AlphaGit
commented
3 years ago @amerfathullah Hi! I think I might be able to look into this issue. Do you have a source file and the set of options that helps reproduce this issue?
Also, note that the "Interpolate 0 frames" is a giveaway that the current settings will not work. That means that between frame1 and frame2, 0 frames will be created. This means that your setting will not generate any new frames for you. Play around with the FPS settings.
DAIN Colab, v1.4.0
colab assigned GPU name, driver_version, memory.total [MiB] Tesla P100-PCIE-16GB, 418.67, 16280 MiB
Interpolation
/content/DAIN revise the unique id to a random numer 9776 Namespace(SAVED_MODEL=None, alpha=[0.0, 1.0], arg='./model_weights/9776-Thu-Sep-17-11-06/args.txt', batch_size=1, channels=3, ctx_lr_coe=1.0, datasetName='Vimeo_90K_interp', datasetPath='', dataset_split=97, debug=False, depth_lr_coe=0.001, dtype=<class 'torch.cuda.FloatTensor'>, end_frame=5682, epsilon=1e-06, factor=0.2, filter_lr_coe=1.0, filter_size=4, flow_lr_coe=0.01, force=False, frame_input_dir='/content/DAIN/input_frames', frame_output_dir='/content/DAIN/output_frames', log='./model_weights/9776-Thu-Sep-17-11-06/log.txt', lr=0.002, netName='DAIN_slowmotion', no_date=False, numEpoch=100, occ_lr_coe=1.0, patience=5, rectify_lr=0.001, save_path='./model_weights/9776-Thu-Sep-17-11-06', save_which=1, seed=1, start_frame=1, time_step=0.5051555555555556, uid=None, use_cuda=True, use_cudnn=1, weight_decay=0, workers=8) cudnn is used Interpolate 0 frames Traceback (most recent call last): File "colab_interpolate.py", line 112, in
y_s, offset, filter = model(torch.stack((X0, X1),dim = 0))
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/content/DAIN/networks/DAIN_slowmotion.py", line 202, in forward
return cur_outputs,cur_offset_output,cur_filter_output
UnboundLocalError: local variable 'cur_offset_output' referenced before assignment
please help me with this issue