tf-faster-rcnn icon indicating copy to clipboard operation
tf-faster-rcnn copied to clipboard

shape not found when finetune

Open Yiman-GO opened this issue 5 years ago • 1 comments

I got an error when I use . ./experiments/scripts/train_faster_rcnn.sh 0 pascal_voc res101 USE_GPU_NMS False . The error is as follows: Traceback (most recent call last): File "./tools/trainval_net.py", line 110, in imdb, roidb = combined_roidb(args.imdb_name) File "./tools/trainval_net.py", line 77, in combined_roidb roidb = get_roidb(imdb_names.split('+')[0]) File "./tools/trainval_net.py", line 73, in get_roidb roidb = get_training_roidb(imdb) File "/home/zfit/PycharmProjects/TENSORFLOW/tf-faster-rcnn_disc/tools/../lib/model/train_val.py", line 332, in get_training_roidb rdl_roidb.prepare_roidb(imdb) File "/home/zfit/PycharmProjects/TENSORFLOW/tf-faster-rcnn_disc/tools/../lib/roi_data_layer/roidb.py", line 38, in prepare_roidb gt_overlaps = roidb[i][b'gt_overlaps'].toarray() File "/home/zfit/anaconda3/envs/tensorflow/lib/python3.6/site-packages/scipy/sparse/compressed.py", line 962, in toarray out = self._process_toarray_args(order, out) File "/home/zfit/anaconda3/envs/tensorflow/lib/python3.6/site-packages/scipy/sparse/base.py", line 1187, in _process_toarray_args return np.zeros(self.shape, dtype=self.dtype, order=order) File "/home/zfit/anaconda3/envs/tensorflow/lib/python3.6/site-packages/scipy/sparse/base.py", line 689, in getattr raise AttributeError(attr + " not found") AttributeError: shape not found

Yiman-GO avatar May 10 '19 07:05 Yiman-GO

I have tried print(roidb[i][b'gt_overlaps']), got "shape not found" too. Does anyone know why?

Yiman-GO avatar May 10 '19 07:05 Yiman-GO