-
Hi,
I tried to export the yolov7 weights to tensorflow model. I could not do it with the current implementation of "export.py".
Any help in how to do it ?
Thank you in advance
-
哥，在s版本的时候，train.py在运行的时候总是在第4个epoch突然中断，
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [8400,5] vs. [0,5]
[[{{node model_1/yolo_loss/while/body/_1/model_1/yol…
-
### Describe the issue
I have generated an onnx model from the yolo_nas_pose nano model which can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/notebooks/YoloNAS_Pose_Fine_Tu…
-
I want to train the Yolov3 network instead of the tiny Yolov3 network. With tiny I can train but when I switch to yolov3 I have a memory problem.
My network contains about 1000 photos
# YOLO opti…
-
Hi,
I trained new YOLOv3-tiny weights on my own PC and everything worked.
Now I copied these files
- yolov3_custom_Tiny.data-00000-of-00001
- yolov3_custom_Tiny.index
and pasted them on a…
-
I would like to increase the number of anchors from 9 to 18 for training, since I read this can improve accuracy (I am not concerned about model runtime, and it is very important for the box to fit ti…
-
The current train loop calculates the total loss as below:
total_loss = giou_loss + conf_loss + prob_loss
This implementation doesn't include regularizer's loss, such as kernel_regularizer of Conv…
-
https://github.com/hizhangp/yolo_tensorflow/blob/88aba9d5569c04170f294a093455390a90f2686e/yolo/yolo_net.py#L178
predict_boxes_tran = tf.stack(
[(predict_boxes[..., 0] + offset) / s…
-
For Tensorflow 1.0.*/1.1.0 is coding by using Python 2.7, I think that it is the best choice that the yolo-tf use python2.7 instead of python 3 in order to speed up? Is it right?
-
Hello everyone,
When I convert my yolo v4 model to tflite int8 or float 16, I have no problem.
However, I have the following error when trying to convert to full_int8:
Traceback (most recent…