python实现Inception Score代码（读取自己生成的图片）

Zhang庆欢

已于 2022-07-31 01:34:20 修改

阅读量3k

点赞数 4

分类专栏： python代码文章标签： python 深度学习 pytorch

于 2022-07-31 01:05:00 首次发布

本文链接：https://blog.youkuaiyun.com/qq_39909808/article/details/126080166

版权

利用Inception Score衡量自己的模型生成的图片多样性

代码：

import torch
from torch import nn
from torch.nn import functional as F
import torch.utils.data
from torchvision.models.inception import inception_v3
import numpy as np
from tqdm import tqdm
from PIL import Image
import os
from scipy.stats import entropy

# we should use same mean and std for inception v3 model in training and testing process
# reference web page: https://pytorch.org/hub/pytorch_vision_inception_v3/
mean_inception = [0.485, 0.456, 0.406]
std_inception = [0.229, 0.224, 0.225]

def imread(filename):
    """
    Loads an image file into a (height, width, 3) uint8 ndarray.
    """
    return np.asarray(Image.open(filename), dtype=np.uint8)[..., :3]

def inception_score(batch_size=50, resize=True, splits=10)