resnet101.tv2_in1k 的模型卡片

一个ResNet-B图像分类模型。

这个模型具有以下特点：

• ReLU激活函数
• 单层7x7卷积池化
• 1x1卷积辅助下采样

在 torchvision 中使用 ImageNet-1k 训练得到，使用了 v2 recipes 次迭代。

模型详情

• 模型类型：图像分类 / 特征提取主干网络
• 模型统计：
  • 参数数量 (M)：44.5
  • GMACs：4.9
  • 激活数量 (M)：10.1
  • 图像尺寸：训练 = 176 x 176，测试 = 224 x 224
• 论文：
  • 深度残差学习用于图像识别： https://arxiv.org/abs/1512.03385
• 原始链接： https://github.com/pytorch/vision

模型使用

图像分类

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('resnet101.tv2_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)

特征图提取

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(
    'resnet101.tv2_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, 64, 88, 88])
    #  torch.Size([1, 256, 44, 44])
    #  torch.Size([1, 512, 22, 22])
    #  torch.Size([1, 1024, 11, 11])
    #  torch.Size([1, 2048, 6, 6])

    print(o.shape)

图像嵌入

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(
    'resnet101.tv2_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, 2048, 6, 6) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor

模型比较

在 timm 上探索这个模型的数据集和运行时指标： model results .

引用

@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}
}

@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}}
}