You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
pytorch-image-models/docs/models/adversarial-inception-v3.md

5.7 KiB

Adversarial Inception v3

Inception v3 is a convolutional neural network architecture from the Inception family that makes several improvements including using Label Smoothing, Factorized 7 x 7 convolutions, and the use of an auxiliary classifer to propagate label information lower down the network (along with the use of batch normalization for layers in the sidehead). The key building block is an Inception Module.

This particular model was trained for study of adversarial examples (adversarial training).

The weights from this model were ported from Tensorflow/Models.

How do I use this model on an image?

To load a pretrained model:

import timm
model = timm.create_model('adv_inception_v3', pretrained=True)
model.eval()

To load and preprocess the image:

import urllib
from PIL import Image
from timm.data import resolve_data_config
from timm.data.transforms_factory import create_transform

config = resolve_data_config({}, model=model)
transform = create_transform(**config)

url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
urllib.request.urlretrieve(url, filename)
img = Image.open(filename).convert('RGB')
tensor = transform(img).unsqueeze(0) # transform and add batch dimension

To get the model predictions:

import torch
with torch.no_grad():
    out = model(tensor)
probabilities = torch.nn.functional.softmax(out[0], dim=0)
print(probabilities.shape)
# prints: torch.Size([1000])

To get the top-5 predictions class names:

# Get imagenet class mappings
url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
urllib.request.urlretrieve(url, filename) 
with open("imagenet_classes.txt", "r") as f:
    categories = [s.strip() for s in f.readlines()]

# Print top categories per image
top5_prob, top5_catid = torch.topk(probabilities, 5)
for i in range(top5_prob.size(0)):
    print(categories[top5_catid[i]], top5_prob[i].item())
# prints class names and probabilities like:
# [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]

Replace the model name with the variant you want to use, e.g. adv_inception_v3. You can find the IDs in the model summaries at the top of this page.

To extract image features with this model, follow the timm feature extraction examples, just change the name of the model you want to use.

How do I finetune this model?

You can finetune any of the pre-trained models just by changing the classifier (the last layer).

model = timm.create_model('adv_inception_v3', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)

To finetune on your own dataset, you have to write a training loop or adapt timm's training script to use your dataset.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

Citation

@article{DBLP:journals/corr/abs-1804-00097,
  author    = {Alexey Kurakin and
               Ian J. Goodfellow and
               Samy Bengio and
               Yinpeng Dong and
               Fangzhou Liao and
               Ming Liang and
               Tianyu Pang and
               Jun Zhu and
               Xiaolin Hu and
               Cihang Xie and
               Jianyu Wang and
               Zhishuai Zhang and
               Zhou Ren and
               Alan L. Yuille and
               Sangxia Huang and
               Yao Zhao and
               Yuzhe Zhao and
               Zhonglin Han and
               Junjiajia Long and
               Yerkebulan Berdibekov and
               Takuya Akiba and
               Seiya Tokui and
               Motoki Abe},
  title     = {Adversarial Attacks and Defences Competition},
  journal   = {CoRR},
  volume    = {abs/1804.00097},
  year      = {2018},
  url       = {http://arxiv.org/abs/1804.00097},
  archivePrefix = {arXiv},
  eprint    = {1804.00097},
  timestamp = {Thu, 31 Oct 2019 16:31:22 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1804-00097.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}