Skip to content
This repository has been archived by the owner on Oct 30, 2019. It is now read-only.

I want to retrain a resnext_101_32*4d.Is it possible? #207

Open
lyl472324464 opened this issue Dec 26, 2018 · 0 comments
Open

I want to retrain a resnext_101_32*4d.Is it possible? #207

lyl472324464 opened this issue Dec 26, 2018 · 0 comments

Comments

@lyl472324464
Copy link

I got this error.
dooncloud@dooncloud-System-Product-Name:~/ResNeXt-master$ th main.lua -retrain pretrained/resnext_101_32x4d.t7 -data dooncloud_model/ -resetClassifier true -nClasses 6 Found Environment variable CUDNN_PATH = /usr/local/cuda/lib64/libcudnn.so.5Loading model from file: pretrained/resnext_101_32x4d.t7 => Replacing classifier with 6-way classifier /home/dooncloud/torch/install/bin/luajit: ...ooncloud/torch/install/share/lua/5.1/threads/threads.lua:183: [thread 2 callback] bad argument #2 to '?' (dimension 1 out of range of 0D tensor at /home/dooncloud/torch/pkg/torch/generic/Tensor.c:19)

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant