Cody的博客

数据格式XX.jpg lable1.jpg 1Codedata_transforms = { 'train': transforms.Compose([ #transforms.RandomHorizontalFlip(), transforms.Resize((64, 64)), transforms.ToTensor(), ...

训练import torchimport torch.nn as nnimport torch.nn.functional as Fimport torch.optim as optimimport torch.backends.cudnn as cudnnimport numpy as npfrom data_gen import OccGenDatasetfrom model ...

Pytorch To Caffemmdnn目前只支持pytorch0.4.0网络前向尽量不要使用中间变量（下面是打印的node）支持的层：layer_map = {'onnx::Conv': 'Conv','onnx::Flatten': 'Flatten','onnx::Gemm': 'FullyConnected','onnx::MaxPool': 'Maxpool','o...