wojciechmo Goto Github PK

Name: Wojciech Mo

Type: User

Bio: deep-learning computer-vision natural-language-processing reinforcement-learning

Wojciech Mo's Projects

Perform camera calibration on set of images with cheesboard pattern.

Synthesise image from semantic map using Cascaded Refinement Netowork and PyTorch.

Compress neural network with pruning and quantization using TensorFlow.

Double pendulum simulation. Equations of motion calculated in MatLab based on Lagrangian formula.

Generate new images with Generative Adversarial Network and Tensorflow.

Complete missing parts of an image with PyTorch

Solving system of linear equations with LU decomposition.

Train Convolutional Neural Network with Tensorflow and multiple GPU cards.

Polynomial approximation based on solving overdetermined system of linear equations with SVD matrix decomposition.

Deploy PyTorch models trained with Python using C++.

Teach an agent how to play Atari Breakout with Deep Q-Learning and TensorFlow.

Compare Q-Learning and Expected Value SARSA.

Teach an agent how to play Lunar Lander with Policy Gradients and TensorFlow.

Translate sentences from spanish to english with seq2seq and PyTorch.

Transform arbitrary photograph or video into artwork using Theano.

Deploy TensorFlow models trained with Python using C, C++, Java and JavaScript.

Generate new images with Variational Autoencoder and Tensorflow.

Train YOLOv2 object detector from scratch using Tensorflow.