Closed Winnie202 closed 1 year ago
You may also need to modify the positional encoding part, otherwise it will not work.
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
https://github.com/llmpass/RSTT/blob/b10988958137cc9fa8a2b814f0f94c4900d736fc/models/layers.py#L163
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
https://github.com/llmpass/RSTT/blob/b10988958137cc9fa8a2b814f0f94c4900d736fc/models/layers.py#L163
Excuse me, don't i need to modify the output sequence length at the following code section? Because num_out_frames is defined here,I'm confused about this,because I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
https://github.com/llmpass/RSTT/blob/b10988958137cc9fa8a2b814f0f94c4900d736fc/models/layers.py#L163
Excuse me, don't i need to modify the output sequence length at the following code section? Because num_out_frames is defined here,I'm confused about this,because I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames
yes.
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
https://github.com/llmpass/RSTT/blob/b10988958137cc9fa8a2b814f0f94c4900d736fc/models/layers.py#L163
Excuse me, don't i need to modify the output sequence length at the following code section? Because num_out_frames is defined here,I'm confused about this,because I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames
yes.
if I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames,does the following code section need change
You may also need to modify the positional encoding part, otherwise it will not work.
Excuse me, which parts of the code are modified
https://github.com/llmpass/RSTT/blob/b10988958137cc9fa8a2b814f0f94c4900d736fc/models/layers.py#L163
Excuse me, don't i need to modify the output sequence length at the following code section? Because num_out_frames is defined here,I'm confused about this,because I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames
yes.
if I don't need to change the size of the output feature map, I just need to modify it num_out_frames same as num_input_frames,does the following code section need change
You are right.
I trained my own dataset, but the effect of interpolation is not good. If I do not want to interpolation frames, that is, input frame=4,output frame=4, how should I modify it? can i modify the output_frame in the weight of completed training?