Hello there,
I recently stumbled upon this repository and was interested in trying out your code. However, using single-threaded sklearn doesn't seem to be efficient to me, compared to using GPU-optimized PyTorch or TF.
Do you have any plans of moving to those frameworks, or would you accept a pullrequest implementing these?
Regards,
Luke
C++ and Python implementation of a automatic system for pedestrian detection at night using far infrared visual information based on convolutional neural networks.
Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation
This project contains a CNN architecture (inspired by vgg16). We trained our model on 5216 training examples and 16 examples as validation dataset. Applied Data augmentation and by customizing the Class weights model was able to classify Chest X-ray with 90% accuracy.
Geant4 EM physics simulation R&D project looking for solutions to reduce the computing performance bottleneck experienced by HEP detector simulation applications.
An Ansible role to deploy a docker environment on specific linux systems (with some extras like ctop, docker-compose, GPU support in docker for Nvidia graphic cards)
Hello there,
I recently stumbled upon this repository and was interested in trying out your code. However, using single-threaded sklearn doesn't seem to be efficient to me, compared to using GPU-optimized PyTorch or TF.
Do you have any plans of moving to those frameworks, or would you accept a pullrequest implementing these?
Regards,
Luke