Qing

layoutlmv3-base-chinese use XLMRobertaTokenizer as tokenizer, add `"tokenizer_class": "XLMRobertaTokenizer"` in https://huggingface.co/microsoft/layoutlmv3-base-chinese/blob/main/config.json works for me.

> > layoutlmv3-base-chinese 使用 XLMRobertaTokenizer 作为标记器，添加[https://huggingface.co/microsoft/layoutlmv3-base-chinese/blob/main/config.json`"tokenizer_class](https://huggingface.co/microsoft/layoutlmv3-base-chinese/blob/main/config.json%60%22tokenizer_class)": "XLMRobertaTokenizer"`对我有用。 > > what is your transformers version? transformers newest not work. 4.5.1

我在 icdar15 + MLT2017 上训练(sgd)，75个 epoch 以后，acc 还是不高： ``` (441/576) Batch: 2.059s | TOTAL: 15min | ETA: 5min | Loss: 0.2540 | Acc_t: 0.8872 | IOU_t: 0.8223 | IOU_k: 0.8405...

@ofexe 在 icdar15 的训练集上跑 600 个 epoch，scale=4 时 hmean=0.77，scale=1 时 hmean=0.79

@Wangweilai1 加载 ImageNet 的预训练权重，只是用 ic15，用 adam 训的

> No dood, its already in there , you just need weights but theres no GUI for it You can try [Lama Cleaner](https://github.com/Sanster/lama-cleaner), it integrates multiple inpainting models, including LDM....

Add Stable Diffusion 1.4 Inpainting in [Lama Cleaner](https://github.com/Sanster/lama-cleaner). It's based on the awesome [diffusers library](https://github.com/huggingface/diffusers).  |Original Image | Inpainted | | --------------| ----------| |||

There are two versions of stable-diffusion weights: 1. huggingface version：[https://huggingface.co/CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) 2. CompVis version：[https://huggingface.co/CompVis/stable-diffusion-v-1-4-original](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) If you have downloaded the **huggingface version**, just copy to `~/.cache/huggingface/diffusers/models--CompVis--stable-diffusion-v1-4`([diffusers's](https://github.com/huggingface/diffusers) default cache folder) If you have...

What version of firefox are you using? I tested 105.0.3 on macOS, it works fine. Can you help to see what error is reported in the console?

Hi, I can't reproduce the problem - What is your python version and pip version? - What operating system is used?