zsf23

android studio 3.0.1 encounter error

6

@moli232777144 compile your mtcnn_AS project via android studio 3.0.1, encounter error as flollow: Error:error: linker command failed with exit code 1 (use -v to see invocation), how can I solvesit...

@truskovskiyk I use the superparameters as default to train model, it seems overfitting, the val_loss does not converge 

Release training codes?

2

the demo codes can generate amazing SR image, is there a plan to release training codes?

encounter error when run OnnxCoremlImport.ipynb

1

run code step by step as OnnxCoremlImport.ipynb , however, it gets error when execute cml = onnx_coreml.convert(model), the error shows that list index out of range in line 347 in...

how to run the release code?

4

@JuheonYi Thanks for sharing the codes, how to run the codes?

In the paper, Formula (7) is used to optimizer each level, I am puzzled why Formula (7) is not a component of training losses?

whether the method proposed in this paper supports explicit key-point to drive source image?

7

since implicity key-points are used in this paper, what I'm concerned about is that explicit key-point, for example 106 2D landmark, can be use to drive source image?