ValueError: operands could not be broadcast together with shapes (1216,800,4) (1,1,3) (1216,800,4)

ruoqianguo / cascade-rcnn_Pytorch

An implementation of Cascade R-CNN: Delving into High Quality Object Detection.

MIT License

437 stars 107 forks source link

ValueError: operands could not be broadcast together with shapes (1216,800,4) (1,1,3) (1216,800,4) #21

Open yuyijie1995 opened 5 years ago

yuyijie1995 commented 5 years ago

File "/home/jsu/cascade/cascade-rcnn_Pytorch/lib/roi_data_layer/minibatch.py", line 79, in _get_image_blob cfg.TRAIN.MAX_SIZE) File "/home/jsu/cascade/cascade-rcnn_Pytorch/lib/model/utils/blob.py", line 39, in prep_im_for_blob im -= pixel_means ValueError: operands could not be broadcast together with shapes (1216,800,4) (1,1,3) (1216,800,4) I maked a VOClike dataset used my data,but when I use it to train ,this error happened ,Can you give me some suggestions? Thanks

zizzizziz commented 4 years ago

I have the same questions. I want to know how do you deal with this error