a961009

Results 3 comments of a961009

Weird results from pretrained model on KITTI images

Here are more results at different scenes ![2011_09_26_drive_0001_sync_02-0000000039_displayImage](https://user-images.githubusercontent.com/48381323/156875625-221ecffd-6573-43ca-8997-a3883b9aefb3.jpg) ![2011_09_26_drive_0009_sync_02-0000000375_displayImage](https://user-images.githubusercontent.com/48381323/156875633-dd49ce53-9dee-46d5-82c4-e93b5defc422.jpg) ![2011_09_26_drive_0015_sync_02-0000000266_displayImage](https://user-images.githubusercontent.com/48381323/156875636-1a142305-5b98-4e52-abf0-b3b25012f795.jpg)

Weird results from pretrained model on KITTI images

https://github.com/ClementPinard/SfmLearner-Pytorch/blob/c2374d50f816e976c6889eb5e07198749d953bc6/run_inference.py#L66 should be `tensor_img = ((tensor_img/255 - 0.5)/0.5).to(device)`

Weird results from pretrained model on KITTI images

> Thanks for your quick reply. After dividing by 255, the results become reasonable as mentioned in original paper. I'll keep you updated, when i find something.