tdsuper

@connectedhealthcaremy I tried to compile the code on a virtual machine and I didn't find the dependence on vcglibrary. I think some code written by @fyu are missed.

Hi, the model I tried to convert is from the checkpoints of [SingleHDR](https://github.com/alex04072000/SingleHDR), which calls `tf.image.sobel_edges`. From the source of tensorflow, I found the implementation of `tf.image.sobel_edges` contains `depthwise_conv2d` operation.

> It seems that some pixels are misaligned between the warped image and the target image. Is it a reasonable result? Can I do something to improve the fitting process?...

> I have. You can leave your email and I'll send it to you. Could you please send me one copy of the dataset? My email is [email protected]. Thanks!

Hi @paschalidoud , thanks for the quick reply. The environment is python 3.9.7, simple-3dviz 0.5.0, moderngl 5.6.4 and macOS Big Sur 11.6.1. I have found that the same question was...

Could you please provide more information, such as the output or the screen shot of your running?

@zwl995 You can first check whether the images are read successfully, i.e. whether [img1](https://github.com/tdsuper/SPHORB/blob/master/example2.cpp#L37) and [img2](https://github.com/tdsuper/SPHORB/blob/master/example2.cpp#L38) are empty matrices.