,224,0.875,bilinear +res2net50_26w_4s,25.8661,74.1339,43.1547,56.8453,25.7,224,0.875,bilinear +gluon_resnet50_v1c,25.7836,74.2164,43.0309,56.9691,25.58,224,0.875,bicubic +selecsls60,25.7285,74.2715,44.0645,55.9355,30.67,224,0.875,bicubic +dla60_res2net,25.6519,74.3481,43.5988,56.4012,21.15,224,0.875,bilinear +dla60_res2next,25.6401,74.3599,43.6696,56.3304,17.33,224,0.875,bilinear +mixnet_l,25.5124,74.4876,43.4554,56.5446,7.33,224,0.875,bicubic +efficientnet_b1,25.4692,74.5308,43.2844,56.7156,7.79,240,0.875,bicubic +tv_resnext50_32x4d,25.4554,74.5446,42.7872,57.2128,25.03,224,0.875,bilinear +tf_mixnet_l,25.422,74.578,42.5337,57.4663,7.33,224,0.875,bicubic +res2next50,25.3886,74.6114,42.5082,57.4918,24.67,224,0.875,bilinear +seresnet101,25.3336,74.6664,42.8246,57.1754,49.33,224,0.875,bilinear +selecsls60b,25.3316,74.6684,43.5595,56.4405,32.77,224,0.875,bicubic +dla102,25.3159,74.6841,43.8268,56.1732,33.73,224,0.875,bilinear +wide_resnet50_2,25.308,74.692,42.1781,57.8219,68.88,224,0.875,bilinear +seresnext50_32x4d,25.2098,74.7902,41.9364,58.0636,27.56,224,0.875,bilinear +res2net50_48w_2s,25.027,74.973,42.2075,57.7925,25.29,224,0.875,bilinear +efficientnet_b0,25.0152,74.9848,42.7872,57.2128,5.29,224,0.875,bicubic +gluon_resnet34_v1b,24.9386,75.0614,42.2429,57.7571,21.8,224,0.875,bicubic +dla60,24.9327,75.0673,43.2962,56.7038,22.33,224,0.875,bilinear +tf_efficientnet_em,24.5416,75.4584,42.4119,57.5881,6.9,240,0.882,bicubic +tv_resnet50,24.07,75.93,41.3134,58.6866,25.56,224,0.875,bilinear +seresnet34,24.0268,75.9732,41.9089,58.0911,21.96,224,0.875,bilinear +densenet121,23.8441,76.1559,41.9246,58.0754,7.98,224,0.875,bicubic +tf_efficientnet_es,23.8185,76.1815,41.3311,58.6689,5.44,224,0.875,bicubic +mixnet_m,23.7104,76.2896,41.1405,58.8595,5.01,224,0.875,bicubic +dla34,23.6692,76.3308,41.5512,58.4488,15.78,224,0.875,bilinear +seresnet50,23.6515,76.3485,40.0912,59.9088,28.09,224,0.875,bilinear +tf_mixnet_m,23.4844,76.5156,40.9892,59.0108,5.01,224,0.875,bicubic +tv_resnet34,23.4727,76.5273,41.3665,58.6335,21.8,224,0.875,bilinear +selecsls42b,23.3567,76.6433,40.6768,59.3232,32.46,224,0.875,bicubic +mobilenetv3_rw,22.6296,77.3704,40.3741,59.6259,5.48,224,0.875,bicubic +tf_mobilenetv3_large_100,22.5687,77.4313,39.7669,60.2331,5.48,224,0.875,bilinear +hrnet_w18_small_v2,22.3369,77.6631,39.8613,60.1387,15.6,224,0.875,bilinear +seresnext26tn_32x4d,21.991,78.009,38.4818,61.5182,16.81,224,0.875,bicubic +seresnext26t_32x4d,21.9851,78.0149,38.5702,61.4298,16.82,224,0.875,bicubic +resnet26d,21.9065,78.0935,38.6193,61.3807,16.01,224,0.875,bicubic +semnasnet_100,21.9026,78.0974,38.5997,61.4003,3.89,224,0.875,bicubic +gluon_resnet18_v1b,21.5489,78.4511,38.8689,61.1311,11.69,224,0.875,bicubic +fbnetc_100,21.484,78.516,38.1615,61.8385,5.57,224,0.875,bilinear +mnasnet_100,21.3504,78.6496,37.7193,62.2807,4.38,224,0.875,bicubic +resnet26,21.2954,78.7046,38.018,61.982,16,224,0.875,bicubic +ssl_resnet18,21.2777,78.7223,39.1126,60.8874,11.69,224,0.875,bilinear +mixnet_s,21.2541,78.7459,38.187,61.813,4.13,224,0.875,bicubic +seresnext26d_32x4d,21.2521,78.7479,37.3106,62.6894,16.81,224,0.875,bicubic +seresnext26_32x4d,21.093,78.907,37.6329,62.3671,16.79,224,0.875,bicubic +spnasnet_100,20.8631,79.1369,37.8962,62.1038,4.42,224,0.875,bilinear +seresnet18,20.8375,79.1625,37.6191,62.3809,11.78,224,0.875,bicubic +tf_mixnet_s,20.47,79.53,36.6071,63.3929,4.13,224,0.875,bicubic +hrnet_w18_small,20.3679,79.6321,37.0925,62.9075,13.19,224,0.875,bilinear +tf_mobilenetv3_large_075,20.3659,79.6341,36.7643,63.2357,3.99,224,0.875,bilinear +resnet18,20.2283,79.7717,37.2615,62.7385,11.69,224,0.875,bilinear +tf_mobilenetv3_large_minimal_100,20.1222,79.8778,36.9078,63.0922,3.92,224,0.875,bilinear +dla60x_c,16.31,83.69,31.7613,68.2387,1.34,224,0.875,bilinear +tf_mobilenetv3_small_100,16.2275,83.7725,31.2229,68.7771,2.54,224,0.875,bilinear +tf_mobilenetv3_small_075,14.9443,85.0557,29.5722,70.4278,2.04,224,0.875,bilinear +dla46_c,14.6574,85.3426,29.3796,70.6204,1.31,224,0.875,bilinear +dla46x_c,14.3823,85.6177,29.191,70.809,1.08,224,0.875,bilinear +tf_mobilenetv3_small_minimal_100,13.9637,86.0363,27.9884,72.0116,2.04,224,0.875,bilinear From fd98fb33c546a2cb5f72bf936c992187ecfcb3f8 Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Sat, 1 Feb 2020 18:12:25 -0800 Subject: [PATCH 8/8] Update sotabench with tf_efficientnet_b8 model --- sotabench.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sotabench.py b/sotabench.py index 1f819751..bd5b0b81 100644 --- a/sotabench.py +++ b/sotabench.py @@ -130,6 +130,8 @@ model_list = [ model_desc='Ported from official Google AI Tensorflow weights'), _entry('tf_efficientnet_b7', 'EfficientNet-B7 (RandAugment)', '1905.11946', batch_size=BATCH_SIZE//8, model_desc='Ported from official Google AI Tensorflow weights'), + _entry('tf_efficientnet_b8', 'EfficientNet-B8 (RandAugment)', '1905.11946', batch_size=BATCH_SIZE // 8, + model_desc='Ported from official Google AI Tensorflow weights'), _entry('tf_efficientnet_b0_ap', 'EfficientNet-B0 (AdvProp)', '1911.09665', model_desc='Ported from official Google AI Tensorflow weights'), _entry('tf_efficientnet_b1_ap', 'EfficientNet-B1 (AdvProp)', '1911.09665',