-
Thank you very much for your codebase. I have trained my own data with resnet50 successfully,but I when train it with mobilenet, the accuracy is very low.
python main.py ucf101 RGB --arch mobilen…
-
我的显示如下:
加载 ORB词典. This could take a while...
empty line at 1082073
数据库载入时间 Vocabulary loaded in 6.48s
fopen /home/ewenwan/ewenwan/project/ORB_SLAM2-src-flow--geom-sem-octo/Thirdparty/ncnn/mode…
-
Hello!
I'm wondering how to train a MobileNetV2 and fully quantize the tflite model. I know that I can do it in EdgeImpulse but I want to change the architecture a bit.
I'm using the tf2.3 versi…
-
-
I noted the table without ap for mobilenetv2,so,how about accuracy?
-
P172和P173的命令运行时存在问题,不确定是不是mmdetection库的更新导致的,下面提供我运行成功的版本:
- 模型下载
`mim download mmdet --config yolov3_mobilenetv2_8xb24-320-300e_coco --dest .`
- 模型运行
`python demo/image_demo.py demo/demo.jpg yolo…
-
I saw the paper [paper2021](https://mftp.mmcheng.net/Papers/21PAMI-PoolNet.pdf)
I see you used MobileNetV2 as backbone. Is there a pretrained model using MobileNetV2?
Also, in PoolNet-VGG16 w/ edge …
-
Describe Question:
when I use W16A16 quantization in main branch, I cann't get qdq_error and xmodel_err, because I found that qdq_error and xmodel_err are all empty. I eventually found that model.g…
-
Hi @dusty-nv ,
I tried to train a custom SSD w/ mibilenetV2 from this repo and then deploy on a jetson agx xavier through jetson-inference. However, it seems that there is an incompability between …
-
### MediaPipe Solution (you are using)
Model Maker
### Programming language
_No response_
### Are you willing to contribute it
No
### Describe the feature and the current behaviour/state
[Mobil…