inference issue

[fatandfat]

Hi I'm trying to inference on some of my images and it runs successfully with images with 4:3 ratio, but when I tried on images with size 720*480 there shows some error

• (planerecnet) kb249@kb249:/media/kb249/K/liuxiaohan/PlaneRecNet$ python simple_inference.py --config=PlaneRecNet_101_config --trained_model=weights/PlaneRecNet_101_9_125000.pth --image=test_images/00000206_10002.jpg Inference image: test_images/00000206_10002.jpg /home/kb249/anaconda3/envs/planerecnet/lib/python3.6/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] Traceback (most recent call last): File "simple_inference.py", line 357, in inference_image(net, args.image, depth_mode=args.depth_mode) File "simple_inference.py", line 152, in inference_image results = net(batch) File "/home/kb249/anaconda3/envs/planerecnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, *kwargs) File "/media/kb249/K/liuxiaohan/PlaneRecNet/planerecnet.py", line 93, in forward mask_pred = self.mask_head(mask_features) File "/home/kb249/anaconda3/envs/planerecnet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(input, kwargs) File "/media/kb249/K/liuxiaohan/PlaneRecNet/planerecnet.py", line 492, in forward feature_add_all_level += self.convs_all_levelsi RuntimeError: The size of tensor a (107) must match the size of tensor b (108) at non-singleton dimension 2

And this is my test image

[EryiXie]

Hi, that's because the image width and height should be divisible by 32. You can write a small function to pad zeros to the resized image so that H and W are divisible by 32. I will also do the same in the next update.

[fatandfat]

Hi, that's because the image width and height should be divisible by 32. You can write a small function to pad zeros to the resized image so that H and W are divisible by 32. I will also do the same in the next update.

ok thanks for your reply and great work