Feature Visualization
How neural networks build up their understanding of images

https://distill.pub/2017/feature-visualization/

#CNN #convolutional_neutral_network
#Visualization

#معرفی_ابزار #مصور_سازی #visualization

تنسور واچ(TensorWatch) ابزاری است که ماکروسافت برای مصورسازی معرفی کرده که شبیه به تنسوربورد است و این امکان را می‌دهد که visualization را به صورت real-time در خود جوپیتر نوت‌بوک انجام دهید.

TensorWatch is a debugging and visualization tool designed for deep learning and reinforcement learning from Microsoft Research. It works in Jupyter Notebook to show real-time visualizations of your machine learning training and perform several other key visualizations of your models and data.


https://github.com/microsoft/tensorwatch

کتابخانه tf.explain ابزاری است برای درک بهتر رفتار شبکه عصبی که امکان تحلیل گرادیان ها و ترسیم المان های مصور سازی نظیر heatmap ها را میدهد.
همچنین قابل ترکیب با tensorboard و قابل استفاده از طریق tf.keras API هم میباشد.

The library is adapted to the Tensorflow 2.0 workflow, using tf.keras API as possible. It provides:
- Heatmaps Visualizations & Gradients Analysis
- Both off-training and tf.keras.Callback Usages
- Tensorboard Integration

tf-explain respects the new TF2.0 API, and is primarily based on tf.keras when possible. It benefits from the @tf.function decorator which helps to keep support for both eager and graph mode. This allows keeping most algorithms computation time negligible compared to full training.

Algorithms implemented in tf-explain:
- Activations Visualizations
- Grad CAM
- Occlusion Sensitivity
- SmoothGrad

Documentation: https://tf-explain.readthedocs.io/en/latest/
Github: https://github.com/sicara/tf-explain

#visualization #tensorflow