about the visual_encoder

[Dinosaurcubs]

Ncie work, congratulations! I got a question recently, it seems you removed the last ln_post layer before the projection layer in the visual_encoder， What is the reason for doing this?

[1125178969]

We will feed the visual features of CLIP to the multimodal encoder for feature fusion, so we think that the LN here is not necessary, but experiments show that with or without this LN has no effect on the results.

[Dinosaurcubs]

got it, thanks!