本文共 1446 字，大约阅读时间需要 4 分钟。

ResNet50??????PyTorch???????? inference ??

????????ResNet50?????????????????????????????????????????????????????????????PyTorch??????ResNet50???????????????

??????

ResNet50??????????????????????Residual Blocks??????????????????

• ????[1, 3, 224, 224]????????????????
• ???1?[1, 64, 112, 112]
• ?????1?[1, 64, 112, 112]
• ?????ReLU?
• ??????[1, 64, 56, 56]
• ?1?[1, 256, 56, 56]
• ?2?[1, 512, 28, 28]
• ?3?[1, 1024, 14, 14]
• ?4?[1, 2048, 7, 7]
• ??????[1, 2048]
• ?????[1, 1000]

???????

??? inference ??????????????????PyTorch?????????????????????????????????????

??????

??????????????????

import cv2import timeimport osimport matplotlib.pyplot as pltimport torchfrom torch import nnimport torchvision.models as modelsimport torchvision.transforms as transformssavepath = 'vis_resnet50/features_elephant'if not os.path.exists(savepath):    os.mkdir(savepath)def draw_features(width, height, x, savename):    tic = time.time()    fig = plt.figure(figsize=(16, 16))    fig.subplots_adjust(left=0.05, right=0.95, bottom=0.05, top=0.95, wspace=0.05)    # ??????????    plt.imshow(x)    plt.savefig(os.path.join(savepath, savename))    plt.close()    toc = time.time()    print(f"?????{toc - tic:.2f}?")

????

• ?????ResNet50?????????????????[1, 3, 224, 224]?
• ??????????PyTorch???????????????
• ????????????????????????????????????????

????????????????ResNet50??????????????????????????

转载地址：http://taxz.baihongyu.com/