Asad

@zhouxianming Using these $ python convert_weight.py $ python freeze_graph.py

@float123 Can you tell me please how we can convert the yolov3 TensorFlow model to TRT for acceleration?

> Did you wait for few epochs? I had nan on a test set for first few epochs (training on the XISRay dataset with default settings) and then it went...

@juanmanuelrq Have you resolved the issue? I have the same problem. all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.2686-nan.ckpt-1" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.2071-nan.ckpt-2" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.1809-nan.ckpt-3" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.1537-nan.ckpt-4" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.1885-nan.ckpt-5" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=6.1779-nan.ckpt-6" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=nan-nan.ckpt-7" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=nan-nan.ckpt-8" all_model_checkpoint_paths: "Pedestrian_yolov3_loss=nan-nan.ckpt-9" all_model_checkpoint_paths:...

@qncsn2016 Thank you so much.

Hi, I am training YOLOV3 with 1 class and dataset is about 7000 images. The training loss decrease for few iterations and then stop decreasing, test loss is always NAN....

@MrZhousf OK. Thank you so much. I'll give it a try.

@kerolos @sabrinatuli Try this solution, it will resolve the Train NAN issue, however for me, test loss is still NAN from start till end. but the model works fine when...

@Yufeng4024 Where did you save your these weights? just copy and place in the root directory of the model. also keep the same name in the config file.

@nourhanTr @richardgohth I wrote a python program to convert (yolo) .txt annotations to .xml annotations. You can use if you still need it. You can convert all files in a...