bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

MIT License

Stars

1.4K

Ecosystems: Jupyter Notebook

Total Pull Requests

Merged Pull Requests

Total Issues

Time to Close Issues

N/A

3 months

Code for training py-faster-rcnn and py-R-FCN on multiple GPUs in caffe

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO de...

Efficient Image Captioning code in Torch, runs on GPU

Solution and summary for Intel & MobileODT Cervical Cancer Screening (3-class classification)

3.47% on CIFAR-10

Nice and tidy implementation of resnet-type networks for classification in tensorflow 2.0