Update model config and README

d05e583 about 1 year ago

4.47 kB

	---
	tags:
	- image-classification
	- timm
	library_name: timm
	license: apache-2.0
	datasets:
	- imagenet-1k
	---
	# Model card for fbnetc_100.rmsp_in1k

	A FBNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.

	Recipe details:
	* A simple RmsProp based recipe without RandAugment. Using RandomErasing, mixup, dropout, standard random-resize-crop augmentation.
	* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
	* Step (exponential decay w/ staircase) LR schedule with warmup


	## Model Details
	- Model Type: Image classification / feature backbone
	- Model Stats:
	- Params (M): 5.6
	- GMACs: 0.4
	- Activations (M): 6.5
	- Image size: 224 x 224
	- Papers:
	- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search: https://arxiv.org/abs/1812.03443
	- Dataset: ImageNet-1k
	- Original: https://github.com/huggingface/pytorch-image-models

	## 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('fbnetc_100.rmsp_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(
	'fbnetc_100.rmsp_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, 16, 112, 112])
	# torch.Size([1, 24, 56, 56])
	# torch.Size([1, 32, 28, 28])
	# torch.Size([1, 112, 14, 14])
	# torch.Size([1, 352, 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(
	'fbnetc_100.rmsp_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, 1984, 7, 7) 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{rw2019timm,
	author = {Ross Wightman},
	title = {PyTorch Image Models},
	year = {2019},
	publisher = {GitHub},
	journal = {GitHub repository},
	doi = {10.5281/zenodo.4414861},
	howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
	}
	```
	```bibtex
	@inproceedings{wu2019fbnet,
	title={Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search},
	author={Wu, Bichen and Dai, Xiaoliang and Zhang, Peizhao and Wang, Yanghan and Sun, Fei and Wu, Yiming and Tian, Yuandong and Vajda, Peter and Jia, Yangqing and Keutzer, Kurt},
	booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
	pages={10734--10742},
	year={2019}
	}
	```