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('cspdarknet53.ra_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(
'cspdarknet53.ra_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 1for o in output:
# print shape of each feature map in output# e.g.:# torch.Size([1, 32, 256, 256])# torch.Size([1, 64, 128, 128])# torch.Size([1, 128, 64, 64])# torch.Size([1, 256, 32, 32])# torch.Size([1, 512, 16, 16])# torch.Size([1, 1024, 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(
'cspdarknet53.ra_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, 1024, 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
@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}
}
@article{Redmon2018YOLOv3AI,
title={YOLOv3: An Incremental Improvement},
author={Joseph Redmon and Ali Farhadi},
journal={ArXiv},
year={2018},
volume={abs/1804.02767}
}
@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}
}
@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}}
}
Runs of timm cspdarknet53.ra_in1k on huggingface.co
20.7K
Total runs
0
24-hour runs
1.2K
3-day runs
278
7-day runs
5.6K
30-day runs
More Information About cspdarknet53.ra_in1k huggingface.co Model
cspdarknet53.ra_in1k huggingface.co is an AI model on huggingface.co that provides cspdarknet53.ra_in1k's model effect (), which can be used instantly with this timm cspdarknet53.ra_in1k model. huggingface.co supports a free trial of the cspdarknet53.ra_in1k model, and also provides paid use of the cspdarknet53.ra_in1k. Support call cspdarknet53.ra_in1k model through api, including Node.js, Python, http.
cspdarknet53.ra_in1k huggingface.co is an online trial and call api platform, which integrates cspdarknet53.ra_in1k's modeling effects, including api services, and provides a free online trial of cspdarknet53.ra_in1k, you can try cspdarknet53.ra_in1k online for free by clicking the link below.
timm cspdarknet53.ra_in1k online free url in huggingface.co:
cspdarknet53.ra_in1k is an open source model from GitHub that offers a free installation service, and any user can find cspdarknet53.ra_in1k on GitHub to install. At the same time, huggingface.co provides the effect of cspdarknet53.ra_in1k install, users can directly use cspdarknet53.ra_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
cspdarknet53.ra_in1k install url in huggingface.co: