Metadata-Version: 2.1
Name: timm_vis
Version: 1.0.0
Summary: Visualizer for PyTorch image models
Home-page: https://github.com/novice03/timm-vis
Author: Pranav Pulijala
License: UNKNOWN
Description: ## PyTorch Image Models Visualizer
        
        Implementation of various visualization techniques for pytorch image classifiers. This library can be used to visualize and understand any PyTorch image classifier. This is NOT an official PyTorch library, nor is it affiliated with Ross Wightman's [pytorch-image-models](https://github.com/rwightman/pytorch-image-models) library. 
        
        Currently, the following methods are implemented:
        
        - Filter visualization
        - Activations visualization
        - Maximally activated patches 
        - Saliency maps [1]
        - Synthetic image generation [1]
        - Adversarial attacks to fool models 
        - Feature inversion [2]
        - Deep Dream [3]
        
        Specific examples and details about the implementation and parameters of the above methods are described in details.ipynb. All of the above visualization techniques are discussed in [this](https://www.youtube.com/watch?v=6wcs6szJWMY&list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv&index=14)
        lecture.
        
        ## Installation
        
        ```bash
        $ pip install timm-vis
        ```
        
        ## Usage
        
        ```python
        from timm_vis.methods import *
        
        # available methods - visualize_filters, visualize_activations, 
        #   maximally_activated_patches, saliency_map, 
        #   generate_image, fool_model, feature_inversion, deep_dream
        
        ```
        
        ## Paper References
        
        [1] Karen Simonyan, Andrea Vedaldi, Andrew Zisserman. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. [https://arxiv.org/abs/1312.6034](https://arxiv.org/abs/1312.6034). 
        
        [2] Aravindh Mahendran, Andrea Vedaldi. Understanding Deep Image Representations by Inverting Them [https://arxiv.org/abs/1412.0035](https://arxiv.org/abs/1412.0035)
        
        [3] Alexander Mordvintsev, Christopher Olah, Mike Tyka. Inceptionism: Going Deeper into Neural Networks [https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html](https://ai.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html)
        
        ## Code References
        
        [4] Ross Wightman [pytorch-image-models](https://github.com/rwightman/pytorch-image-models)
        
        [5] Irfan Alghani Khalid [Saliency Map for Visualizing Deep Learning Model Using PyTorch](https://towardsdatascience.com/saliency-map-using-pytorch-68270fe45e80)
        
        [6] Utku Ozbulak. [pytorch-cnn-adversarial-attacks](https://github.com/utkuozbulak/pytorch-cnn-adversarial-attacks)
        
        [7] Duc Ngo [deep-dream-in-pytorch](https://github.com/duc0/deep-dream-in-pytorch)
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
