fuchao01 issues

Results 11 issues of


                                            fuchao01

Traceback (most recent call last): File "train.py", line 257, in train() File "train.py", line 117, in train base_weights = torch.load(args.save_folder + basenet) File "/usr/lib64/python2.7/site-packages/torch/serialization.py", line 265, in load f =...

多labels

你好，我看到有一个single label的例子，要是多labels如何使用

有人将这ckpt转化为pb

训练效果没有给出的模型好

你好，我按照训练步骤训练了一版，但是效果没有给出的模型那么好，很多误检，是我哪里写的不对吗？代码我也没有改动

Mirror文件中68个点的排列顺序

你好： Mirror文件中68个点的排列顺序，如果我想扩展到106个点应该如何构建Mirror文件？

how to apply in InceptionV3

TypeError: new_forward() got an unexpected keyword argument 'attention_mask'

**ENV:** torch 1.11.0+cu113 torchvision 0.12.0+cu113 diffusers 0.11.1 transformers 4.25.0 Traceback (most recent call last): File "src/diffuser_training.py", line 1252, in main(args) File "src/diffuser_training.py", line 1152, in main model_pred = unet(noisy_latents, timesteps,...

time consuming

![image](https://github.com/crowsonkb/k-diffusion/assets/3631804/f1b9d9d0-1d8b-4b72-8395-43d1b0fb03b5) In k-diffusion sampling https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py#LL56C1-L56C1, it takes 170ms

OOM

720p 16s,9:16,在A100 80G显存跑报OOM，这个尺寸需要多显卡推理吗？

fuchao01

关于训练

train error