66634d2200
Add support to split random erasing blocks into randomly selected number with --recount arg. Fix random selection of aspect ratios.
5 years ago
6946281fde
Experimenting with random erasing changes
5 years ago
aeaaad7304
Merge pull request #24 from rwightman/gluon_xception
...
Port Gluon Aligned Xception models
5 years ago
3b4868f6dc
A few more additions to Gluon Xception models to match interface of others.
5 years ago
f937e2a600
Merge pull request #23 from aovoc/patch-1
...
Update helpers.py
5 years ago
4d505e0785
Add working Gluon Xception-65 model. Some cleanup still needed.
5 years ago
4e7a854dd0
Update helpers.py
...
Fixing out of memory error by loading the checkpoint onto the CPU.
5 years ago
0c874195db
Update results csv files, bump version for timm pip release
5 years ago
9b35818811
Update README.md
5 years ago
4fe2da558c
Add MixNet Small and Large PyTorch native weights (no same padding)
5 years ago
15e66863b1
Update README.md
5 years ago
e879cf52fa
Update validation scores for new TF EfficientNet weights.
5 years ago
b35050a144
Update README.md
5 years ago
77e2e0c4e3
Add new auto-augmentation Tensorflow EfficientNet weights, incl B6 and B7 models. Validation scores still pending but looking good.
5 years ago
857f33015a
Add native PyTorch weights for MixNet-Medium with no SAME padding necessary. Remove unused block of code.
5 years ago
e7c8a37334
Make min-lr and cooldown-epochs cmdline args, change dash in color_jitter arg for consistency
6 years ago
d4debe6597
Update version, results csv files, and move remaining dropbox weights to github
6 years ago
dfa9298b4e
Add MixNet ( https://arxiv.org/abs/1907.09595 ) with pretrained weights converted from Tensorflow impl
...
* refactor 'same' convolution and add helper to use MixedConv2d when needed
* improve performance of 'same' padding for cases that can be handled statically
* add support for extra exp, pw, and dw kernel specs with grouping support to decoder/string defs for MixNet
* shuffle some args for a bit more consistency, a little less clutter overall in gen_efficientnet.py
6 years ago
7a92caa560
Add basic image folder style dataset to read directly out of tar files, example in validate.py
6 years ago
d6ac5bbc48
EfficientNet and related cleanup
...
* remove folded_bn support and corresponding untrainable tflite ported weights
* combine bn args into dict
* add inplace support to activations and use where possible for reduced mem on large models
6 years ago
c11973602d
Merge pull request #19 from rwightman/resnet-refactor
...
Resnet refactoring
6 years ago
d97510fd4a
Add new results csv and update README with 3 new ResNet weight results
6 years ago
3d9be78fc6
A bit more ResNet cleanup.
...
* add inplace=True back
* minor comment improvements
* few clarity changes
6 years ago
33436fafad
Add weights for ResNeXt50d model
6 years ago
e78cd79073
Move ResNet additions for Gluon into main ResNet impl. Add ResNet-26 and ResNet-26d models with weights.
6 years ago
c37cb0f2b7
ImageNet-1k vs ImageNet-v2 comparison
6 years ago
6cdf35e670
Add explicit half/fp16 support to loader and validation script
6 years ago
5684c6af32
Update README.md
...
Add blurb about results csv
6 years ago
a6b2f6eca5
Update README, bump version
6 years ago
2a1d09b4c0
Add result csv with summary of all pretrained models
6 years ago
edb425ea48
Add crop_pct arg to validate, extra fields to csv output, 'all' filters pretrained
6 years ago
949b7a81c4
Fix typo in Densenet default resolutions
6 years ago
da52fcf78a
Add NASNet-Large model
6 years ago
f632190fd9
Add .gitattributes
6 years ago
5bc0ed3d7c
Grammar
6 years ago
c89acdfc02
Update EffResNetComparison.ipynb
6 years ago
73642f7462
Adjust notebook path
6 years ago
c30f625215
Update EffResNetComparison
6 years ago
c4916897f8
EfficientNet vs ResNet comparison in Colaboratory
6 years ago
6057496409
Register dpn107
6 years ago
3d1a66b6fc
Version 0.1.6
6 years ago
a6878b5218
Fix DPN config keys that I broke
6 years ago
8a05b8d555
Merge pull request #16 from rwightman/misc-epoch
...
Weights, arguments, epoch counting, and more
6 years ago
9b0070edc9
Add two comments back, fix typo
6 years ago
188aeae8f4
Bump version 0.1.4
6 years ago
c3287aafb3
Slight improvement in EfficientNet-B2 native PyTorch weights
6 years ago
b8762cc67d
Model updates. Add my best ResNet50 weights top-1=78.47. Add some other torchvision weights.
...
* Remove some models that don't exist as pretrained an likely never will (se)resnext152
* Add some torchvision weights as tv_ for models that I have added better weights for
* Add wide resnet recently added to torchvision along with resnext101-32x8d
* Add functionality to model registry to allow filtering on pretrained weight presence
6 years ago
65a634626f
Switch random erasing to doing normal_() on CPU to avoid instability, remove a debug print
6 years ago
c6b32cbe73
A number of tweaks to arguments, epoch handling, config
...
* reorganize train args
* allow resolve_data_config to be used with dict args, not just arparse
* stop incrementing epoch before save, more consistent naming vs csv, etc
* update resume and start epoch handling to match above
* stop auto-incrementing epoch in scheduler
6 years ago
9d653b68a2
Make drop_connect rate scaling match official impl. Fixes #14
6 years ago
Ross Wightman