公版的mask 具体是指什么呢
直接在MLU上运行您的代码 无论逐层或是融合 会报错:
Traceback (most recent call last):
File "mlu_trace_test.py", line 192, in <module>
quantized_net_mlu(randn_mlu.to(ct.mlu_device()))
File "/torch/venv3/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "/torch/src/catch/examples/online/mask-rcnn/models/maskrcnn-benchmark-master/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 69, in forward
proposals, proposal_losses = self.rpn(images, features, self.Anchors_mlu, targets)
File "/torch/venv3/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "/torch/src/catch/examples/online/mask-rcnn/models/maskrcnn-benchmark-master/maskrcnn_benchmark/modeling/rpn/rpn.py", line 173, in forward
im_min_w, nms_scale, nms_threshold, TO_REMOVE)
RuntimeError: torch_mlu::proposal_fpn() Expected a value of type 'Tensor' for argument '_2' but instead found type 'NoneType'.
Position: 2
Value: None
Declaration: torch_mlu::proposal_fpn(Tensor[] _0, Tensor[] _1, Tensor _2, int[] _3, int[] _4, int _5, int _6, int _7, int _8, int _9, float _10, float _11, float _12, float _13, float _14) -> (Tensor _0, Tensor _1)
请登录后评论