swinv2_tiny_window16_256.ms_in1k 模型卡片

import torch
import torch_npu
import argparse
from openmind import pipeline, is_torch_npu_available
from PIL import Image
import requests
import timm

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default=None,
    )
    args = parser.parse_args()
    return args

def main():
    args = parse_args()
    model_path = args.model_name_or_path
    
    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
    
    url = "http://images.cocodataset.org/val2017/000000039769.jpg"
    img = Image.open(requests.get(url, stream=True).raw)
    
    model = timm.create_model(model_path, pretrained=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
    top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
    print(top5_class_indices)

if __name__=="__main__":
    main()

import torch
import torch_npu
import argparse
from openmind import pipeline, is_torch_npu_available
from PIL import Image
import requests
import timm

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default=None,
    )
    args = parser.parse_args()
    return args



def main():
    args = parse_args()
    model_path = args.model_name_or_path
    
    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
    
    url = "http://images.cocodataset.org/val2017/000000039769.jpg"
    img = Image.open(requests.get(url, stream=True).raw)
    
    model = timm.create_model(model_path, pretrained=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. for swin_base_patch4_window7_224 (NHWC output)
        #  torch.Size([1, 56, 56, 128])
        #  torch.Size([1, 28, 28, 256])
        #  torch.Size([1, 14, 14, 512])
        #  torch.Size([1, 7, 7, 1024])
        # e.g. for swinv2_cr_small_ns_224 (NCHW output)
        #  torch.Size([1, 96, 56, 56]) 
        #  torch.Size([1, 192, 28, 28])
        #  torch.Size([1, 384, 14, 14])
        #  torch.Size([1, 768, 7, 7])
        print(o.shape)

import torch
import torch_npu
import argparse
from openmind import pipeline, is_torch_npu_available
from PIL import Image
import requests
import timm

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default=None,
    )
    args = parser.parse_args()
    return args



def main():
    args = parse_args()
    model_path = args.model_name_or_path
    
    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
    
    url = "http://images.cocodataset.org/val2017/000000039769.jpg"
    img = Image.open(requests.get(url, stream=True).raw)
    
    model = timm.create_model(model_path, pretrained=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

    # or equivalently (without needing to set num_classes=0)

    output = model.forward_features(transforms(img).unsqueeze(0))
    # output is unpooled (ie.e a (batch_size, H, W,  num_features) tensor for swin / swinv2
    # or (batch_size, num_features, H, W) for swinv2_cr

    output = model.forward_head(output, pre_logits=True)
    # output is (batch_size, num_features) tensor

@inproceedings{liu2021swinv2,
  title={Swin Transformer V2: Scaling Up Capacity and Resolution}, 
  author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
  booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}

@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}}
}