cspresnet50.ra_in1k 模型卡片

from PIL import Image
import timm
import argparse
import torch
from openmind import is_torch_npu_available

if is_torch_npu_available():
    device = "npu:0"
else:
    device = "cpu"
def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
    "--model_name_or_path",
    type=str,
    help="Path to the model file",
    default=None,
    )
    args = parser.parse_args()
    return args
if __name__ == '__main__':
    args = parse_args()
    model_path = args.model_name_or_path
    img=model_path+"/Img/beignets-task-guide.png"
    img = Image.open(img)

    model = timm.create_model(model_path, pretrained=False).to(device)
    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).to(device)) # unsqueeze single image into batch of 1

    top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
    print("top5_probabilities",top5_probabilities)
    # top5_probabilities tensor([[0.1222, 0.1189, 0.1177, 0.1176, 0.1173]], device='npu:0',grad_fn=<TopkBackward0>)
    print("top5_class_indices",top5_class_indices)
    # top5_class_indices tensor([[961, 168, 839, 928, 277]], device='npu:0')

# from urllib.request import urlopen
from PIL import Image
import timm
import argparse
import torch
from openmind import is_torch_npu_available

if is_torch_npu_available():
    device = "npu:0"
else:
    device = "cpu"
def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
    "--model_name_or_path",
    type=str,
    help="Path to the model file",
    default=None,
    )
    args = parser.parse_args()
    return args
if __name__ == '__main__':
    args = parse_args()
    # model_path = args.model_name_or_path
    img=model_path+"/Img/beignets-task-guide.png"
    img = Image.open(img)
    
    model = timm.create_model(model_path, pretrained=False,features_only=True).to(device)
    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).to(device)) # unsqueeze single image into batch of 1

    for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  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)

# from urllib.request import urlopen
from PIL import Image
import timm
import argparse
import torch
from openmind import is_torch_npu_available

if is_torch_npu_available():
    device = "npu:0"
else:
    device = "cpu"
def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
    "--model_name_or_path",
    type=str,
    help="Path to the model file",
    default=None,
    )
    args = parser.parse_args()
    return args
if __name__ == '__main__':
    args = parse_args()
    model_path = args.model_name_or_path
    img=model_path+"/Img/beignets-task-guide.png"
    img = Image.open(img)

    model = timm.create_model(model_path, pretrained=False).to(device)
    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).to(device)) # unsqueeze single image into batch of 1
    output = model.forward_features(transforms(img).unsqueeze(0).to(device))
    # 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

@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{He2015,
  author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  title = {Deep Residual Learning for Image Recognition},
  journal = {arXiv preprint arXiv:1512.03385},
  year = {2015}
}

@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}}
}