YYZ-rose
YYZ-rose
@leviome 我只是想批量测试图片后，计算map。
@404hasbeenfound 你测试完后是不是只有生成图片？没有相应的txt文件
@louxy126 请问这个命令应该怎么写的？直接在python yolo.py后面接上吗？还是通过代码把它print出来
@louxy126 万分感谢你的回复！！！！！谢谢了！！！！
有没有人用这个网络跑过公开的数据集，这个网络的效果在voc这些数据集上表现的怎么样啊？
@BlueBlueFF can u share your code which train and test on VOCdataset? i am look forward train and test on VOCdataset.thank u~
@Tuyota i think it ，u have used python3.6 . i have same problem zhu shi xiong
i meet the same problem, i try this modle by my data,but loss don't decrease. ok tanggong this name is chinese name. 这个损失是什么鬼！我到2万多轮损失还是2千多 @tangdong1994
Traceback (most recent call last): File "train_test.py", line 455, in train() File "train_test.py", line 321, in train loss_l, loss_c = criterion(out, priors, targets) File "/home/yangyuze/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__ result...