20.09.2024, 18:56
I will change the text as following, I hope that is more clear.
The only exception is for DeepExEncMode = 0 that has no memory limitation.
Please assign a value to max_memory_frame.
I released the new RC8.
Now in the case max_memory_frames == 0, the value is automatically assigned with the values suggested depending on the total GPU memory.
Dan
Quote:DeepExMaxMemFrames: Parameter used by ColorMNet model, specify the max number of encoded frames to keep in memory.If you know a way to get in python the amount of GPU memory I can try to set DeepExMaxMemFrames when is = 0, but for the moment it need to be always > 0.
Its value depend on encode mode and must defined manually following the suggested values.
encode_mode=0, represent the batch size, suggested value are:
6 or 8 : for 8GB GPU
12 or 14 : for 12GB GPU
24 or 28: for 24GB GPU
must be > 0
encode_mode=1, suggested values are:
4 or 5 : for 8GB GPU
8 or 9 : for 12GB GPU
15 or 16: for 24GB GPU
must be > 0
encode_mode=2, there is no limit to this value, it can be set = 0 (all the frames in the clip)
The only exception is for DeepExEncMode = 0 that has no memory limitation.
Please assign a value to max_memory_frame.
I released the new RC8.
Now in the case max_memory_frames == 0, the value is automatically assigned with the values suggested depending on the total GPU memory.
Dan