weida wang

@CMsmartvoice My tensorflow version is 2.6, and tensorflowTTS version is 1.8. @zoezhu Yes, this is a workaround, but this method is a little indirect and not been pointed out in...

@ireneb612 I didn't change any path of any file or any folder, i first run `pip uninstall tensorflowTTS`, then try zoezhu's method `python setup.py install`, but unfortunately it gave me...

@CMsmartvoice I have applied the access permission of online colab notebook, could you please approve it ?

@CMsmartvoice Yes, I can access the colab notebook now, thank you !

I opened a related [issue](https://github.com/facebookresearch/pytorch3d/issues/1261) about supporting loading obj with vertex color. But in my case, the vertex color range is [0,255], here is [0,1]. If someone contribute this feature,...

Haha, this might be just a coincidence ~ facecolor.mat is a matlab file, it stores the color of 35709 vertices, a face has 35709 vertices. The reason why i use...

In [SORT paper](https://arxiv.org/pdf/1602.00763.pdf), it says these 7 states are :  @nihalsangeeth, I think the reason is not naively to reduce complexity, but the reality is that ratio of an...

@Royzon Have successfully deployed FRDA in android device, i am curious about its speed

@sushreebarsa You should first git clone repo, then change the `MODEL_DIR` :  I try it myself, got the same error

我的解决办法是在析构函数里调用ncnn::UnlockedPoolAllocator 和 ncnn::PoolAllocator的clear()