Home
last modified time | relevance | path

Searched refs:mlir_quantize (Results 1 – 8 of 8) sorted by relevance

/external/tensorflow/tensorflow/lite/tools/optimize/debugging/
DREADME.md39 # for mlir_quantize
47 # calling convert() only, calibrate model first and call `mlir_quantize` to run
52 return convert.mlir_quantize(calibrated, enable_numeric_verify=True)
/external/tensorflow/tensorflow/lite/g3doc/performance/
Dquantization_debugger.ipynb744 "### Using (internal) mlir_quantize API to access in-depth features\n",
747 "`TFLiteConverter._experimental_calibrate_only` and `converter.mlir_quantize` are\n",
776 "`convert.mlir_quantize` while generating the debug model manually."
803 "quantized_model = convert.mlir_quantize(\n",
820 "You can directly call `convert.mlir_quantize` to get the selective quantized\n",
834 "selective_quantized_model = convert.mlir_quantize(\n",
/external/tensorflow/tensorflow/lite/tools/optimize/debugging/python/
Ddebugger.py239 return convert.mlir_quantize(
292 self.quant_model = convert.mlir_quantize(
Ddebugger_test.py92 return convert.mlir_quantize(
/external/tensorflow/tensorflow/lite/python/
Dconvert.py199 def mlir_quantize(input_data_str, function
Dlite_v2_test.py41 from tensorflow.lite.python.convert import mlir_quantize
523 quantized_tflite_model = mlir_quantize(
1095 quantized_tflite_model = mlir_quantize(
1132 debug_mode_tflite = mlir_quantize(
Dlite_test.py32 from tensorflow.lite.python.convert import mlir_quantize
1316 quantized_tflite_model = mlir_quantize(
Dlite.py39 from tensorflow.lite.python.convert import mlir_quantize as _mlir_quantize