roi_align() issue

[LucasHu]

solved

[GMYelims]

Traceback (most recent call last):
File "inference_1.py", line 142, in
net.inference(image, config, Network)
File "inference_1.py", line 47, in inference
pred_boxes = net(resized_img.cuda(0), im_info.cuda(0)).numpy()
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "../model/rcnn_emd_refine/network.py", line 32, in forward
return self._forward_test(image, im_info)
File "../model/rcnn_emd_refine/network.py", line 50, in _forward_test
pred_bbox = self.RCNN(fpn_fms, rpn_rois)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "../model/rcnn_emd_refine/network.py", line 86, in forward
pool_features = roi_pooler(fpn_fms, rcnn_rois, stride, (7, 7), "ROIAlignV2")
File "../lib/layers/pooler.py", line 42, in roi_pooler
sampling_ratio=-1, aligned=pooler_aligned)
TypeError: roi_align() got an unexpected keyword argument 'aligned'``

Did you have the same error?how to solve this?