将训好的模型的参数赋值给另外一个网络,
在测试赋值是否正确的时候,在
output = model(input)
一直报错:
runtime error: CUDNN_STATUS_MAPPING_ERROR
多方调试无果。
参考failed to enqueue CUDNN_STATUS_MAPPING_ERROR
In Cudnn documentation about this particular error:
CUDNN_STATUS_MAPPING_ERROR
An access to GPU memory space failed, which is usually caused by a failure to bind a texture.
To correct: prior to the function call, unbind any previously bound textures.
Otherwise, this may indicate an internal error/bug in the library.
参考RuntimeError: CUDNN_STATUS_MAPPING_ERROR,
才发现是model没有放在 gpu上,而Input在 gpu上。增加
model = model.cuda()
就解决了。