Add model

7aacec6 about 1 year ago

3.8 kB

	---
	tags:
	- image-classification
	- timm
	library_name: timm
	license: apache-2.0
	datasets:
	- imagenet-1k
	---
	# Model card for nasnetalarge.tf_in1k

	A NasNet image classification model. Trained on ImageNet-1k by paper authors. Ported from Tensorflow via Cadene's pretrained-models.pytorch.

	## Model Details
	- Model Type: Image classification / feature backbone
	- Model Stats:
	- Params (M): 88.8
	- GMACs: 23.9
	- Activations (M): 90.6
	- Image size: 331 x 331
	- Papers:
	- Learning Transferable Architectures for Scalable Image Recognition: https://arxiv.org/abs/1707.07012
	- Original:
	- https://github.com/tensorflow/models
	- https://github.com/Cadene/pretrained-models.pytorch
	- Dataset: ImageNet-1k

	## 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('nasnetalarge.tf_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(
	'nasnetalarge.tf_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, 165, 165])
	# torch.Size([1, 168, 83, 83])
	# torch.Size([1, 1008, 42, 42])
	# torch.Size([1, 2016, 21, 21])
	# torch.Size([1, 4032, 11, 11])

	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(
	'nasnetalarge.tf_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, 4032, 11, 11) shaped tensor

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

	## Model Comparison
	Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

	## Citation
	```bibtex
	@misc{zoph2018learning,
	title={Learning Transferable Architectures for Scalable Image Recognition},
	author={Barret Zoph and Vijay Vasudevan and Jonathon Shlens and Quoc V. Le},
	year={2018},
	eprint={1707.07012},
	archivePrefix={arXiv},
	primaryClass={cs.CV}
	}
	```