import torch
model = torch.hub.load('pytorch/vision:v0.10.0', 'inception_v3', pretrained=True)
model.eval()

所有预训练模型都期望以相同方式归一化输入图像,即形状为 (3 x H x W) 的 3 通道 RGB 图像 mini-batch,其中 HW 期望至少为 299。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。

以下是示例执行。

# 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(299),
    transforms.CenterCrop(299),
    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

Inception v3:基于对网络扩展方式的探索,旨在通过适当分解的卷积和强力正则化来尽可能高效地利用增加的计算量。我们在 ILSVRC 2012 分类挑战赛验证集上对我们的方法进行了基准测试,证明了相较于最新技术取得了显著提升:使用计算成本为每次推理 50 亿次乘加运算且参数少于 2500 万的网络进行单帧评估时,top-1 错误率为 21.2%,top-5 错误率为 5.6%。通过 4 个模型的集成和多裁剪评估,我们在验证集上的 top-5 错误率为 3.5%(测试集上为 3.6%),验证集上的 top-1 错误率为 17.3%。

使用预训练模型在 ImageNet 数据集上的单裁剪错误率如下所示。

模型结构 Top-1 错误率 Top-5 错误率
inception_v3 22.55 6.44

参考文献