search

wkcn / AttentionSampler

Attention-based sampler in TASN (Trilinear Attention Sampling Network)
23 stars 0 forks source link

File "./AttentionSampler/attention_sampler/attention_sampler.py", line 26, in forward #1

Closed tiancity-bytedance closed 5 years ago

tiancity-bytedance commented 5 years ago

I tried you code, but get this error File "/usr/local/lib/python3.6/site-packages/mxnet-1.3.1-py3.6.egg/mxnet/operator.py", line 987, in forward_entry aux=tensors[4]) File "/mnt/cephfs_hl/vc/zhangtiancheng/finegrained/code/TASN/MobulaOP/mobula/glue/mx.py", line 88, in forward out = self._forward(*in_data) File "./AttentionSampler/attention_sampler/attention_sampler.py", line 26, in forward self.F.broadcast_minimum(threshold, attx, out=attx) File "<string>", line 48, in broadcast_minimum File "/usr/local/lib/python3.6/site-packages/mxnet-1.3.1-py3.6.egg/mxnet/_ctypes/ndarray.py", line 92, in _imperative_invoke ctypes.byref(out_stypes))) File "/usr/local/lib/python3.6/site-packages/mxnet-1.3.1-py3.6.egg/mxnet/base.py", line 253, in check_call raise MXNetError(py_str(_LIB.MXGetLastError())) mxnet.base.MXNetError: [10:27:32] src/operator/tensor/./elemwise_binary_broadcast_op.h:68: Check failed: l == 1 || r == 1 operands could not be broadcast together with shapes [12,1] [12,512,1]

wkcn commented 5 years ago

Thank you for the report! I will check it.

wkcn commented 5 years ago

Hi, @tiancity-bytedance, I have fixed it.

wkcn commented 5 years ago

Close it since the bug has been fixed. If there is any question, feel free to reopen this issue : )