search

ijkguo / mx-rcnn

Parallel Faster R-CNN implementation with MXNet.
Other
671 stars 290 forks source link

Hi, When I run demo.py on CPU, there is a error: mxnet.base.MXNetError: [00:42:42] src/operator/./convolution-inl.h:299: Check failed: (param_.workspace) >= (required_size) Minimum workspace size: 1228800000 Bytes Given: 1073741824 Byteequired_size) Minimum workspace size: 1228800000 Bytes Given: 1073741824 Bytes #37

Closed alysazhang closed 7 years ago

alysazhang commented 7 years ago

Could it be possible running on CPU?

ijkguo commented 7 years ago

Yes, just change symbol_vgg,py and add workspace=2048 to all convolutional layers

alysazhang commented 7 years ago

Thanks a lot. Your advice is helpful.