不断更新中。。。
1.问题:check failure stack trace:***
解决方法:路径错误,重新去看自己的路径是否有错误
2.Check failed: error == cudaSuccess (2 vs. 0) out of memory
解决方法:
显存不够 修改train_val.prototex的batch_size,我都调到1了,尼玛这是多小的显存啊
3.Check failed: target_blobs[j]->shape() == source_blob->shape() Cannot share param 0 weights from layer 'fc6'; shape mismatch. Source param shape is 4096 256 (1048576); target param shape is 4096 9216 (37748736)
解决方法:好像是你输入的训练图片和测试图片大小不一致。。。