João Lourenço Silva's repositories
EfficientUNetPlusPlus
Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.
segmentation_models.pytorch
Segmentation models with pretrained backbones. PyTorch.
qca-annotator
Simple React App to make QCA annotations on x-ray coronary angiography images and corresponding and semantic segmentation masks.
aima-python
Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
AutoAugment
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
automl
Google Brain AutoML
hiddenlayer
Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.
metrics
Machine learning metrics for distributed, scalable PyTorch applications.
online-cv
A minimal Jekyll Theme to host your resume (CV)
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
pytorch-lightning
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
syncap
Code and data for our paper "The Role of Syntactic Planning in Compositional Image Captioning", EACL 2021.
vision
Datasets, Transforms and Models specific to Computer Vision
web-gpu-monitor
Simple web-based monitoring tool for your small GPU cluster.