ValueError: cannot reshape array of size 4554552 into shape (1024,512,3,3)

[AIGirl10]

Trying to convert custom model for License Plate

• Downloaded model from here: https://drive.google.com/file/d/1EUPtbtdF0bjRtNjGv436vDY28EN5DXDH/view?usp=sharing
• Saving model

  python save_model.py --weights ./data/custom.weights --output ./checkpoints/custom-416 --input_size 416 --model yolov4 

• But this command gives me following error

  Traceback (most recent call last):
  File "save_model.py", line 58, in <module>
   app.run(main)
  File "/home/user/.local/lib/python3.6/site-packages/absl/app.py", line 312, in run
   _run_main(main, args)
  File "/home/user/.local/lib/python3.6/site-packages/absl/app.py", line 258, in _run_main
   sys.exit(main(argv))
  File "save_model.py", line 54, in main
   save_tf()
  File "save_model.py", line 49, in save_tf
   utils.load_weights(model, FLAGS.weights, FLAGS.model, FLAGS.tiny)
  File "/home/user/Videos/newpro/number-plate/VT-LPR/tensorflow_yolov4_tflite/core/utils.py", line 63, in load_weights
   conv_weights = conv_weights.reshape(conv_shape).transpose([2, 3, 1, 0])  
  ValueError: cannot reshape array of size 4554552 into shape (1024,512,3,3)

@usama-x930

can you please help me out ?

[usama-x930]

There are few steps to follow:

1. First clone this repository.
2. Download weights from google drive link.
3. Put the single model weights in the "tensorflow_yolov4_tflite/data/" folder and also put "obj.names" file in the "tensorflow_yolov4_tflite/data/classes/" folder.
4. Edit "tensorflow_yolov4_tflite/core/config.py" file -->> Line 14 to -->> "./data/classes/obj.names"
5. Make sure to install all the required libraries as mentioned in requirements.txt

• opencv-python==4.1.1.26
• lxml
• tqdm
• tensorflow==2.3.0rc0
• absl-py
• easydict
• matplotlib
• pillow You can install using PIP Package. For example pip install easydict

6. Now run this command: python save_model.py --weights ./data/yolov4_custom_last.weights --output ./checkpoints/custom-416 --input_size 416 --model yolov4

You will find the converted model in: tensorflow_yolov4_tflite\checkpoints\custom-416 folder.

Hope your will problem be solve from this. Thanks