CheungBH

About webcam_blender.sh

2

Hi. I am trying to use your prediction to control the animator in blender. However, I met a problem when I am running "webcam_blender.sh" The "webcam.sh" demo can be run...

Keep ratio in ncnn android demo?

4

Hello. I noticed that you use padding(keep ratio) in training and demo code(python). But in the ncnn android code, there is no padding. Why is it? Won't the performance be...

你好，我想问一下， MobileNetSSD_deploy.id.h这个文件是哪里来的啊？自己写的还是ncnn源码编译出来的？我在ncnn的那个PC端demo中没看到这个文件 然后cpp/Mobilenetssd/include里面的文件是怎么得到的我也不太清楚，希望解答一下～谢谢

Other characters

5

Hello. Would your program support run with other characters? And are there any references about building other characters?

Loading pretrain model

1

Hi. I am trying to load your provided pre-trained models "resnet50-19c8e357.pth" and "pose_resnet_4.5_pixels_human36m.pth" to test, but I failed. 2021-07-08 10:47:24,038 checkpointer INFO: Loading checkpoint from datasets/resnet50-19c8e357.pth Traceback (most recent call...

meta-sim with object detection and object segmentation

2

Hello. Will the code with tasks object detection and object segmentation be release?

Accuracy keeps dropping

2

Hi. Thanks for your work. I am using your cl_training code. However, I found the train and test accuracy keeps dropping after training for 600 epochs. Is it normal? ![Uploading...

Error when deploying nanodet

5

Hello. I trained a nanodet model from https://github.com/RangiLyu/nanodet, and an error occurred to me when processing _auto status = NanoDet::instance->GetCommandQueue(&command_queue);_ : 2021-10-03 22:27:42.800142+0800 TNNDemo[7059:1059735] new NanoDet E/tnn: virtual tnn::Status tnn::DefaultNetwork::InitLayers(tnn::NetStructure...

I met "CUDA OUT OF MEMORY" error even when setting batch size=1. How many sizes of GRAM do you use when training?

你好，我在对yolov3进行剪枝的时候，发现我剪枝的比例和最后实际比例没对上。例如说我设置了阈值为0.6，但同一个模型中，shortcut pruning最后剪枝比例是0.498，slim pruning的剪枝比例是0.748。请问这个正常吗