rangerToby

Results 6 comments of rangerToby

Getting Check failed: status == CUDNN_STATUS_SUCCESS (1 vs. 0) CUDNN_STATUS_NOT_INITIALIZED

try to reduce the batch_size value in prototxt

The alpha variable's value of "avg_pool" and "skip_connect" is the mostly biggest over the others

@shuangjian24 this happens on my own dataset cnn classification too, and i find something in paper PC-darts, which can explain this, pooling op(or skip connect) has no parameters so it...

验证时，输出的结果都是-1

hello，我使用的pytorch1.6在验证阶段会出现结果全是0，请问你的问题解决了么？

验证时，输出的结果都是-1

请问是怎么解决的呢，能分享一下么？

验证时，输出的结果都是-1

谢谢

Please explain the training steps using own dataset

hey, DebojitBiswas. I meet the same question, have you figure it out?