Open Crestina2001 opened 4 months ago
The config is like:
convlstm: False convgru: False batch_size: 4 lr: 0.0001 frames_input: 10 frames_output: 10 epochs: 20
When convlstm and convgru are both False, it actually uses convgru.
Here is the result using convlstm(epochs: 20):
After training for 150 epochs, the result seem to improve, but not by much. I get the best val loss when epoch = 144. Here is the visualization: It is still far from satisfaction.
guru,hello!Could you share your code with me.Great thanks!
Could anyone offer a solution. Many thanks.