shudct
shudct
`/usr/bin/ffmpeg -y -loglevel warning -loop 1 -t 1.5 -i end.png -loop 1 -t 1.5 -i start.png -t 1.5 -i blank.wav -filter_complex gltransition=duration=1.3:offset=0.1:source=LinearBlur.glsl -ac 2 -ar 44100 -b:v 2M -r 24...
Thanks for sharing the excellent project. I wander if I can test images with batching directly or modify some files。Thanks again~
Hi all, 1. In train_val.prototxt, I notice that the input data such as label is 1 \* 5 \* 1 \* 1, the dim 5 means [batch_ind, x1, y1, x2,...
### Motivation Is there any plan to support DINO for pytorch2onnx? In another way, how can I convert DINO pytorch model to onnx? such as rewrite dino_head and so on....
  我使用最新的代码微调,使用的是下面的参数,但是warmup的学习率没有变化(我是每一个step都打印),数据使用的是moss 4w条+math 1w条,请问可能是什么原因呢
hi all, in the paper, the trained model is 5.4M on PASCAL VOC 2007 test. However, the link to the trained model from the author is 20M~. Does the network...
add preprocessing scripts for vggface and gender dataset edited by dct
### Your current environment ```text The output of `python collect_env.py` ``` Collecting environment information... PyTorch version: 2.3.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to...
安装后初始化报错
## Checklist: 1. 查找[历史相关issue](https://github.com/PaddlePaddle/PaddleX/issues)寻求解答 2. 翻阅[FAQ常见问题汇总和答疑](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/FAQ/FAQ.md) 3. 确认bug是否在新版本里还未修复 4. 翻阅[PaddleX 使用文档](https://github.com/PaddlePaddle/PaddleX/tree/develop#paddlex-%E4%BD%BF%E7%94%A8%E6%96%87%E6%A1%A3) ## 描述问题 ## 复现 1. 您是否已经正常运行我们提供的[教程](https://github.com/PaddlePaddle/PaddleX/tree/develop/tutorials)?没有 2. 您是否在教程的基础上修改代码内容?还请您提供运行的代码 3. 您使用的数据集是? 4. 请提供您出现的报错信息及相关log ## 环境 1. 请提供您使用的PaddlePaddle和PaddleX的版本号 paddlepaddle-gpu 3.0.0b1 paddlex...