-
Hi,
I'm using this manual on 1 GPU V100:
`https://huggingface.co/docs/diffusers/main/en/training/dreambooth#performing-inference-using-a-saved-checkpoint`
using dog dataset and finetuning the…
unrue updated
11 months ago
-
**System information**.
TensorFlow version (you are using): 2.5
Are you willing to contribute it (Yes/No): Yes. As much as possible.
**Describe the feature and the current behavior/state**.
…
-
I'm trying to use a resnet50 backbone on an hpc cluster without network access, so downloaded it as shown in the [FAQs](https://sleap.ai/faq.html). However, I now get this error that some dimensions d…
-
Hi, I used this command after prepared dataset python bin/train.py -cn lama-fourier-celeba data.batch_size=10 but I got this below error. Why it's happen? How I can fix it? I'm using windows os.
@win…
-
### Issue Description
Image generation fails with the following trace:
```
00:54:57-794076 ERROR Exception: LoRAModule.forward() got an unexpected keyword argument 'scale' …
-
### Checklist
- [ ] I have searched related issues but cannot get the expected help.
- [ ] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) b…
-
自己用发票的数据训练了一个文本识别模型，训练集19000多张，测试集约5000张，使用的是Resnet34，训练了1000轮，acc在89%左右就上不去了。使用该模型测试时，总体效果还行，但是发现对于**框出来很标准的文本**，有时候会漏检某些字，例如“2020年12月04日”，就会把“日”漏掉，“有限公司”会识别成“有限司”等。请问一下**训练的时候需要调整什么参数**？或者在**部署的时候需要…
-
I am using huggingface model zoo to reproduce the standard image classification task based on Cifar10. However, I found the huggingface's implementations, although much faster, have much worse perform…
-
-
作者您好，想请教您我在阅读文章时的一个疑问：
文章中您提到backbone是ResNet-34，但是单个模块消融实验的baseline却是ResNet-32。请问这里的ResNet-32是如何实现的？
期待您的回复，非常感谢！