pnasnet5large.tf_in1k模型卡

一个PNasNet图像分类模型。由论文作者在ImageNet-1k上进行训练。通过Cadene的pretrained-models.pytorch从Tensorflow移植而来。

模型详情

• 模型类型：图像分类/特征主干
• 模型统计信息：
  • 参数数量（百万）：86.1
  • GMACs：25.0
  • 激活数量（百万）：92.9
  • 图像尺寸：331 x 331
• 相关论文：
  • 渐进式神经架构搜索： https://arxiv.org/abs/1712.00559
• 原始论文：
  • https://github.com/tensorflow/models
  • https://github.com/Cadene/pretrained-models.pytorch
• 数据集： ImageNet-1k

模型用法

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('pnasnet5large.tf_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(
    'pnasnet5large.tf_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, 96, 165, 165])
    #  torch.Size([1, 270, 83, 83])
    #  torch.Size([1, 1080, 42, 42])
    #  torch.Size([1, 2160, 21, 21])
    #  torch.Size([1, 4320, 11, 11])

    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(
    'pnasnet5large.tf_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, 4320, 11, 11) shaped tensor

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

模型比较

在timm model results 中探索此模型的数据集和运行时指标。

引用

@misc{liu2018progressive,
  title={Progressive Neural Architecture Search}, 
  author={Chenxi Liu and Barret Zoph and Maxim Neumann and Jonathon Shlens and Wei Hua and Li-Jia Li and Li Fei-Fei and Alan Yuille and Jonathan Huang and Kevin Murphy},
  year={2018},
  eprint={1712.00559},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}