Blog Directory
Top level » Software » Machine Learning » Deep learning » Miscellaneous A comparison of deep-learning frameworks   A comparison of deep-learning frameworks (from Facebook)   Autoencoder network for learning a continuous representation of molecular structures.   CGT   - Computation Graph Toolkit (CGT) is a library for evaluation and differentiation of functions of multidimensional arrays. CleverHans   - A library for benchmarking vulnerability to adversarial examples. Deep learning frameworks: Overview   Deep learning galery   Deep learning software   distiller   Distributed (Deep) Machine Learning Community   - a collection of interesting ML projects with a focus on distributed computation Geometric deep learning   gnumpy   - a simple Python module that interfaces in a way almost identical to numpy, but does its computations on your computer's GPU. horovod   - Distributed training framework for TensorFlow (claimed to be faster than traditional Distributed TensorFlow). Hummingbird   - a library for compiling trained traditional ML models into tensor computations. Hummingbird allows users to seamlessly leverage neural network frameworks (such as PyTorch) to accelerate traditional ML models. Keras.JS   - Run trained Keras models in your browser, GPU-powered using WebGL. Models are serialized directly from the Keras JSON-format configuration file and associated HDF5 weights. NNPACK   - Acceleration package for neural networks on multi-core CPUs OverFeat   - an image recognizer and feature extractor built around a convolutional network. Rapids   - a suite of open source software libraries allowing one to execute end-to-end data science and analytics pipelines entirely on GPUs. SqueezeNet   - AlexNet-level accuracy with 50x fewer parameters TorchCraft   - an interface between StarCraft: Brood War and Torch, the deep learning environment.