mct-nightly 2.3.0.20250217.528__py3-none-any.whl → 2.3.0.20250218.513__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (6) hide show
  1. {mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/METADATA +3 -3
  2. {mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/RECORD +6 -6
  3. model_compression_toolkit/__init__.py +1 -1
  4. {mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/LICENSE.md +0 -0
  5. {mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/WHEEL +0 -0
  6. {mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/top_level.txt +0 -0
{mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: mct-nightly
3
- Version: 2.3.0.20250217.528
3
+ Version: 2.3.0.20250218.513
4
4
  Summary: A Model Compression Toolkit for neural networks
5
5
  Classifier: Programming Language :: Python :: 3
6
6
  Classifier: License :: OSI Approved :: Apache Software License
@@ -67,7 +67,7 @@ pip install model-compression-toolkit
67
67
  ```
68
68
  For installing the nightly version or installing from source, refer to the [installation guide](https://github.com/sony/model_optimization/blob/main/INSTALLATION.md).
69
69
 
70
- **Important note**: In order to use MCT, you’ll need to provide a floating point .pt or .keras model as an input.
70
+ **Important note**: In order to use MCT, you’ll need to provide a pre-trained floating point model (PyTorch/Keras) as an input.
71
71
 
72
72
  ### Tutorials and Examples
73
73
 
@@ -91,7 +91,7 @@ QAT (Quantization Aware Training) | High | High (~12-36 GPU hours) | [QAT API](
91
91
  For each flow, **Quantization core** utilizes various algorithms and hyper-parameters for optimal [hardware-aware](https://github.com/sony/model_optimization/blob/main/model_compression_toolkit/target_platform_capabilities/README.md) quantization results.
92
92
  For further details, please see [Supported features and algorithms](#high-level-features-and-techniques).
93
93
 
94
- **Required input**: Floating point model - 32bit model in either .pt or .keras format
94
+ **Required input**: Pre-trained floating point model (PyTorch/Keras)
95
95
 
96
96
  **Optional input**: Representative dataset - can be either provided by the user, or generated utilizing the [Data Generation](#data-generation-) capability
97
97
 
{mct_nightly-2.3.0.20250217.528.dist-info → mct_nightly-2.3.0.20250218.513.dist-info}/RECORD RENAMED
@@ -1,4 +1,4 @@
1
- model_compression_toolkit/__init__.py,sha256=y9CAIwpSai4w1Mnye2OVfPLLbprfxq_5TcerYrrNMsI,1557
1
+ model_compression_toolkit/__init__.py,sha256=L4EkNtR-te33w9SEvsB2NdnEnI240JVQctspC0VdZxc,1557
2
2
  model_compression_toolkit/constants.py,sha256=i_R6uXBfO1ph_X6DNJych2x59SUojfJbn7dNjs_mZnc,3846
3
3
  model_compression_toolkit/defaultdict.py,sha256=LSc-sbZYXENMCw3U9F4GiXuv67IKpdn0Qm7Fr11jy-4,2277
4
4
  model_compression_toolkit/logger.py,sha256=L3q7tn3Uht0i_7phnlOWMR2Te2zvzrt2HOz9vYEInts,4529
@@ -523,8 +523,8 @@ model_compression_toolkit/xquant/pytorch/model_analyzer.py,sha256=b93o800yVB3Z-i
523
523
  model_compression_toolkit/xquant/pytorch/pytorch_report_utils.py,sha256=UVN_S9ULHBEldBpShCOt8-soT8YTQ5oE362y96qF_FA,3950
524
524
  model_compression_toolkit/xquant/pytorch/similarity_functions.py,sha256=CERxq5K8rqaiE-DlwhZBTUd9x69dtYJlkHOPLB54vm8,2354
525
525
  model_compression_toolkit/xquant/pytorch/tensorboard_utils.py,sha256=mkoEktLFFHtEKzzFRn_jCnxjhJolK12TZ5AQeDHzUO8,9767
526
- mct_nightly-2.3.0.20250217.528.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
527
- mct_nightly-2.3.0.20250217.528.dist-info/METADATA,sha256=mw-eU4ot0q1seKBlaHN-SD_tnbQTYslBNFEds2u6C6w,26936
528
- mct_nightly-2.3.0.20250217.528.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
529
- mct_nightly-2.3.0.20250217.528.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
530
- mct_nightly-2.3.0.20250217.528.dist-info/RECORD,,
526
+ mct_nightly-2.3.0.20250218.513.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
527
+ mct_nightly-2.3.0.20250218.513.dist-info/METADATA,sha256=UqI_zzn8YEFqY_SRZgaZ5jbXjNqkVUDB_crtLj9j8RI,26933
528
+ mct_nightly-2.3.0.20250218.513.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
529
+ mct_nightly-2.3.0.20250218.513.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
530
+ mct_nightly-2.3.0.20250218.513.dist-info/RECORD,,
model_compression_toolkit/__init__.py CHANGED
@@ -27,4 +27,4 @@ from model_compression_toolkit import data_generation
27
27
  from model_compression_toolkit import pruning
28
28
  from model_compression_toolkit.trainable_infrastructure.keras.load_model import keras_load_quantized_model
29
29
 
30
- __version__ = "2.3.0.20250217.000528"
30
+ __version__ = "2.3.0.20250218.000513"