mct-nightly 2.3.0.20250212.515__py3-none-any.whl → 2.3.0.20250214.519__py3-none-any.whl

{mct_nightly-2.3.0.20250212.515.dist-info → mct_nightly-2.3.0.20250214.519.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mct-nightly
-Version: 2.3.0.20250212.515
+Version: 2.3.0.20250214.519
 Summary: A Model Compression Toolkit for neural networks
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
@@ -32,7 +32,7 @@ Dynamic: summary
 <div align="center" markdown="1">
 <p>
       <a href="https://sony.github.io/model_optimization/" target="_blank">
-        <img src="/docsrc/images/mctHeader1-cropped.svg" width="1000"></a>
+        <img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/mctHeader1-cropped.svg" width="1000"></a>
 </p>
   
 ______________________________________________________________________
@@ -98,7 +98,7 @@ For further details, please see [Supported features and algorithms](#high-level-
 <div align="center">
 <p align="center">
 
-<img src="/docsrc/images/mctDiagram_clean.svg" width="800">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/mctDiagram_clean.svg" width="800">
 </p>    
 </div>
 
@@ -179,16 +179,16 @@ Currently, MCT is being tested on various Python, Pytorch and TensorFlow version
 ## <div align="center">Results</div>
 
 <p align="center">
-<img src="/docsrc/images/Classification.png" width="200">
-<img src="/docsrc/images/SemSeg.png" width="200">
-<img src="/docsrc/images/PoseEst.png" width="200">
-<img src="/docsrc/images/ObjDet.png" width="200">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/Classification.png" width="200">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/SemSeg.png" width="200">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/PoseEst.png" width="200">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/ObjDet.png" width="200">
 
 MCT can quantize an existing 32-bit floating-point model to an 8-bit fixed-point (or less) model without compromising accuracy. 
 Below is a graph of [MobileNetV2](https://pytorch.org/vision/main/models/generated/torchvision.models.mobilenet_v2.html) accuracy on ImageNet vs average bit-width of weights (X-axis), using **single-precision** quantization, **mixed-precision** quantization, and mixed-precision quantization with GPTQ. 
 
 <p align="center">
-<img src="/docsrc/images/torch_mobilenetv2.png" width="800">
+<img src="https://github.com/sony/model_optimization/blob/main/docsrc/images/torch_mobilenetv2.png" width="800">
 
 For more results, please see [1]
 

{mct_nightly-2.3.0.20250212.515.dist-info → mct_nightly-2.3.0.20250214.519.dist-info}/RECORD

@@ -1,4 +1,4 @@
-model_compression_toolkit/__init__.py,sha256=fdQULWA3Jfq4DXBTLjZeTDAj4emfHV9r-YOcqsP6s4s,1557
+model_compression_toolkit/__init__.py,sha256=G7Jw23vCRFmgc4p4ecBtStYMdDk79Lf_gpYPEL7AxZE,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
@@ -523,8 +523,8 @@ 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-2.3.0.20250212.515.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
-mct_nightly-2.3.0.20250212.515.dist-info/METADATA,sha256=UH1-RbailayAjuK7F01Wtojtlinjt03YaMrEO2O--pY,26572
-mct_nightly-2.3.0.20250212.515.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-mct_nightly-2.3.0.20250212.515.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
-mct_nightly-2.3.0.20250212.515.dist-info/RECORD,,
+mct_nightly-2.3.0.20250214.519.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
+mct_nightly-2.3.0.20250214.519.dist-info/METADATA,sha256=EgRG9bv9An6_dmDl0LVHb7GwXCtLhF-NDHsPCODmeLU,26936
+mct_nightly-2.3.0.20250214.519.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+mct_nightly-2.3.0.20250214.519.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
+mct_nightly-2.3.0.20250214.519.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__ = "2.3.0.20250212.000515"
+__version__ = "2.3.0.20250214.000519"