IBN-Net

import torch
model = torch.hub.load('XingangPan/IBN-Net', 'resnet50_ibn_a', pretrained=True)
model.eval()

所有预训练模型都要求输入图像以相同方式归一化，即形状为 (3 x H x W) 的 3 通道 RGB 图像的迷你批次，其中 H 和 W 预期至少为 224。图像必须加载到 [0, 1] 范围内，然后使用 mean = [0.485, 0.456, 0.406] 和 std = [0.229, 0.224, 0.225] 进行归一化。

这是一个示例执行。

# Download an example image from the pytorch website
import urllib
url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
try: urllib.URLopener().retrieve(url, filename)
except: urllib.request.urlretrieve(url, filename)

# sample execution (requires torchvision)
from PIL import Image
from torchvision import transforms
input_image = Image.open(filename)
preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model

# move the input and model to GPU for speed if available
if torch.cuda.is_available():
    input_batch = input_batch.to('cuda')
    model.to('cuda')

with torch.no_grad():
    output = model(input_batch)
# Tensor of shape 1000, with confidence scores over ImageNet's 1000 classes
print(output[0])
# The output has unnormalized scores. To get probabilities, you can run a softmax on it.
probabilities = torch.nn.functional.softmax(output[0], dim=0)
print(probabilities)

# Download ImageNet labels
!wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt

# Read the categories
with open("imagenet_classes.txt", "r") as f:
    categories = [s.strip() for s in f.readlines()]
# Show top categories per image
top5_prob, top5_catid = torch.topk(probabilities, 5)
for i in range(top5_prob.size(0)):
    print(categories[top5_catid[i]], top5_prob[i].item())

模型描述

IBN-Net 是一种具有域/外观不变性的 CNN 模型。受风格迁移工作的启发，IBN-Net 将实例归一化和批量归一化巧妙地统一在一个深度网络中。它提供了一种简单的方法来同时提高建模和泛化能力，而无需增加模型复杂性。IBN-Net 特别适用于跨域或人/车辆再识别任务。

下面列出了 ImageNet 数据集上预训练模型的相应准确率。

模型名称	Top-1 准确率	Top-5 准确率
resnet50_ibn_a	77.46	93.68
resnet101_ibn_a	78.61	94.41
resnext101_ibn_a	79.12	94.58
se_resnet101_ibn_a	78.75	94.49

下面列出了两个 Re-ID 基准 Market1501 和 DukeMTMC-reID 上的 rank1/mAP（来自 michuanhaohao/reid-strong-baseline）。

骨干网络	Market1501	DukeMTMC-reID
ResNet50	94.5 (85.9)	86.4 (76.4)
ResNet101	94.5 (87.1)	87.6 (77.6)
SeResNet50	94.4 (86.3)	86.4 (76.5)
SeResNet101	94.6 (87.3)	87.5 (78.0)
SeResNeXt50	94.9 (87.6)	88.0 (78.3)
SeResNeXt101	95.0 (88.0)	88.4 (79.0)
ResNet50-IBN-a	95.0 (88.2)	90.1 (79.1)

参考文献

• 一箭双雕：通过 IBN-Net 增强学习和泛化能力