conv_weights = conv_weights.reshape(conv_shape).transpose([2, 3, 1, 0]) ValueError: cannot reshape array of size 1645 into shape (64,64,1,1)

hunglc007 / tensorflow-yolov4-tflite

YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite

https://github.com/hunglc007/tensorflow-yolov4-tflite

MIT License

2.23k stars 1.24k forks source link

conv_weights = conv_weights.reshape(conv_shape).transpose([2, 3, 1, 0]) ValueError: cannot reshape array of size 1645 into shape (64,64,1,1) #322

Open Starkguava opened 3 years ago

Starkguava commented 3 years ago

I changed the INPUT_SIZE to 384. train.py: flags.DEFINE_string('weights', None, 'pretrained weights')

when i convert_tflite, It reports an error: conv_weights = conv_weights.reshape(conv_shape).transpose([2, 3, 1, 0]) ValueError: cannot reshape array of size 1645 into shape (64,64,1,1)

chairiq commented 3 years ago

Hi i have similar problem with my network. Is there any solution? I would like to note that i use grayscale images.