inception_v4.tf_in1k模型卡片

一个Inception-v4图像分类模型。通过Cadene的pretrained-models.pytorch从Tensorflow移植而来，训练于ImageNet-1k论文作者。

模型细节

• 模型类型：图像分类 / 特征骨干
• 模型统计:
  • 参数 (M)：42.7
  • GMACs: 12.3
  • 激活数 (M): 15.1
  • 图像大小: 299 x 299
• 论文:
  • https://arxiv.org/abs/1602.07261 : https://arxiv.org/abs/1602.07261
• 原始:
  • https://github.com/tensorflow/models
  • https://github.com/Cadene/pretrained-models.pytorch
• 数据集: ImageNet-1k

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('inception_v4.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(
    'inception_v4.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, 64, 147, 147])
    #  torch.Size([1, 160, 73, 73])
    #  torch.Size([1, 384, 35, 35])
    #  torch.Size([1, 1024, 17, 17])
    #  torch.Size([1, 1536, 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(
    'inception_v4.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, 1536, 8, 8) shaped tensor

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

模型对比

在timm中探索该模型的数据集和运行时指标 model results 。

引用

@article{Szegedy2016Inceptionv4IA,
  title={Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning},
  author={Christian Szegedy and Sergey Ioffe and Vincent Vanhoucke and Alexander A. Alemi},
  journal={ArXiv},
  year={2016},
  volume={abs/1602.07261}
}