to-be-snail

InternalError (see above for traceback): Blas SGEMM launch failed : m=802816, n=64, k=32

23

When I perform channel pruning on the mobilenet at ilsvrc12 dataset,this error occured. But the pruning at cifar10 dataset can be done normally.

Incompatible shapes: [64,1024,1,1] vs. [128,1024,1,1] error

9

Because pruning with RL method takes long long time,I use uniform prune method. But when evaluating after pruning,I got this error Incompatible shapes: [64,1024,1,1] vs. [128,1024,1,1] error. Here is the...

This template is for miscellaneous issues not covered by the other issue categories. For questions on how to work with PocketFlow, or support for problems that are not verified bugs...

I have add thirdparty/bins to environmental variables and add dependencies libgflags.lib to project,but I still have this problem "无法打开输入文件 libgflags.lib"

result error

8

I have tried convert_vgg.py and make a test,found that the result of keras model is different with the result of caffemodel, can you tell me why?