-
### 问题确认 Search before asking
- [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
![image](https://user-images.githubusercontent.…
zmdcs updated
2 years ago
-
# Lines of code
https://github.com/code-423n4/2022-09-nouns-builder/blob/main/src/auction/Auction.sol#L192
# Vulnerability details
## Impact
The ```_settleAuction``` function in the ```Auction.so…
-
在自己数据集上训练,数据集训练集大小为2160张图片,设备为使用rtx3090,batch_size为每个gpu大小为4,预估时长一个epoch需要1天,训练的很慢是正常的吗?我使用coco数据集去测试了下,每个gpu的图片数量为1张时,训练一个epoch预估需要219天。。。,请问pp-yoloe训练时长很慢是什么原因呢
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
1 ppyoloe对于小目标(比如visdrone数据集)和密集型目标(比如crowdhum…
-
![1](https://user-images.githubusercontent.com/44281534/165916312-6e72c068-b64c-4fff-bbd5-556cd4fb3fd5.png)
![2](https://user-images.githubusercontent.com/44281534/165916325-f34ec751-47df-4412-8154-4…
-
`python deploy/python/infer.py --model_dir=D:\Yanglingyun\Github\model\ppyoloe_crn_m_300e_coco --image_file=D:\Yanglingyun\Github\datas\RGB\s08_e01\colorImg34.jpg --run_mode=trt_fp16 --device=gpu --ru…
-
目前的想法是通过paddle-serving部署。
paddle-serving部署时支持pipeline模式,可以通过定义op来进行多个模型的串联。
但是将模型转换为paddle-serving支持的模型时,目标检测与追踪的模型(pp-yoloe)输出包含两个结果,维度与关键点检测模型(HRNet)的输入并不匹配。并且最终需要通过stgcn来判断是否摔倒,而stgcn需要50帧图像才…
-
Context: we're not importing the API explorer via npm in some SPA, but directly load it from unpkg.com in a static page
So far this import looked like https://unpkg.com/openapi-explorer/dist/openap…
-
##### System information (version)
- OpenVINO => 2022.1
- Operating System / Platform => Windows 64 Bit
- Compiler => Visual Studio 2019
- Problem classification: Model Loading
- Framework: Paddl…
-
A configuration file so we don't have to go through and edit source code every time there's a new release.
Other extra optional things that will probably be a pain: since there's a file, it's proba…
aqilc updated
2 years ago