mct-nightly 2.3.0.20250301.607__py3-none-any.whl → 2.3.0.20250303.547__py3-none-any.whl

{mct_nightly-2.3.0.20250301.607.dist-info → mct_nightly-2.3.0.20250303.547.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mct-nightly
-Version: 2.3.0.20250301.607
+Version: 2.3.0.20250303.547
 Summary: A Model Compression Toolkit for neural networks
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License

{mct_nightly-2.3.0.20250301.607.dist-info → mct_nightly-2.3.0.20250303.547.dist-info}/RECORD

@@ -1,4 +1,4 @@
-model_compression_toolkit/__init__.py,sha256=Azc5OjDMUTHIOfiySrkkU3g_S-Pz3L_Ir73nWN8Q1KU,1557
+model_compression_toolkit/__init__.py,sha256=XUmnCPJRShQlD16RUhAF8kEhlRn3s-VGaR8A6to87o4,1557
 model_compression_toolkit/constants.py,sha256=i_R6uXBfO1ph_X6DNJych2x59SUojfJbn7dNjs_mZnc,3846
 model_compression_toolkit/defaultdict.py,sha256=LSc-sbZYXENMCw3U9F4GiXuv67IKpdn0Qm7Fr11jy-4,2277
 model_compression_toolkit/logger.py,sha256=L3q7tn3Uht0i_7phnlOWMR2Te2zvzrt2HOz9vYEInts,4529
@@ -24,7 +24,7 @@ model_compression_toolkit/core/common/back2framework/__init__.py,sha256=cco4TmeI
 model_compression_toolkit/core/common/back2framework/base_model_builder.py,sha256=V1oShKzbSkdcTvREn8VnQQBzvm-tTHkWMXqMkYozF2s,2023
 model_compression_toolkit/core/common/collectors/__init__.py,sha256=sw7LOPN1bM82o3SkMaklyH0jw-TLGK0-fl2Wq73rffI,697
 model_compression_toolkit/core/common/collectors/base_collector.py,sha256=JoBTX3rRcRnUF3_Azjg848aiJt9drCJ5TsR9RahVI0Y,2591
-model_compression_toolkit/core/common/collectors/histogram_collector.py,sha256=UM44md-qYpes9zBdXam9YKxEhBlkumYhuDy3wy6vE6w,6735
+model_compression_toolkit/core/common/collectors/histogram_collector.py,sha256=zra5V06Brpjc1cUNIMVVGqdoqAuro62_hGy2Zm5-XMQ,6754
 model_compression_toolkit/core/common/collectors/mean_collector.py,sha256=mjr3U_z7vn8rrqpkHnfErUOflToIYl4ozBVzP2awqDQ,3414
 model_compression_toolkit/core/common/collectors/min_max_per_channel_collector.py,sha256=5oKsJEKdVmj4C7fKdHhmrFN5k4G2BaFETpmf_xKNs7s,5207
 model_compression_toolkit/core/common/collectors/statistics_collector.py,sha256=psijsQZefwjMDH8SU5E18n65HiGtQilPhKr1hhzZX-I,8268
@@ -524,8 +524,8 @@ model_compression_toolkit/xquant/pytorch/model_analyzer.py,sha256=b93o800yVB3Z-i
 model_compression_toolkit/xquant/pytorch/pytorch_report_utils.py,sha256=UVN_S9ULHBEldBpShCOt8-soT8YTQ5oE362y96qF_FA,3950
 model_compression_toolkit/xquant/pytorch/similarity_functions.py,sha256=CERxq5K8rqaiE-DlwhZBTUd9x69dtYJlkHOPLB54vm8,2354
 model_compression_toolkit/xquant/pytorch/tensorboard_utils.py,sha256=mkoEktLFFHtEKzzFRn_jCnxjhJolK12TZ5AQeDHzUO8,9767
-mct_nightly-2.3.0.20250301.607.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
-mct_nightly-2.3.0.20250301.607.dist-info/METADATA,sha256=DrcLEqs5Db87W-jQSA4u0jCni7x_L3qxH7rpQo78SuA,27079
-mct_nightly-2.3.0.20250301.607.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-mct_nightly-2.3.0.20250301.607.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
-mct_nightly-2.3.0.20250301.607.dist-info/RECORD,,
+mct_nightly-2.3.0.20250303.547.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
+mct_nightly-2.3.0.20250303.547.dist-info/METADATA,sha256=-St847XvmURdE0vGMxsGeW34Al2Hi1Zh8HzcPKn_5vo,27079
+mct_nightly-2.3.0.20250303.547.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mct_nightly-2.3.0.20250303.547.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
+mct_nightly-2.3.0.20250303.547.dist-info/RECORD,,

model_compression_toolkit/__init__.py

@@ -27,4 +27,4 @@ from model_compression_toolkit import data_generation
 from model_compression_toolkit import pruning
 from model_compression_toolkit.trainable_infrastructure.keras.load_model import keras_load_quantized_model
 
-__version__ = "2.3.0.20250301.000607"
+__version__ = "2.3.0.20250303.000547"

model_compression_toolkit/core/common/collectors/histogram_collector.py

@@ -78,7 +78,7 @@ class HistogramCollector(BaseCollector):
             merged_histogram_counts = None
             for histogram in self._histogram_per_iteration:  # Iterate all collected histograms and merge them
                 if merged_histogram_counts is None:  # First histogram to consider
-                    merged_histogram_counts = histogram[0].astype(np.float64)  # Convert to float64
+                    merged_histogram_counts = interpolate_histogram(merged_histogram_bins, histogram[1], histogram[0])
                 else:  # Merge rest of histograms into existing final histogram
                     merged_histogram_counts += interpolate_histogram(merged_histogram_bins, histogram[1], histogram[0])