FlowNetPytorch
FlowNetPytorch copied to clipboard
ClementPinard
Pytorch implementation of FlowNet by Dosovitskiy et al.
Hi, I try to use this implementation in my term project. However, I use the PIV image dataset instead of flying chairs. This dataset is a bit different from flying...
Code training used in the process: loss = multiscaleEPE(output, target, weights=args.multiscale_weights, sparse=args.sparse) flow2_EPE = args.div_flow * realEPE(output[0], target, sparse=args.sparse) I can't understand the loss function you designed, could you please...
At the bottom of README.md, there is a formula for ratate function which I think has a little typo. I suppose the correct formula is: ``` rotate: x,y,theta -> (x*cos(theta)...
When I try to run inference on my images with `run_inference.py` and a pre-trained model load in the google drive mentionned for it : https://drive.google.com/drive/folders/0B5EC7HMbyk3CbjFPb0RuODI3NmM I have this error :...
In the main.py file,there is a Normalization operation which is " transforms.Normalize(mean=[0.45, 0.432, 0.411], std=[1, 1, 1])". I was confused of the meaning of the values [0.45, 0.432, 0.411]. I...
div_flow is used for 2 reasons : Training is deemed more stable for low output target values. it was used by initial caffe code, and thus it makes this training...
Excuse me, is import spatial_correlation_sample the contents of the package to be installed?
Hi, In the data augmentation code, the rotation map is computed directly from the coordinates of the flow: https://github.com/ClementPinard/FlowNetPytorch/blob/79894dc7d9c81c7cc06ee03be13139f4e467bb4b/flow_transforms.py#L188-L192 Instead, I think it should rather rotate the flow according to...
Hello there, i'm tring to use this model to reconstruct result which showed in your .gif, but my results show quite different. I saved the output optical flow images and...
Metadata
Owner
Metadata
Pytorch implementation of FlowNet by Dosovitskiy et al.