dundun

谢谢回复，目前有看到基于ernie_gen和UNIMO-Text提供的预训练+微调框架，是利用这个吗

UNIMO-text的预训练模型目前好像没法下载了？ 报错： Traceback (most recent call last): File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/transformers/model_utils.py", line 237, in from_pretrained file_path, default_root) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/utils/downloader.py", line 168, in get_path_from_url fullpath = _download(url, root_dir, md5sum) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddlenlp/utils/downloader.py", line 205,...

你好，今晚测试了相同代码发现能下载了

我也是这个unimo中文模型，请问下能否不用fastertransformer的方式部署呢（https://github.com/PaddlePaddle/PaddleNLP/tree/develop/applications/text_summarization/unimo-text/deploy/paddle_inference） ， 环境是windows+CUDA11.6+cudnn8.4，直接用train里的预测速度太慢了

换成官方镜像了 cuda11.6 cuDNN8.4 cmake3.16 使用fastertransformer部署时报错： [ 6%] Performing build step for 'extern_fastertransformer' Scanning dependencies of target topk [ 2%] Building CUDA object fastertransformer/cuda/CMakeFiles/topk.dir/topk_kernels.cu.o In file included from /usr/local/cuda/include/thrust/system/cuda/config.h:33, from /usr/local/cuda/include/thrust/system/cuda/detail/execution_policy.h:35,...

感觉确实是版本问题不好改 我去aistudio看了眼环境是 cuda11.2 cmake3.24.2 重装下环境试试吧

@Faridasabry01 Hello, could you please help me check the question raised in https://github.com/miccunifi/ladi-vton/issues/11#issuecomment-2748490783, I am very confused why I keep generating paired images.(running with the flag --test_order unpaired.

I have the same problem, did you solve it?