EnigmaHong

Results 3 issues of EnigmaHong

我用vgg训练了四个方向的分类,4万的数据,效果不理想。请问文字方向识别数据集是怎么样?

你好,请问maskFacePoints如何计算得到,如果我想要贴个胡子,怎么得到这个,谢谢

accelerate launch --num_processes 8 --mixed_precision fp16 train_t2i_custom_v2.py --config=configs/custom.py I use the above command to train a picture style model, loss is always shock, grad_norm: nan (nan), the effect is not...