gombru Goto Github PK

models

Models built with TensorFlow

multi-modal-hate-speech

Code of the paper "Exploring Hate Speech Detection in Multimodal Publications" accepted in WACV 2020.

pycaffecnntemplate

pycaffe CNN template of an AlexNet - CaffeNet with data augmentation and training stuff

pycaffefcntemplate

pycaffe FCN VGG16 from https://github.com/shelhamer/fcn.berkeleyvision.org with some training stuff added and adapted to 2 classes

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

pytorchcnn

socialmediaweaklabeling

Learning to learn from Web and Social Media data. Joint image-text embeddings oriented to image by text retrieval.

tensorflowcnntemplate

Simple pycaffe-like example of an AlexNet-CaffeNet in TensorFlow

tensorflowcnntraining

textfcn

A Caffe Fully Convolutional Network that detects any kind of text and generates pixel-level heatmaps.

textinsocialnetworks

Automatic discovery of textual information in images from Social Networks - Master thesis of the Master in Computer Vision (CVC-UAB)

textproposalsinitialsuppression

Localizing text in scene images using TextProposals algorithm + FCN supression

textstyletransfer

texttopicnet

Self-supervised learning of visual features through embedding images into text topic spaces

torch-rnn-custom

tsne

My TSNE based on https://github.com/lvdmaaten/bhtsne/ and http://cs.stanford.edu/people/karpathy/cnnembed/

webvision

My strategy for the WebVision Challenge, using image-text join embeddings and soft labels.