mct-nightly 1.8.0.8032023.post421__py3-none-any.whl → 1.8.0.8052023.post414__py3-none-any.whl

{mct_nightly-1.8.0.8032023.post421.dist-info → mct_nightly-1.8.0.8052023.post414.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mct-nightly
-Version: 1.8.0.8032023.post421
+Version: 1.8.0.8052023.post414
 Summary: A Model Compression Toolkit for neural networks
 Home-page: UNKNOWN
 License: UNKNOWN
@@ -49,8 +49,8 @@ MCT is developed by researchers and engineers working at Sony Semiconductor Isra
 ## Supported Features
 
 MCT supports different quantization methods:
-* Post training quantization (PTQ): [Keras API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/keras_post_training_quantization_experimental.html#ug-keras-post-training-quantization-experimental), [PyTorch API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/pytorch_post_training_quantization_experimental.html#ug-pytorch-post-training-quantization-experimental)
-* Gradient-based post training quantization (GPTQ): [Keras API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/keras_gradient_post_training_quantization_experimental.html#ug-keras-gradient-post-training-quantization-experimental), [PyTorch API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/pytorch_gradient_post_training_quantization_experimental.html#ug-pytorch-gradient-post-training-quantization-experimental)
+* Post-training quantization (PTQ): [Keras API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/keras_post_training_quantization_experimental.html#ug-keras-post-training-quantization-experimental), [PyTorch API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/pytorch_post_training_quantization_experimental.html#ug-pytorch-post-training-quantization-experimental)
+* Gradient-based post-training quantization (GPTQ): [Keras API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/keras_gradient_post_training_quantization_experimental.html#ug-keras-gradient-post-training-quantization-experimental), [PyTorch API](https://sony.github.io/model_optimization/docs/api/experimental_api_docs/methods/pytorch_gradient_post_training_quantization_experimental.html#ug-pytorch-gradient-post-training-quantization-experimental)
 * Quantization aware training (QAT)[*](#experimental-features)
 
 
@@ -66,15 +66,16 @@ In addition, MCT supports different quantization schemes for quantizing weights
 * Symmetric
 * Uniform
 
-Core features:
+Main features:
 * <ins>Graph optimizations:</ins> Transforming the model to an equivalent (yet, more efficient) model (for example, batch-normalization layer folding to its preceding linear layer).
-* <ins>Quantization parameter search:</ins> Different methods can be used to minimize the expected added quantization-noise during thresholds search (by default, we use Mean-Square-Errorm but other metrics can be used such as No-Clipping, Mean-Average-Error, and more).
+* <ins>Quantization parameter search:</ins> Different methods can be used to minimize the expected added quantization-noise during thresholds search (by default, we use Mean-Square-Error, but other metrics can be used such as No-Clipping, Mean-Average-Error, and more).
 * <ins>Advanced quantization algorithms:</ins> To prevent a performance degradation some algorithms are applied such as: 
   * <ins>Shift negative correction:</ins> Symmetric activation quantization can hurt the model's performance when some layers output both negative and positive activations, but their range is asymmetric. For more details please visit [1].
   * <ins>Outliers filtering:</ins> Computing z-score for activation statistics to detect and remove outliers.
 * <ins>Clustering:</ins> Using non-uniform quantization grid to quantize the weights and activations to match their distributions.[*](#experimental-features)
 * <ins>Mixed-precision search:</ins> Assigning quantization bit-width per layer (for weights/activations), based on the layer's sensitivity to different bit-widths.
 * <ins>Visualization:</ins> You can use TensorBoard to observe useful information for troubleshooting the quantized model's performance (for example, the model in different phases of the quantization, collected statistics, similarity between layers of the float and quantized model and bit-width configuration for mixed-precision quantization). For more details, please read the [visualization documentation](https://sony.github.io/model_optimization/docs/guidelines/visualization.html).   
+* <ins>Target Platform Capabilities:</ins> The Target Platform Capabilities (TPC) describes the target platform (an edge device with dedicated hardware). For more details, please read the [TPC README](model_compression_toolkit/target_platform_capabilities/README.md).   
 
 
 #### Experimental features 
@@ -107,15 +108,15 @@ A nightly package is also available (unstable):
 pip install mct-nightly
 ```
 
-### Requierments
+### Requirements
 
-To run MCT, one of the supported frameworks, Tenosflow/Pytorch, needs to be installed.
+To run MCT, one of the supported frameworks, Tensorflow/Pytorch, needs to be installed.
 
-For using with Tensorflow please install the packages: 
+For use with Tensorflow please install the packages: 
 [tensorflow](https://www.tensorflow.org/install), 
 [tensorflow-model-optimization](https://www.tensorflow.org/model_optimization/guide/install)
 
-For using with PyTorch please install the packages: 
+For use with PyTorch please install the packages: 
 [torch](https://pytorch.org/)
 
 Also, a [requirements](requirements.txt) file can be used to set up your environment.