Update model config and README

4128812 10 months ago

No virus

3.67 kB

	---
	tags:
	- image-classification
	- timm
	library_name: timm
	license: apache-2.0
	datasets:
	- imagenet-1k
	- imagenet-22k
	---
	# Model card for tiny_vit_21m_224.dist_in22k_ft_in1k

	A TinyViT image classification model. Pretrained on ImageNet-22k with distillation and fine-tuned on ImageNet-1k by paper authors.

	## Model Details
	- Model Type: Image classification / feature backbone
	- Model Stats:
	- Params (M): 21.2
	- GMACs: 4.1
	- Activations (M): 15.9
	- Image size: 224 x 224
	- Papers:
	- TinyViT: Fast Pretraining Distillation for Small Vision Transformers: https://arxiv.org/abs/2207.10666
	- Original: https://github.com/microsoft/Cream/tree/main/TinyViT
	- Dataset: ImageNet-1k
	- Pretrain Dataset: ImageNet-22k

	## Model Usage
	### Image Classification
	```python
	from urllib.request import urlopen
	from PIL import Image
	import timm

	img = Image.open(urlopen(
	'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
	))

	model = timm.create_model('tiny_vit_21m_224.dist_in22k_ft_in1k', pretrained=True)
	model = model.eval()

	# get model specific transforms (normalization, resize)
	data_config = timm.data.resolve_model_data_config(model)
	transforms = timm.data.create_transform(**data_config, is_training=False)

	output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1

	top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
	```

	### Feature Map Extraction
	```python
	from urllib.request import urlopen
	from PIL import Image
	import timm

	img = Image.open(urlopen(
	'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
	))

	model = timm.create_model(
	'tiny_vit_21m_224.dist_in22k_ft_in1k',
	pretrained=True,
	features_only=True,
	)
	model = model.eval()

	# get model specific transforms (normalization, resize)
	data_config = timm.data.resolve_model_data_config(model)
	transforms = timm.data.create_transform(**data_config, is_training=False)

	output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1

	for o in output:
	# print shape of each feature map in output
	# e.g.:
	# torch.Size([1, 96, 56, 56])
	# torch.Size([1, 192, 28, 28])
	# torch.Size([1, 384, 14, 14])
	# torch.Size([1, 576, 7, 7])

	print(o.shape)
	```

	### Image Embeddings
	```python
	from urllib.request import urlopen
	from PIL import Image
	import timm

	img = Image.open(urlopen(
	'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
	))

	model = timm.create_model(
	'tiny_vit_21m_224.dist_in22k_ft_in1k',
	pretrained=True,
	num_classes=0, # remove classifier nn.Linear
	)
	model = model.eval()

	# get model specific transforms (normalization, resize)
	data_config = timm.data.resolve_model_data_config(model)
	transforms = timm.data.create_transform(**data_config, is_training=False)

	output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor

	# or equivalently (without needing to set num_classes=0)

	output = model.forward_features(transforms(img).unsqueeze(0))
	# output is unpooled, a (1, 576, 7, 7) shaped tensor

	output = model.forward_head(output, pre_logits=True)
	# output is a (1, num_features) shaped tensor
	```

	## Citation
	```bibtex
	@InProceedings{tiny_vit,
	title={TinyViT: Fast Pretraining Distillation for Small Vision Transformers},
	author={Wu, Kan and Zhang, Jinnian and Peng, Houwen and Liu, Mengchen and Xiao, Bin and Fu, Jianlong and Yuan, Lu},
	booktitle={European conference on computer vision (ECCV)},
	year={2022}
	}
	```