ValueError: could not broadcast input array from shape (2,17100,1) into shape (17100,1)

[zhuyanfang000]

who knows why?T-T I'm crazy!
I0331 21:30:19.628304 16920 net.cpp:744] Ignoring source layer fc1000
I0331 21:30:19.628332 16920 net.cpp:744] Ignoring source layer prob
Solving...
Traceback (most recent call last):
File "./tools/train_net.py", line 112, in
max_iters=args.max_iters)
File "/home/omnisky/faster-rcnn-resnet-master/tools/../lib/fast_rcnn/train.py", line 160, in train_net
model_paths = sw.train_model(max_iters)
File "/home/omnisky/faster-rcnn-resnet-master/tools/../lib/fast_rcnn/train.py", line 101, in train_model
self.solver.step(1)
File "/home/omnisky/faster-rcnn-resnet-master/tools/../lib/rpn/proposal_layer.py", line 122, in forward
proposals = bbox_transform_inv(anchors, bbox_deltas)
File "/home/omnisky/faster-rcnn-resnet-master/tools/../lib/fast_rcnn/bbox_transform.py", line 53, in bbox_transform_inv
pred_boxes[:, 0::4] = pred_ctr_x - 0.5 * pred_w
ValueError: could not broadcast input array from shape (2,17100,1) into shape (17100,1)

[Microos]

you shall check your anchor numbers to see if they are consistent in related layers