ssinha89

> Sorry I have not test the code. The face_tracker is another file. I will update this later today. I am preparing the 3D animation part. That part is large...

@lelechen63 Thanks for updating the 3d animation data preparation code. It would also be great if you could share the details of the expression generation from audio as mentioned here....

> @lelechen63 `TypeError: __init__() got an unexpected keyword argument 'camera_up'`, `camera_up` parametrer unnecessary? I got the same error. On removing that argument, I got the error File "/usr/local/lib/python3.7/dist-packages/soft_renderer-1.0.0-py3.7-linux-x86_64.egg/soft_renderer/transform.py", line 65,...

@lelechen63 The vgnet is trained using ground-truth 2d landmarks which are procrustes aligned and normalized to the range -0.2 to 0.2. I have seen that _lrw_data.py_ includes _lrw_gt_prepare(),_ which in...

> The demo script test_demo.sh includes function calls to test_demo_ani.py and test_demo_finetune.py. It seems the test_demo_finetune.py finetunes the pre-trained model on the test video frames, while the test_demo_ani.py simply evaluates...

I have done the preprocessing (landmark -0.2 to 0.2 then multiplied by 5), using pytorch 0.4 and using the same combination of loss functions as in vgnet.py. After a few...

I am still facing this issue of GAN convergence while training VGNET with ground truth 2D landmarks(scaled) and face images(cropped and warped). The generator GAN loss keeps increasing during the...

Thanks for the suggestion. I trained the network with only the L1 loss on GRID dataset. As you said the results are reasonably good, however there is blur in the...