-
#### 1. OS using Ubuntu 18.04
#### 2. OS Architecture e.g. x64
#### 3->8. Using docker pinto0309/openvino2tensorflow:lastest
#### 9. URL of the repository from which the transformed model was taken…
-
Hi, Thanks for your great works!
I have downloaded tensorflow lite Yolox [model](https://github.com/PINTO0309/PINTO_model_zoo/tree/main/132_YOLOX) converted by you. I also wrote code inference for te…
-
E:\PyProject\yolox>python tools/demo.py image --conf 0.25 --nms 0.45 --tsize 640 --save_result --device [gpu]
2021-08-02 11:08:40.983 | INFO | __main__:main:247 - Args: Namespace(camid=0, ckpt='.…
-
你好，我直接下载官方提供的yolox-nano模型跑demo程序，测试dog.jpg，发现输出结果稍微有点问题，多了一个目标。调用代码如下：
`python tools/demo.py image -n yolox-nano -c ./models/yolox_nano.pth.tar --path assets/dog.jpg --conf 0.3 --nms 0.65 --tsize 416…
-
When run openvino c++ demo, the following error accured:
'''
Cannot create Swish layer Mul_43 id:38
C:\j\workspace\private-ci\ie\build-windows-icc2018\b\repos\closed-dldt\inference-engine\src\infer…
-
Hi,
I am trying to train YOLOX-nano with my own dataset in COCO format.
So I just need to change:
self.data_dir = "datasets/my_coco_dataset"
self.train_ann = "instances_train.json"
self.val_ann =…
-
python tools/demo.py image --conf 0.25 --nms 0.45 --tsize 736 --save_result --device [gpu]
用的 yolox-nano模型，输入图像736，速度0.36秒左右，这速度不太可能啊，很慢很慢，这demo命令没错吧，用的是gpu。之前别的模型，cpu跑infer才50ms，这个是不是哪里出错了，太离谱了。
-
two parameters of self.depth and self.width is used to adjust the architecture of CSPdarknet53，if I use the yolox-l or yolox-x， how to set the value of self.depth and self.width ， I noticed that the…
-
2021-08-02 15:19:10 | INFO | yolox.core.trainer:193 - ---> start train epoch1
2021-08-02 15:19:14 | INFO | yolox.core.trainer:254 - epoch: 1/300, iter: 10/161, mem: 8760Mb, iter_time: 0.349s,…
-
`./yolox ../model_trt.engine -i ../../../../assets/dog.jpg
blob image
3ms
num of boxes before nms: 67359`