Fenil Doshi comments

Repositories
Issues
Comments

Results 4 comments of


                                            Fenil Doshi

Inference time evaluation input size and TX2 backend

The input size is 1232x368. The image is cropped before passing through the model. You can see this is Dataloader/KITTILoader.py

Prediction/Eval on Middlebury dataset

Did you finetune the model on Middlebury dataset or did you just use the pre-trained model(for 10 epochs) on Sceneflow dataset?

Prediction/Eval on Middlebury dataset

Also, I was wondering, how much time did it take for you to run the image through the model. For an 816x1056 image, the prediction time for the network is...

No module named 'libs.GANet.build.lib'

You will first need to run compile.sh and only then the lib folder will be created in the build. Then, you can run predict.sh