TensorFlow-2.x-YOLOv3

TensorFlow-2.x-YOLOv3 copied to clipboard

Issue with following parameters in configs.py (TRAIN_SAVE_BEST_ONLY and TRAIN_SAVE_CHECKPOINT)

4

Hello Rokas, thank you a lot for your tutorial. I followed your tutorial step by step exactly but go this error although I have changed the values and paths like...

Marcelbgit

Do not work out trained weights in Ubuntu on Windows. Windows 10, Cuda 11.2, cudnn 8.1 rtx 3060

1

Hello, I really appreciate your work. Very cool course on neural networks. There was a small problem. I decided to transfer this project from Ubuntu 18.04 to Windows 10 with...

EVNN304

hello I installed all requirements correctly and tried the detection_demo.py script I had a problem while converting yolov3.weights to .pb model `Traceback (most recent call last): File "C:\Users\test\Downloads\Deep Learning\Apps\tensorflow-tensorRT\TensorFlow-2.x-YOLOv3-master\TensorFlow-2.x-YOLOv3-master\tools\Convert_to_pb.py", line...

shahla-ai

problems during inference when using converted tflite model

1

Hi there, I recently tried to convert your model to tf lite and run inference on it, but am experiencing some errors. I'm using the following code to convert the...

lukqw

Hi, I really appreciate your work! It is not totally clear for me if I create a new custom model then how can I use this as normal way (read...

illestothi

regularizer is not included in total loss

3

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 Conv2D. In my...

hgjung97

ciou_enclose_area

1

 left and up why not tf.minimum()？why mot computer minimum is compute enclose_area? left = tf.maximum(boxes1_coor[..., 0], boxes2_coor[..., 0]) up = tf.maximum(boxes1_coor[..., 1], boxes2_coor[..., 1])

lihualilee

I try to use batch inference with tensorRT. I modifile some path of original code. I hope the code below will help to everybody want to use batch inference with...

wadnaa

image_preprocess resizing

4

hi, I just stumbled upon the code of image_preprocess in yolov3/utils.py why is the image padded instead of resized (stretched) correctly? is this why the boxes work better in my...

lukqw

Hi, thanks for the tutorial. But i have a problem here Is it possible to run detect_realtime in detection_custom.py in google colab? Thanks

ihsanramdhani