Wide ResNet

import torch
# load WRN-50-2:
model = torch.hub.load('pytorch/vision:v0.10.0', 'wide_resnet50_2', pretrained=True)
# or WRN-101-2
model = torch.hub.load('pytorch/vision:v0.10.0', 'wide_resnet101_2', 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 图像的小批量,其中 H
和 W
至少应为 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
与 ResNet 相比,Wide Residual networks 只是增加了通道数。否则,其架构是相同的。使用瓶颈块的更深层次的 ImageNet 模型在内部 3x3 卷积中增加了通道数。
wide_resnet50_2
和 wide_resnet101_2
模型在 FP16 中使用混合精度训练,并使用带热重启的 SGD 进行训练。检查点权重为半精度(批归一化除外),尺寸更小,也可用于 FP32 模型。
模型结构 | Top-1 错误率 | Top-5 错误率 | # 参数 |
---|---|---|---|
wide_resnet50_2 | 21.49 | 5.91 | 68.9M |
wide_resnet101_2 | 21.16 | 5.72 | 126.9M |
参考文献
