yaorong0921
yaorong0921
@mikumeow Hi, could you please share your code which works on the Keras's example? Many thanks :-)
Hello @ae208gpu, I am using Windows and do not encounter any problems. Could you please try with a win system?
Hi @ae208gpu, I will try to find the script for combining since it was on a server that I am now having problems accessing. BTW, please refer to [this explanation](https://github.com/yaorong0921/Driver-Intention-Prediction/issues/4),...
> @yaorong0921 which model was used to generate the flownet images ? Hi @Sidd1609 , We used [FlowNet 2.0](https://github.com/NVIDIA/flownet2-pytorch) to extract the optical flow of all outside images.
Hi @wasilone11, for visualizing, I output results from the model for each test sample at each time step. Then I made the demo video with subtitles indicating the prediction (I...
Hi, could you please check whether there are images in each folder? It seems that the number of images is not correct.
Hi, please give ``--no_train`` when you run the script so you will start the evaluation.
Hi, I have tried the link to download and unzip the optical flow images, and there was no error. Could you please try again, maybe use Windows?
Hi, I meant that I could unzip the optical flow zip file (downloaded via the link) without error. Could you unzip it and maybe use windows?
Dear @jihwan722, Before the decoder, there is a convLSTM encoder. Table II refers to the output after the encoder. Did you include it in the pipeline?