Video Predicting using ConvLSTM and pytorch
Repository for frame prediction on the MovingMNIST dataset using seq2seq ConvLSTM following either of these guides:
Make sure you have the following libraries installed!
python=3.6.8
torch=1.1.0
torchvision=0.3.0
pytorch-lightning=0.7.1
matplotlib=3.1.3
tensorboard=1.15.0a20190708
Install the above libraries
Clone this repo
git clone https://github.com/holmdk/Video-Prediction-using-PyTorch.git
cd ./Video-Prediction-using-PyTorch
python main.py
The first row displays our predictions, the second row the ground truth and the third row the absolute error on a pixel-level. The first 8 columns are the input, followed by output in the final 8 columns. This matches the output from the Tensorboard logging.
After some iterations, we notice that our model is actually generating images of all zeros! This is a common issue people using ConvLSTM reports, however, do not be discouraged! Simply keep training the model, and you should start to see actual and plausible future predictions.
Now, we are actually starting to see actual predictions, however blurry they might be.