Sequence_length meaning

[Harin99]

Hello, I'm implementing the training code of E-RAFT.
But there's a sequence_length variable in the paper and code, so what exactly does that mean?

If i set a sequence_length = 2, it seemed like 2 sequential data were being loaded on the code. ( like below )
e.g) [ 0, 1 ]

If so, by any chance,
Can i think of sequence_length as the number of applying warm_start at once?

For example, if i set the batch_size = 2 & sequence_length = 5, the sequence data will be loaded by 2 batches of 5 each like below.
1 batch : [0, 1, 2, 3, 4]
2 batch : [10, 11, 12, 13, 14]
In each batch, the first "flow_init" variable will be initialized to 0, then warm start will be applied.

Is it right way that i understood it now?

Thank you for your great work!!

[magehrig]

Hi @Harin99

Yes, sequence length greater than 1 implies that we use warm starting. Without checking the code, I think that a sequence length of N should load N+1 samples (e.g. [0,1,2,3,4,5] for N = 5). This is because we need at least two subsequent samples to infer optical flow with E-RAFT.

If you would like to reproduce the results, I suggest first getting the model to train without using the warm-starting loss (e.g. sequence length of 1). That should be much easier to implement, and you will already get very good results.