Thanks for your issue. To help us better solve the issue, please provide the following information:
PaddleRS version: (please specify the branch as well,e.g. PaddleRS release/1.0)
PaddlePaddle version: (e.g. PaddlePaddle 2.3.0)
Operation system: (e.g. Linux/Windows/MacOS)
Python version: (e.g. Python3.7/8)
CUDA/cuDNN version: (e.g. CUDA10.2/cuDNN 7.6.5)
Additional context: (add any other context about the problem)
欢迎您的提问。辛苦您提供以下信息,以方便我们快速定位和解决问题:
PaddleRS版本:PaddleRS dev/1.0
PaddlePaddle版本:PaddlePaddle 2.4.0
操作系统信息:Linux
Python版本号:Python3.9)
CUDA/cuDNN版本:如CUDA11.4
其他内容: (增加其他与问题相关的内容):
InvalidArgumentError: The 'shape' in ReshapeOp is invalid. The input tensor X'size must be equal to the capacity of 'shape'. But received X's shape = [1, 4, 256, 256], X's size = 262144, 'shape' is [1, 4, 1, 4096], the capacity of 'shape' is 16384.
[Hint: Expected capacity == in_size, but received capacity:16384 != in_size:262144.] (at /paddle/paddle/fluid/operators/reshape_op.cc:230)
[operator < reshape2 > error]
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.
Thanks for your issue. To help us better solve the issue, please provide the following information:
欢迎您的提问。辛苦您提供以下信息,以方便我们快速定位和解决问题: