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 HW 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]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_a77.4693.68
resnet101_ibn_a78.6194.41
resnext101_ibn_a79.1294.58
se_resnet101_ibn_a78.7594.49

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Market1501DukeMTMC-reID
ResNet5094.5 (85.9)86.4 (76.4)
ResNet10194.5 (87.1)87.6 (77.6)
SeResNet5094.4 (86.3)86.4 (76.5)
SeResNet10194.6 (87.3)87.5 (78.0)
SeResNeXt5094.9 (87.6)88.0 (78.3)
SeResNeXt10195.0 (88.0)88.4 (79.0)
ResNet50-IBN-a95.0 (88.2)90.1 (79.1)

参考文献

具有域/外观不变性的网络

模型类型: 视觉
提交者: 潘星钢