search

yikang-li / FactorizableNet

Factorizable Net (Multi-GPU version): An Efficient Subgraph-based Framework for Scene Graph Generation
216 stars 38 forks source link

image not getting loaded #24

Open Prudhvinik1 opened 5 years ago

Prudhvinik1 commented 5 years ago

/home/prudhvik/FactorNet/FactorizableNet/data/VRD/images/sg_test_images/161638840_4de67b36c9_o.jpg use_gt_boxes=args.use_gt_boxes) File "/home/prudhvik/FactorNet/FactorizableNet/models/HDN_v2/engines_v1.py", line 123, in test for i, sample in enumerate(loader): # (im_data, im_info, gt_objects, gt_relationships) File "/home/prudhvik/anaconda/envs/py2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 637, in next return self._process_next_batch(batch) File "/home/prudhvik/anaconda/envs/py2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 658, in _process_next_batch raise batch.exc_type(batch.exc_msg) AttributeError: Traceback (most recent call last): File "/home/prudhvik/anaconda/envs/py2/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 138, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/prudhvik/FactorNet/FactorizableNet/lib/datasets/VRD_loader.py", line 66, in getitem img_original_shape = img.shape AttributeError: 'NoneType' object has no attribute 'shape'

Hi, I see that some of the images are not being read by imread() function and causing this issue. I am using VRD dataset for evaluating the pretrained model.

varshanth commented 4 years ago

Same issue. @yikang-li , can you please let us know the fix?

yikang-li commented 4 years ago

Can you please provide the OpenCV version?

Did you use the dataset we provided?

Hastyrush commented 4 years ago

Hi @Prudhvinik1,

You should check if your symbolic link (ln -s /path/to/images F-Net/data/VRD/images) is done properly. The error means that the loader cannot find the specified folder to load the images from.

I encountered this problem as well, and I solved it by setting the correct link path to the image folder. Hope this helps!

muraliadithya commented 4 years ago

@yikang-li @Hastyrush I am having similar problems. I have the following questions: (i) I am currently using the VRD dataset using the link provided. It extracts to a folder called sg_dataset with two jsons and two other folders full of images inside it (one each for traning and testing images). Where should I put this, relative to the repository? (ii) What should the /path/to/images symlink point to? (iii) Once this issue clears up, where can I find predictions for the images, and if possible, how can I query the model on new images that I have?

Thanks a lot!

mkt1412 commented 3 years ago

@yikang-li @Hastyrush I am having similar problems. I have the following questions: (i) I am currently using the VRD dataset using the link provided. It extracts to a folder called sg_dataset with two jsons and two other folders full of images inside it (one each for traning and testing images). Where should I put this, relative to the repository? (ii) What should the /path/to/images symlink point to? (iii) Once this issue clears up, where can I find predictions for the images, and if possible, how can I query the model on new images that I have?

Thanks a lot!

Hi, I'm facing the same problem. Have you got it resolved? Thanks!

brleandro commented 3 years ago

I am having the same problem with the image data/VRD/images/sg_test_images/9535248286_31dee34cdf_b.jpg.

Does anyone know how to solve?