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()

所有預訓練模型都要求輸入影像以相同的方式進行歸一化，即由形狀為 (3 x H x W) 的 3 通道 RGB 影像組成的小批次資料，其中 H 和 W 預計至少為 224。影像必須載入到 [0, 1] 範圍內，然後使用 mean = [0.485, 0.456, 0.406] 和 std = [0.229, 0.224, 0.225] 進行歸一化。

這是一個示例執行。

# 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 模型來自ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware論文。

傳統上，人們傾向於為所有硬體平臺設計一個高效模型。但是，不同的硬體具有不同的屬性，例如，CPU 頻率更高，而 GPU 更擅長並行化。因此，我們不是進行泛化，而是需要為不同的硬體平臺定製 CNN 架構。如下所示，在相似的準確度下，定製化在所有三個平臺上都提供了免費但顯著的效能提升。

模型結構	GPU 延遲	CPU 延遲	移動裝置延遲
proxylessnas_gpu	5.1毫秒	204.9毫秒	124毫秒
proxylessnas_cpu	7.4毫秒	138.7毫秒	116毫秒
proxylessnas_mobile	7.2毫秒	164.1毫秒	78毫秒

預訓練模型對應的 Top-1 準確度如下所示。

模型結構	Top-1 錯誤率
proxylessnas_cpu	24.7
proxylessnas_gpu	24.9
proxylessnas_mobile	25.4
proxylessnas_mobile_14	23.3

參考文獻

• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.