MagicSource
MagicSource
hi, where is pretrained model
Hi, how to change the background to black, it seems white by default

``` Traceback (most recent call last): File "demo.py", line 268, in image, ex, color_mask) File "/t/extremnet/utils/visualize.py", line 41, in vis_octagon img = vis_mask(img, mask, col) File "/t/extremnet/utils/visualize.py", line 22, in...
I think the code has some error: ``` def prefetch_data(db, queue, sample_data, data_aug, debug=False): ind = 0 print("start prefetching data...") np.random.seed(os.getpid()) while True: try: data, ind = sample_data(db, ind, data_aug=data_aug,...
readme里面的网页demo有开源吗
Does there any voice sample inferenced?
Does it easy to upgrade or make a branch a new architecture?
Does it support bigger input size such as 512?