Training on the ETH dataset.
Closed this issue · 1 comments
huang-xx commented
For the case where the prediction length is 8 time-steps, the result in the paper will appear at the 256th epoch. No need to change parameters.
For the case where the prediction length is 12 time-steps, do the following things:
- Change "lr" to
1e-5
in line 148 and 149 in train.py; - Change value
150
to30
in line 173 in train.py; - Comment out the 175th and 176th line of code in train.py
- Change value
250
to30
in line 178 in train.py. - Change value
5e-3
to1e-4
in line 180 in train.py. - Set the 'seed' to
86
in line 20 in evaluate_model.py.
You will get the result at epoch 54.