Closed yangchris11 closed 7 months ago
Hi,
Once the inference stage becomes prolonged and all edges are removed, the training of SG(or TG) has failed. As described in the paper, the training process of both graphs is separated and independent. Spatial graph usually has fewer training data than Temporal graph, leading to potentially poor performance. You can add some data augmentation methods during the training of SG.
Thank you for the replies 🙇 closing the issue
Hi,
I also faced the same problem with Wildtrack dataset, where the training of SG has failed. Did you find a solution?
Thank you for your exciting work and the source code!
I tried reproducing the result from scratch using the same YML config to train the SG and TG separately on Wildtrack.
However, during the inference stage, it will become prolonged and produce unsatisfactory results as there are no edge predictions with a score> 0.9; therefore, all nodes will be retained after the SG predicting stage.
I tried to use the SG weights released by the author in this repository and the TG weights trained by myself and got the following results with gt detection, which is comparable :
Therefore I am curious if the training step or configuration of SG is different from TG? Thanks!