Merge branch 'gcucurull-master'

Author: rwightman

docs/models/.templates/code_snippets.md

@@ -0,0 +1,62 @@
+## How do I use this model on an image?
+To load a pretrained model:
+
+```python
+import timm
+model = timm.create_model('{{ model_name }}', pretrained=True)
+model.eval()
+```
+
+To load and preprocess the image:
+```python 
+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:
+```python
+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:
+```python
+# 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. `{{ model_name }}`. 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](https://rwightman.github.io/pytorch-image-models/feature_extraction/), 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).
+```python
+model = timm.create_model('{{ model_name }}', 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](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

docs/models/.templates/generate_readmes.py

@@ -0,0 +1,64 @@
+"""
+Run this script to generate the model-index files in `models` from the templates in `.templates/models`.
+"""
+
+import argparse
+from pathlib import Path
+
+from jinja2 import Environment, FileSystemLoader
+
+import modelindex
+
+
+def generate_readmes(templates_path: Path, dest_path: Path):
+    """Add the code snippet template to the readmes"""
+    readme_templates_path = templates_path / "models"
+    code_template_path = templates_path / "code_snippets.md"
+
+    env = Environment(
+        loader=FileSystemLoader([readme_templates_path, readme_templates_path.parent]),
+    )
+
+    for readme in readme_templates_path.iterdir():
+        if readme.suffix == ".md":
+            template = env.get_template(readme.name)
+
+            # get the first model_name for this model family
+            mi = modelindex.load(str(readme))
+            model_name = mi.models[0].name
+
+            full_content = template.render(model_name=model_name)
+
+            # generate full_readme
+            with open(dest_path / readme.name, "w") as f:
+                f.write(full_content)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Model index generation config")
+    parser.add_argument(
+        "-t",
+        "--templates",
+        default=Path(__file__).parent / ".templates",
+        type=str,
+        help="Location of the markdown templates",
+    )
+    parser.add_argument(
+        "-d",
+        "--dest",
+        default=Path(__file__).parent / "models",
+        type=str,
+        help="Destination folder that contains the generated model-index files.",
+    )
+    args = parser.parse_args()
+    templates_path = Path(args.templates)
+    dest_readmes_path = Path(args.dest)
+
+    generate_readmes(
+        templates_path,
+        dest_readmes_path,
+    )
+
+
+if __name__ == "__main__":
+    main()

docs/models/.templates/models/adversarial-inception-v3.md

@@ -0,0 +1,98 @@
+# Adversarial Inception v3
+
+**Inception v3** is a convolutional neural network architecture from the Inception family that makes several improvements including using [Label Smoothing](https://paperswithcode.com/method/label-smoothing), Factorized 7 x 7 convolutions, and the use of an [auxiliary classifer](https://paperswithcode.com/method/auxiliary-classifier) 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](https://paperswithcode.com/method/inception-v3-module).
+
+This particular model was trained for study of adversarial examples (adversarial training).
+
+The weights from this model were ported from [Tensorflow/Models](https://github.com/tensorflow/models).
+
+{% include 'code_snippets.md' %}
+
+## How do I train this model?
+
+You can follow the [timm recipe scripts](https://rwightman.github.io/pytorch-image-models/scripts/) for training a new model afresh.
+
+## Citation
+
+```BibTeX
+@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}
+}
+```
+
+<!--
+Type: model-index
+Collections:
+- Name: Adversarial Inception v3
+  Paper:
+    Title: Adversarial Attacks and Defences Competition
+    URL: https://paperswithcode.com/paper/adversarial-attacks-and-defences-competition
+Models:
+- Name: adv_inception_v3
+  In Collection: Adversarial Inception v3
+  Metadata:
+    FLOPs: 7352418880
+    Parameters: 23830000
+    File Size: 95549439
+    Architecture:
+    - 1x1 Convolution
+    - Auxiliary Classifier
+    - Average Pooling
+    - Average Pooling
+    - Batch Normalization
+    - Convolution
+    - Dense Connections
+    - Dropout
+    - Inception-v3 Module
+    - Max Pooling
+    - ReLU
+    - Softmax
+    Tasks:
+    - Image Classification
+    Training Data:
+    - ImageNet
+    ID: adv_inception_v3
+    Crop Pct: '0.875'
+    Image Size: '299'
+    Interpolation: bicubic
+  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/inception_v3.py#L456
+  Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/adv_inception_v3-9e27bd63.pth
+  Results:
+  - Task: Image Classification
+    Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 77.58%
+      Top 5 Accuracy: 93.74%
+-->