SpatioTemporalEntropyModel icon indicating copy to clipboard operation
SpatioTemporalEntropyModel copied to clipboard

Spatio-Temporal Entropy Model (STEM) for end-to-end leaned video compression.

Results 2 SpatioTemporalEntropyModel issues
Sort by recently updated
recently updated
newest added

When training and testing the spatio-temporal entropy model, is the I-frame training model using a pre-trained model? Another question, args.i_model_path I did not find, is as follows ![image](https://user-images.githubusercontent.com/31470730/189013709-7525e293-2e9b-400a-a480-217e396abb76.png)

大佬请问一下 一直没想明白为啥他的编码端会比解码端FLOPs低,感觉只有熵模型的话,编码端解码端计算量应该差不多吧 还有那个测编码端的FLOPs是,I帧网络的g_a部分 + 熵编码的compress部分,两部分计算量相加吗 ![1](https://user-images.githubusercontent.com/62051306/194994830-b99a072b-b75d-4461-b730-7f1b0ec3ee58.png) 感谢大佬分享,感激不尽orz