ProxylessNAS

import torch
target_platform = "proxyless_cpu"
# proxyless_gpu, proxyless_mobile, proxyless_mobile14 are also avaliable.
model = torch.hub.load('mit-han-lab/ProxylessNAS', target_platform, pretrained=True)
model.eval()

所有预训练模型都要求输入图像以相同方式进行归一化，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，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

ProxylessNAS 模型来自 ProxylessNAS: 在目标任务和硬件上直接进行神经网络架构搜索 论文。

通常，人们倾向于为“所有硬件平台”设计“一个高效模型”。但不同硬件具有不同特性，例如，CPU 频率更高，而 GPU 更擅长并行化。因此，与其泛化，不如为不同硬件平台**专门化** CNN 架构。如下所示，在相似准确度下，专门化在所有三个平台上都带来了免费而显著的性能提升。

模型结构	GPU 延迟	CPU 延迟	移动设备延迟
proxylessnas_gpu	5.1ms	204.9ms	124ms
proxylessnas_cpu	7.4ms	138.7ms	116ms
proxylessnas_mobile	7.2ms	164.1ms	78ms

预训练模型的相应 top-1 准确率如下所示。

模型结构	Top-1 错误率
proxylessnas_cpu	24.7
proxylessnas_gpu	24.9
proxylessnas_mobile	25.4
proxylessnas_mobile_14	23.3

参考文献

• ProxylessNAS: 在目标任务和硬件上直接进行神经网络架构搜索.