saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-25 19:48:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix bugs for 1: Calibrator should check model inputs; 2: (#6017)

Browse source 
quantize_inupts forgot to use parameter initializer_use_weight_qtyp.
This commit is contained in:
Zhang Lei 2020-12-03 00:00:16 -08:00 committed by GitHub
parent bdd06f6310
commit 648c9c7789
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
onnxruntime/python/tools/quantization/calibrate.py
View file

@ -58,6 +58,7 @@ class ONNXCalibrater:
model = onnx.shape_inference.infer_shapes(model)
value_infos = {vi.name: vi for vi in model.graph.value_info}
value_infos.update({ot.name: ot for ot in model.graph.output})
value_infos.update({it.name: it for it in model.graph.input})
added_nodes = []
added_outputs = []
@ -264,4 +265,4 @@ def calibrate(model_path,
quantization_params_dict = calibrater.calculate_quantization_params(dict_for_quantization)
print("Calibrated,quantized parameters calculated and returned.")
return quantization_params_dict
return quantization_params_dict

2
onnxruntime/python/tools/quantization/onnx_quantizer.py
View file

@ -806,7 +806,7 @@ class ONNXQuantizer:
# Quantize the input
initializer = find_by_name(node_input, self.model.initializer())
if initializer is not None:
weight = self._get_quantized_weight(initializer, self.weight_qType)
weight = self._get_quantized_weight(initializer, self.weight_qType if initializer_use_weight_qType else self.input_qType)
# Update graph
self._update_weight(weight)