tf.lite.experimental.QuantizationDebugger

View source on GitHub

Debugger for Quantized TensorFlow Lite debug mode models.

  tf 
 . 
 lite 
 . 
 experimental 
 . 
 QuantizationDebugger 
 ( 
 quant_debug_model_path 
 : 
 Optional 
 [ 
 str 
 ] 
 = 
 None 
 , 
 quant_debug_model_content 
 : 
 Optional 
 [ 
 bytes 
 ] 
 = 
 None 
 , 
 float_model_path 
 : 
 Optional 
 [ 
 str 
 ] 
 = 
 None 
 , 
 float_model_content 
 : 
 Optional 
 [ 
 bytes 
 ] 
 = 
 None 
 , 
 debug_dataset 
 : 
 Optional 
 [ 
 Callable 
 [[], 
 Iterable 
 [ 
 Sequence 
 [ 
 np 
 . 
 ndarray 
 ]]]] 
 = 
 None 
 , 
 debug_options 
 : 
 Optional 
 [ 
   tf 
 . 
 lite 
 . 
 experimental 
 . 
 QuantizationDebugOptions 
 
 
 ] 
 = 
 None 
 , 
 converter 
 : 
 Optional 
 [ 
 TFLiteConverter 
 ] 
 = 
 None 
 ) 
 -> 
 None 
 

Used in the notebooks

This can run the TensorFlow Lite converted models equipped with debug ops and collect debug information. This debugger calculates statistics from user-defined post-processing functions as well as default ones.

Methods

get_debug_quantized_model

View source

  get_debug_quantized_model 
 () 
 -> 
 bytes 
 

Returns an instrumented quantized model.

Convert the quantized model with the initialized converter and return bytes for model. The model will be instrumented with numeric verification operations and should only be used for debugging.

get_nondebug_quantized_model

View source

  get_nondebug_quantized_model 
 () 
 -> 
 bytes 
 

Returns a non-instrumented quantized model.

Convert the quantized model with the initialized converter and return bytes for nondebug model. The model will not be instrumented with numeric verification operations.

layer_statistics_dump

View source

  layer_statistics_dump 
 ( 
 file 
 : 
 IO 
 [ 
 str 
 ] 
 ) 
 -> 
 None 
 

Dumps layer statistics into file, in csv format.

run

View source

  run 
 () 
 -> 
 None 
 

Runs models and gets metrics.