resnet33ts.ra2_in1k 模型卡片

一个ResNet图像分类模型。该模型采用了三层分层的干细胞架构，没有池化层，并且使用了SiLU激活函数。由Ross Wightman在timm中使用ImageNet-1k数据集进行训练。

该模型架构是使用timm的灵活的 BYOBNet (Bring-Your-Own-Blocks Network) 实现的。

BYOBNet可以配置以下内容：

• block / stage布局
• 干细胞布局
• 输出步幅（膨胀率）
• 激活和规范化层
• 通道和空间/自注意力层

...并且还包括timm中许多其他架构常见的功能，包括：

• 随机深度（stochastic depth）
• 梯度检查点（gradient checkpointing）
• 分层学习率衰减（layer-wise LR decay）
• 每个阶段的特征提取（per-stage feature extraction）

模型细节

• 模型类型：图像分类 / 特征主干
• 模型统计信息：
  • 参数数量（M）：19.7
  • GMACs：4.8
  • 激活值（M）：11.7
  • 图像尺寸：训练 = 256 x 256，测试 = 288 x 288
• 论文：
  • @: a
• 数据集：ImageNet-1k
• 原始模型： https://github.com/huggingface/pytorch-image-models

模型用途

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('resnet33ts.ra2_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(
    'resnet33ts.ra2_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, 256, 64, 64])
    #  torch.Size([1, 512, 32, 32])
    #  torch.Size([1, 1536, 16, 16])
    #  torch.Size([1, 1280, 8, 8])

    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(
    'resnet33ts.ra2_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, 1280, 8, 8) shaped tensor

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

模型比较

在timm中探索此模型的数据集和运行时指标 model results .

引用

@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}}
}

r