11 2022 档案
摘要:import torchvision import torch input_ = torch.rand(3, 128, 24, 96) #[b,c,h,w] bbox = [[0,0.1,0.15,0.4,0.6], [0,0.1,0.15,0.4,0.6], [1,0.01,0.15,0.4,0.
阅读全文
摘要:#pytorch net = net_now() state_dict = torch.load(model_path, map_location=lambda storage, loc: storage) net.load_state_dict(state_dict, strict=True) #
阅读全文
摘要:曾几何时,我一直都是记忆的>> 可以保存终端打印的到本地txt 比如: who >> use 确实会在本地生成use文件,然后打开文本use就会有如下信息: algo tty7 2022-10-27 19:38 (:0) algo pts/21 2022-11-10 18:25 (10.188.18
阅读全文
摘要:根据caffe训练打印的 I1102 20:42:49.268401 188 solver.cpp:352] Iteration 135020 (0.108123 iter/s, 92.4871s/10 iter), 114.5/13668.5ep, loss = 0.0899582 提取itera
阅读全文