v0.4.0

aidge_quantization v0.4.0 Release Notes

We are delighted to announce the new version of aidge_quantzation !

Highlights

None.

Contributors

Since the previous release, the following people contributed to the project:

• @contributor_one
• @contributor_two

Thank you to all of them!

Deprecation

None.

Expired Deprecation

None.

New Features

None.

Improvements

None.

Bug fixes :fire::bug:

None.

Documentation

None.

Developpers

None.

aidge_quantization/unit_tests/test_ptq.py

@@ -17,7 +17,7 @@ from aidge_core import Log, Level
 NB_SAMPLES      = 1000               # max : 1000
 SAMPLE_SHAPE    = (1, 1, 28, 28)
 MODEL_NAME      = 'MiniResNet.onnx'  # 'ConvNet.onnx'
-ACCURACIES      = (95.4, 94.5)       # (97.9, 97.7)
+ACCURACIES      = (95.4, 94.4)       # (97.9, 97.7)
 NB_BITS         = 4
 
 # --------------------------------------------------------------
@@ -91,12 +91,13 @@ class test_ptq(unittest.TestCase):
 
         # quantize the model
 
+        
         aidge_quantization.quantize_network(
             self.model, 
             NB_BITS, 
             tensors, 
             clipping_mode=aidge_quantization.Clipping.MSE, 
-            apply_rounding=True, 
+            no_quantization=False,
             optimize_signs=True, 
             single_shift=False
         )