tflite_model.py

%cd /mydrive/customTF2/data/

'''**********************************
   FOR FLOATING-POINT INFERENCE
**********************************'''

import tensorflow as tf

saved_model_dir = '/mydrive/customTF2/data/tflite/saved_model'

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
tflite_model = converter.convert()
open("/mydrive/customTF2/data/tflite/detect.tflite", "wb").write(tflite_model)


'''**************************************************
  FOR FLOATING-POINT INFERENCE WITH OPTIMIZATIONS
***************************************************'''

# import tensorflow as tf
# converter = tf.lite.TFLiteConverter.from_saved_model('/mydrive/customTF2/data/tflite/saved_model',signature_keys=['serving_default'])
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# converter.experimental_new_converter = True
# converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS,  
#                                        tf.lite.OpsSet.SELECT_TF_OPS]
# tflite_model = converter.convert()

# with tf.io.gfile.GFile('/mydrive/customTF2/data/tflite/detect.tflite', 'wb') as f:
#   f.write(tflite_model)


'''**********************************
    FOR DYNAMIC RANGE QUANTIZATION 
*************************************
 The model is now a bit smaller with quantized weights, but other variable data is still in float format.'''

# import tensorflow as tf

# converter = tf.lite.TFLiteConverter.from_saved_model('/mydrive/customTF2/data/tflite/saved_model',signature_keys=['serving_default'])
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# tflite_quant_model = converter.convert()

# with tf.io.gfile.GFile('/mydrive/customTF2/data/tflite/detect.tflite', 'wb') as f:
#   f.write(tflite_quant_model)


# '''***********************************************************************
#    FOR INTEGER WITH FLOAT FALLBACK QUANTIZATION WITH DEFAULT OPTMIZATIONS 
# **************************************************************************
# Now all weights and variable data are quantized, and the model is significantly smaller compared to the original TensorFlow Lite model.
# However, to maintain compatibility with applications that traditionally use float model input and output tensors, 
# the TensorFlow Lite Converter leaves the model input and output tensors in float'''

# import tensorflow as tf
# import numpy as np

# saved_model_dir = '/mydrive/customTF2/data/tflite/saved_model'

# def representative_dataset():
#     for _ in range(100):
#       data = np.random.rand(1, 320, 320, 3)
#       yield [data.astype(np.float32)]

# converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# converter.representative_dataset = representative_dataset
# tflite_quant_model = converter.convert()

# with open('/mydrive/customTF2/data/tflite/detect.tflite', 'wb') as f:
#   f.write(tflite_quant_model)


# '''*********************************
#   FOR FULL INTEGER QUANTIZATION
# ************************************
# The internal quantization remains the same as previous float fallback quantization method, 
# but you can see the input and output tensors here are also now integer format'''

# import tensorflow as tf
# import numpy as np

# saved_model_dir = '/mydrive/customTF2/data/tflite/saved_model'

# def representative_dataset():
#     for _ in range(100):
#       data = np.random.rand(1, 320, 320, 3)
#       yield [data.astype(np.float32)]

# converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
# converter.optimizations = [tf.lite.Optimize.DEFAULT]
# converter.representative_dataset = representative_dataset
# converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
# converter.inference_input_type = tf.uint8  
# converter.inference_output_type = tf.uint8 
# tflite_quant_model_full_int = converter.convert()

# with open('/mydrive/customTF2/data/tflite/detect.tflite', 'wb') as f:
#   f.write(tflite_quant_model_full_int)