pytorch0.4+cuda10.0+py3.6.5
代码:https://github.com/amdegroot/ssd.pytorch
问题1:RuntimeError: The shape of the mask [32, 8732] at index 0 does not match the shape of the indexed tensor [279424, 1] at index 0
解决:
修改multibox_loss.py
step1: switch the two lines 97,98:
loss_c = loss_c.view(num, -1)
loss_c[pos] = 0 # filter out pos boxes for now
step2: change the line144 N = num_pos.data.sum() to
N = num_pos.data.sum().double()
loss_l = loss_l.double()/N
loss_c = loss_c.double()/N
问题2:自动跳出迭代:
需要修改3个文件:detection.py; multibox_loss.py; train.py
https://github.com/kentaroy47/ssd.pytorch/commit/4dc4bcead9b5f2d12108a935c85a87dfca83fe82
在运行到3670 后,仍然跳出迭代
再次修改:train.py
batch_iterator = None
for iteration in range(args.start_iter, cfg['max_iter']):
if (not batc

在PyTorch 0.4、CUDA 10.0和Python 3.6.5环境下,SSD模型训练中遇到的问题及解决方案。包括RuntimeError关于mask形状的错误和训练过程中自动跳出迭代的修复。通过修改multibox_loss.py、detection.py、train.py等文件,成功训练到105000次,模型精度达到88%,LOSS约为2.7。
最低0.47元/天 解锁文章
1400





