Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Generic implementation for clustering with deep learning : representation learning (DNN) + clustering
| Date | Stars |
|---|---|
| 2026-08-01 | 296 |
| 2026-08-06 | 296 |
| 2026-08-12 | 296 |
| 2026-08-13 | 296 |
| 2026-08-18 | 296 |
| 2026-11-04 | 296 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
Deep Learning for Clustering ======================= Code for project "Deep Learning for Clustering" under lab course "Deep Learning for Computer Vision and Biomedicine" - TUM. Depends on **numpy**, **theano**, **lasagne**, **scikit-learn**, **matplotlib**. #### Contributors - [Mohd Yawar Nihal Siddiqui](mailto:[email protected]) - [Elie Aljalbout](mailto:[email protected]) - [Vladimir Golkov](mailto:[email protected]) (Supervisor) #### Related Papers: This repository is an implementation of the paper : Elie Aljalbout, Vladimir Golkov, Yawar Siddiqui, Daniel Cremers "Clustering with Deep Learning: Taxonomy and new methods" - arxiv: https://arxiv.org/abs/1801.07648 Usage -------- Use the main script for training, visualizing clusters and/or reporting clustering metrics ``` python main.py <options> ``` Option | | -------- | --- ```-d DATASET_NAME, --dataset DATASET_NAME ```| ``(Required) Dataset on which autoencoder is to be trained trained, or metrics/visualizations are to be performed [MNIST,COIL20]`` ```-a ARCH_IDX, --architecture ARCH_IDX```| ``(Required) Index of architecture of autoencoder in the json file (archs/)`` ``--pretrain EPOCHS`` | ``Pretrain the autoencoder for specified #epochs specified by architecture on specified dataset`` ``--cluster EPOCHS``| ``Refine the autoencoder for specified #epochs with clustering loss, assumes that pretraining results are available`` ``--metrics``| ``Report k-means clustering metrics on the clustered latent space, assumes pretrain and cluster based training have been performed`` ``--visualize``|``Visualize the image space and latent space, assumes pre-training and cluster based training have been performed`` Project Structure ------------------------ Folder / File | Description| -------- | --- <i class="icon-folder-open"></i> archs| Contains json files specifying architectures for autoencoder networks used. File ``mnist.json`` contains architectures for MNIST dataset. We use the second architecture for the reported results (command line argument ``-a 1``) <i class="icon-folder-open"></i> coil, mnist | Contains the datasets COIL20 and MNIST respectively <i class="icon-folder-open"></i> logs| Output folder for logs generated by the scripts. Named by date and time of script execution <i class="icon-folder-open"></i>plots|Scatter plots showing the raw, pre-trained latent space, and the final latent space clusters <i class="icon-folder-open"></i>saved_params | Contains saved network parameters and saved representation of inputs in latent space <i class="icon-file"></i> custom_layers.py | Custom lasagne layers, Unpool2D - which performs inverse max pooling by replicating input pixels as dictated by the filter size, and the ClusteringLayer - a layer that outputs soft cluster assignments based on k-means cluster distance <i class="icon-file"></i> main.py | The main python script for training and evaluating the network <i class="icon-file"></i> misc.py | Contains dataset handlers and other utility methods <i class="icon-file"></i>network.py| Contains classes for parsing and building the network from json files and also for training the network Autoencoder Builder ----------------------------- We've implemented a **NetworkBuilder** class that can be used to quickly describe the architecture of an autoencoder through a **json** file. The json specification of the architecture is a dictionary with the following fields | Field | Description ---------|------------ name| Name identifier given to the architecture, used for file naming while saving parameters batch_size| Batch size to be used while training the network use_batch_norm| Whether to use batch normalization for convolutional/deconvolutional layers network_type| Type of network - convolutional or fully connected layers| A list describing the encoder part of the autoencoder Further, each item in the layers list is a dictionary with the following fields | Field | Description ---------|------------
Excerpt of 8,394 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fd3ade273f58b021, topic:deep-learning, readme:pretraining, readme:pre-training