Thank you for sharing the awesome work on GitHub.
I want to train LSTR on my custom dataset for offline inference. So I modified the code:
|
long_start, long_end = max(0, work_start - self.long_memory_length), work_start - 1 |
and
|
long_start, long_end = max(0, work_start - self.long_memory_length), work_start - 1 |
to
long_start, long_end = max(0, visual_inputs.shape[0] - self.long_memory_length), visual_inputs.shape[0] - 1
I wonder if I did the right thing? Is there anything else I should change?
Thank you for sharing the awesome work on GitHub.
I want to train LSTR on my custom dataset for offline inference. So I modified the code:
long-short-term-transformer/src/rekognition_online_action_detection/datasets/perframe_data_layers.py
Line 79 in da956f6
long-short-term-transformer/src/rekognition_online_action_detection/datasets/perframe_data_layers.py
Line 182 in da956f6
long_start, long_end = max(0, visual_inputs.shape[0] - self.long_memory_length), visual_inputs.shape[0] - 1I wonder if I did the right thing? Is there anything else I should change?