metadata

tags:
  - image-classification
  - timm
library_name: timm
license: apache-2.0
datasets:
  - imagenet-1k

Model card for fbnetv3_g.ra2_in1k

A FBNet-v3 image classification model. Trained on ImageNet-1k in timm using recipe template described below.

Recipe details:

RandAugment RA2 recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back.
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): 16.6
- GMACs: 1.3
- Activations (M): 14.9
- Image size: train = 240 x 240, test = 288 x 288
Papers:
- FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining: https://arxiv.org/abs/2006.02049
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
Dataset: ImageNet-1k
Original: https://github.com/huggingface/pytorch-image-models

Model Usage

Image Classification

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('fbnetv3_g.ra2_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

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(
    'fbnetv3_g.ra2_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, 24, 120, 120])
    #  torch.Size([1, 40, 60, 60])
    #  torch.Size([1, 56, 30, 30])
    #  torch.Size([1, 160, 15, 15])
    #  torch.Size([1, 1728, 8, 8])

    print(o.shape)

Image Embeddings

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(
    'fbnetv3_g.ra2_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, 1728, 8, 8) 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.

Citation

@inproceedings{dai2021fbnetv3,
  title={Fbnetv3: Joint architecture-recipe search using predictor pretraining},
  author={Dai, Xiaoliang and Wan, Alvin and Zhang, Peizhao and Wu, Bichen and He, Zijian and Wei, Zhen and Chen, Kan and Tian, Yuandong and Yu, Matthew and Vajda, Peter and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={16276--16285},
  year={2021}
}

@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}}
}

@inproceedings{wightman2021resnet,
  title={ResNet strikes back: An improved training procedure in timm},
  author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
  booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}