Open omerbrandis opened 3 years ago
hi
value of img_metas in SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/inference.py", line 197 at runtime (prior to ori_shape = (img_metas[i][1],img_metas[i][0])) is None.
omer.
i encountered the same problem, @omerbrandis were u able to solve it?
hello
I've tried running /SipMask/SipMask-benchmark$ python demo/fcos_demo.py --config-file configs/ffr/ffr-sipmask_R_50_FPN_1x.yaml --weights training_dir/ffr_50/model_0090000.pth --images-dir datasets/ffr/images/
returned following error: Traceback (most recent call last): File "demo/fcos_demo.py", line 113, in
main()
File "demo/fcos_demo.py", line 104, in main
composite = coco_demo.run_on_opencv_image(img)
File "/home/ubuntu/SipMask/SipMask-benchmark/demo/predictor.py", line 172, in run_on_opencv_image
predictions = self.compute_prediction(image)
File "/home/ubuntu/SipMask/SipMask-benchmark/demo/predictor.py", line 205, in compute_prediction
predictions = self.model(image_list)
File "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, kwargs)
File "/home/ubuntu/SipMask/SipMask-benchmark/fcos_core/modeling/detector/generalized_rcnn.py", line 51, in forward
proposals, proposal_losses = self.rpn(images, features, imge_metas, targets)
File "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, *kwargs)
File "/home/ubuntu/SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/sipmask.py", line 239, in forward
centerness, box_cof, box_mask, images.image_sizes, img_metas
File "/home/ubuntu/SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/sipmask.py", line 257, in _forward_test
centerness, box_cof, box_mask, image_sizes, img_metas
File "/home/ubuntu/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(input, kwargs)
File "/home/ubuntu/SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/inference.py", line 163, in forward
boxlists = self.select_over_all_levels(boxlists, feat_masks, image_sizes, img_metas)
File "/home/ubuntu/SipMask/SipMask-benchmark/fcos_core/modeling/rpn/sipmask/inference.py", line 197, in select_over_all_levels
ori_shape = (img_metas[i][1],img_metas[i][0])
TypeError: 'NoneType' object is not subscriptable
please advise, Omer