Settings of pre-trained models about arflow HOT 7 CLOSED

the model named with _ar means training with AR and with a basic pretrained model.
for example, pwclite_ar.tar is trained on Sintel training set with pwclite_raw.tar as the pretrained model(which is trained from scratch on raw videos and not used AR in the pre-training stage).

from arflow.

Thank you for the reply.

I tested Sintel's pwclite_ar.tar on the training set. The results look much worse than the numbers reported in Table 1 in the paper. If I understand correctly, pwclite_ar.tar is the one fine-tuned on the training set and should match the one used in Table 1. Did I miss something? Thank you.

from arflow.

Can you tell me what result did you get?
I run the command

python3 train.py -c configs/sintel_ft.json -m checkpoints/Sintel/pwclite_ar.tar -e

and get the results same as the paper

* Epoch 1 EPE_0: 2.79 EPE_1: 3.73

from arflow.

What I got are * Epoch 1 EPE_0: 4.20 EPE_1: 5.19.

I am using PyTorch 1.6.0. Not sure if this causes the difference.

from arflow.

Hi @playerkk,
I tested it in PyTorch 1.6 and found that the problem was caused by the default behavior of align_corners for grid_sample has changed to False since PyTorch 1.3.0.

Specify align_corners=True in utils/warp_utils.py and you will get the correct results.

from arflow.

After fixing the issue, I can reproduce the numbers. Thanks for the help.

from arflow.

I got these two numbers : 3.20 and 4.23 not the same as yours, when I tried to add align_corners=True I got this error
im1_recons = nn.functional.grid_sample(x, v_grid, mode=mode, padding_mode=pad,align_corners=True)
TypeError: grid_sample() got an unexpected keyword argument 'align_corners

from arflow.