ValueError: could not broadcast input array from shape (4) into shape (0)

[MuhammadAli1214]

Hi there,
I am getting this error when I try to run the training script. Full error message is given below.

Traceback (most recent call last):
File "upsnet/upsnet_end2end_train.py", line 403, in
upsnet_train()
File "upsnet/upsnet_end2end_train.py", line 269, in upsnet_train
output = train_model(*batch)
File "/home/kvml/anaconda3/envs/upsnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "upsnet/../lib/utils/data_parallel.py", line 110, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/kvml/anaconda3/envs/upsnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "upsnet/../upsnet/models/resnet_upsnet.py", line 110, in forward
rois, cls_label, bbox_target, bbox_inside_weight, bbox_outside_weight, mask_rois, mask_target, roi_has_mask, nongt_inds = self.proposal_target(rois, label['roidb'], data['im_info'])
File "/home/kvml/anaconda3/envs/upsnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "upsnet/../upsnet/operators/modules/proposal_mask_target.py", line 49, in forward
frcn_blobs = sample_rois(entry, im_info[im_i, 2], im_i)
File "upsnet/../upsnet/bbox/sample_rois.py", line 105, in sample_rois
bbox_targets, bbox_inside_weights = _expand_bbox_targets(bbox_targets)
File "upsnet/../upsnet/bbox/sample_rois.py", line 180, in _expand_bbox_targets
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
ValueError: could not broadcast input array from shape (4) into shape (0)

Could anyone please help me with this issue?

[rlangefe]

Were you able to solve this? I have the same issue when I run mine.