-
section5_1_pix2pixのPix2Pixクラスの定義の
Pix2Pix.train
のGのパラメータ更新部のコードの下記部分
### ### ### ### ### ### ### ### ### ### ### ### ### ### ###
# Generator
# 評価フェーズなので勾配は計算しない
# 識別器D…
-
Hi @xuebinqin, you've made an excellent work thank you! I'm pretty new to ML so I apologize for some stupid questions ahead.
1. What GPUs (and how many) you've used to train the last u2net (basic o…
-
Hi, I am training a face-retouching model using FFHQ and FFHQR datasets. Since I am training on 1024x1024 my batch size is 2. Here is the sample output
:
[rank0]: File "/opt/venv/lib/python3.10/site-packages/datasets/builder.py", line 1750, in _prepare_split_single
[rank0]: …
-
## ❓ Questions/Help/Support
Hi, support teams.
This is my first time asking a question.
I believe the following code will load the checkpoints.
==================================================…
-
The model name **instruct-pix2pix-00-22000.ckpt** looks like it was trained for 22 epochs. But when I trained the model, it was trained more than that. Just want to confirm how many epochs we shall tr…
-
hello!
When I tried to reproduce the results on the CelebAMaskHQ dataset, I got an error on command(python generate_counterfactuals.py --dataset_name celebamhq --checkpoints_dir path/to/checkpoint…
-
Hi, I can get good results with cyclegan in 'lsgan' mode on horse2zebra dataset, but when I change the gan mode to 'wgangp' and follow your codes:
self.loss_gp, gradients = cal_gradient_penalty()...
…
-
Hello. I am training CycleGAN with 2D data but the range is not from 0 to 255 like in image data. I saw in the code, the data is normalized by (data-127.5)/127.5 to be in between -1 and 1. The output …
-
### 🐛 Describe the bug
torchbench_amp_fp16_training
xpu train pytorch_CycleGAN_and_pix2pix
Traceback (most recent call last):
File "/home/sdp/actions-runner/_work/torch-xpu-ops/pytorch/benchmar…