-
### 软件环境
```Markdown
- paddlepaddle:
- paddlepaddle-gpu: 2.6.1
- paddlenlp: 3.0.0b0.post20240725
```
### 重复问题
- [X] I have searched the existing issues
### 错误描述
```Markdown
PaddleNLP进行预训练时设置`-…
-
### System Info
- `transformers` version: 4.42.0
- Platform: Linux-5.15.0-105-generic-x86_64-with-glibc2.35
- Python version: 3.9.19
- Huggingface_hub version: 0.23.4
- Safetensors version: 0.4…
-
When I run this script with an updated base.yaml:
`python tools/train_experiment.py --config_file config/base.yaml --phase 'train'`
Here is the issue `/opt/conda/lib/python3.10/site-packages/tran…
-
Hello, can you tell me how can achieve the the accuracy of 94.5% on UCF101 using the Resnext101?
I use your code, the same network architecture(Resnext101) and your pretrained parameters(resnext-101-…
-
## Instructions To Reproduce the 🐛 Bug:
1. Full runnable code :
```
`#!/usr/bin/env python
# Copyright (c) Facebook, Inc. and its affiliates.
# this is an adaptation of detectron2/tools/deploy/ex…
-
## ❔Question
How i can use more and more augmentations related to Image Enhancements.
## Additional context
-
> PyTorch 是由 Facebook 开发，基于 **Torch** 开发，从并不常用的 Lua 语言转为 Python 语言开发的深度学习框架，Torch 是 TensorFlow 开源前非常出名的一个深度学习框架，而 PyTorch 在开源后由于其使用简单，动态计算图的特性得到非常多的关注，并且成为了 TensorFlow 的 最大竞争对手。目前其 Github 也有 2w8+ 关注。
…
-
Hi, Thanks for making such an amazing project.
I have trying to use it for my log files. I could parse log files to its equivalent csv files using Logparser by LogPAI, but I have no idea how to con…
-
Adapt sequence sampling throughout training so that we first train on "simpler sequences" and then on more and more "complexe" sequences. We discussed three different types of strategies depending on …
-
Hi, thank you Yuxin and team for making this amazing resource and for all of your support answering questions!!!
I'm running into an issue where I think I am either **not running inference properly…