Kaan Akan

Hi, we mostly used T4s or V100s for training our models. However, these GPUs are not necessary for the training process. You can change the batch size and use other...

Hi, Unfortunately, the code does not support multi-gpu training. You can only use one GPU for training or evaluation. We implemented the dataloader scheme a little different. We had a...

Hi, Thank you for your interest in our work. In the literature, the stochastic models generate more than one sample because the samples differ because of the latent variables. `nsample`...

Thank you for the response. I trained the model from scratch over ten different runs and I couldn't get the reported results in the repository. The results I got are...

Hello again, thank you for your response. I compiled the roi align using cuda and train 5 different runs with the up-to-date repository. Although there is an improvement in the...

Thank you. Did you report the maximum of the results you have got? e.g., best of 10 runs?

Hello, Sorry for the very late response. The results can change from training to training (also, from inference to inference) since our model is stochastic. You are right, these are...

Hello, As mentioned in the paper, we use the **posterior** distribution in the conditioning frames (t < receptive_field) to update the state variables. In the prediction phase (t > receptive_field),...

Hello, Thank you for your questions. The term `information leakage` is a little tricky here. It sounds like StretchBEV-P uses labels to predict the future, and the predicted future is...