planckztd

Results 6 comments of planckztd

训练非常的慢，有什么好建议？

@cardwing @XingangPan 您好，我在测试和训练过程中都出现了如下的错误，想问一下是不是cudnn的版本问题，我的cuda是８．０，cudnn　v4 data created data loaded data loaded 1 bad /home/kb457/torch/install/bin/luajit: /home/kb457/torch/install/share/lua/5.1/nn/Container.lua:67: In 2 module of nn.Sequential: ...torch/install/share/lua/5.1/cudnn/BatchNormalization.lua:69: bad argument #1 to 'resizeAs' (torch.CudaTensor expected, got userdata) stack...

How to make the game automatically recognize and run all the replay files in the folder ?

I want the same function, too.

I want to ask for someone's yolo_net pretrain model, not the yolo_tiny_net

OK， I had worked it out. maybe the error caused by losses change too many. Add batch normalization after conv layers or fully connected layers to avoid the loss to...

Using Linux or Windows for this project?

I also find it difficult. Author said that you need linux to train your model. refer to:[https://torchcraft.github.io/TorchCraftAI/docs/install-windows.html](url)

dimension out of range (expected to be in range of [-1, 0], but got 1)

the same problem,we need some help @CXY573

RCNN_roi_align ERROR when training

I meet the same problem, and solved now. thanks @AshStuff