Model card for cs3darknet_focus_s.ra4_e3600_r256_in1k
A CS3-DarkNet (Cross-Stage-Partial w/ 3 convolutions) image classification model. Trained on ImageNet-1k by Ross Wightman.
Trained with timm scripts using hyper-parameters inspired by the MobileNet-V4 paper with timm enhancements.
A collection of hparams (timm .yaml config files) for this training series can be found here: https://gist.github.com/rwightman/f6705cb65c03daeebca8aa129b1b94ad
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 3.3
- GMACs: 0.7
- Activations (M): 2.7
- Image size: train = 256 x 256, test = 320 x 320
- Dataset: ImageNet-1k
- Papers:
- PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN: https://arxiv.org/abs/1911.11929
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('cs3darknet_focus_s.ra4_e3600_r256_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(
'cs3darknet_focus_s.ra4_e3600_r256_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, 32, 128, 128])
# torch.Size([1, 64, 64, 64])
# torch.Size([1, 128, 32, 32])
# torch.Size([1, 256, 16, 16])
# torch.Size([1, 512, 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(
'cs3darknet_focus_s.ra4_e3600_r256_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, 512, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
Model Comparison
By Top-1
Citation
@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}}
}
@article{Wang2019CSPNetAN,
title={CSPNet: A New Backbone that can Enhance Learning Capability of CNN},
author={Chien-Yao Wang and Hong-Yuan Mark Liao and I-Hau Yeh and Yueh-Hua Wu and Ping-Yang Chen and Jun-Wei Hsieh},
journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
year={2019},
pages={1571-1580}
}
- Downloads last month
- 140
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.