Posts

I used Captum to interpre the output of a MobileNetV2, which visualized the main regions in the input image that drove the model to …
5 min read

I converted a PyTorch model to Core ML and ran it on an iPhone.
4 min read

I combined my previous posts on image captioning and visual question answering and extended them to a wider topic - connecting computer …
8 min read

Recently I was working with PyTorch multi-GPU training and I came across a nightmare GPU memory problem. After some expensive trial and …
14 min read

I will start from the problem of semantic segmentation, introduce how to use CNNs to solve it, and talk about fully convolutional …
30 min read

I read some papers on VQA and summarized its state-of-the-art, bottlenecks and possible solutions.
6 min read

I have been fascinated by image captioning for some time but still have not played with it. I gave it a try today using the open source …
5 min read