rememberBr

Crash while adjusting mask shape

3

### Provide environment information python=3.9.1 labelme = I tested both 5.2.1 and 5.3.1 with this issue ### What OS are you using? win10 ### Describe the Bug I encountered an...

关于训练遇到的问题

6

您好，我在尝试使用您的代码进行训练时发现，虽然论文以及github的readme里都是使用的SIRST数据集，但是在train_alcnet.py中数据集设置里默认值却是DENTIST和Iceberg，contrast.py里有对数据预处理的代码，也是针对这两个数据集的，我尝试自己修改但是遇到了其他的问题。 train_alcnet.py的参数设置里，选择的是PCMNet，但是只提供了MPCMResNetFPN和ResNetFCN的初始化代码，我尝试直接修改net_choice=‘MPCMResNetFPN’以及从model中导入PCMNet，但是代码都卡在了model.initialize(init=init.MSRAPrelu(), ctx=args.ctx, force_reinit=True)，请问该怎么办呢，能不能整理一份可执行的代码，非常感谢

Pruning based on self built datasets

1

Hello, may I ask if it is possible to add a pruning method on a self built dataset? Currently, the dataset can only select ['VOC ',' COCO ']

[Bug]: IR Models with dynamic dimensions continuously increase memory during inference

5

### OpenVINO Version 2023.2，2022.1，2023.3，2024.0 ### Operating System Windows System ### Device used for inference CPU ### Framework None ### Model used _No response_ ### Issue description I have an ONNX...

[Bug]: Accuracy issue on various CPU platforms with MobileNetV3-Large and ShuffleNetV2-x0.5

14

### OpenVINO Version 2024.0 2024.1，2024.2 ### Operating System Windows System ### Device used for inference CPU ### Framework None ### Model used mobilenetV3，shuffleNetV2 ### Issue description After the model was...

### Describe the issue [debug.zip](https://github.com/user-attachments/files/17427171/debug.zip) When I use gtest for unit testing and want to perform a separate test, I use: testing:: GTEST_LAG (filter). When using the release version of...

我修改infer.cu代码使项目可以适配TensorRT V10

2

我修改infer.cu代码使项目可以适配TensorRT V10 ``` #include #include #include #include #include #include #include #include "infer.hpp" namespace trt { using namespace std; using namespace nvinfer1; #define checkRuntime(call) \ do { \ auto ___call__ret_code__ =...

repvit-sam train self built datasets and an error

2

I have two questions: 1. Will repvit-sam provide a pipeline for training self built datasets? Make it only segment the categories we need, not anything else 2. I used tim=0.9.12...

Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion,...