Yi-Chen (Howard) Lo
### TL;DR: Make sure the width and height of your bboxes are greater than zero! So, I also ran into this issues (I am experimenting with my own dataset and...
@hanxiaoyaoer Hi, the 745 classes are generated from [here](https://github.com/howardyclo/ImageNet2COCO). Please take a look, thanks ;-).
Ok, I found that we can incorporate word features with [parallel inputs](http://opennmt.net/OpenNMT-tf/data.html#parallel-inputs). But it seems like we cannot make the decoder predict those features like Lua version? (a.k.a multi-task learning)
### Abstract - Current unsupervised/unpaired image-to-image translation (UIT) methods (see ref) typically requires many images in both source and target classes, which greatly limits their use. - This paper proposes...
### Spend Time to Understand Data 1. Understand the distribution and patterns. 2. Look for data imbalances and biases. 3. Examples: - Are very local features enough or do we...
### Summary - This paper presents "DVQA", a challenging VQA dataset for bar chart (structure, data retrieval and reasoning). - This paper demonstrates exsiting VQA algorithms can not perform well...
For problems in SANDY part, I just directly ask the author. Here is the Q&As: ### The detail of how SANDY encodes novel words 1. The static (global dictionary) look...
## MAML - A model-agnostic (only gradient decent) meta learning algorithm aims to find a good initialization point for model such that it can be fine-tuned quickly on new tasks....
## Reptile - Introduce a new FOMAML algorithm, Reptile, which works by repeatedly sampling a task, training on it, and **moving the initialization towards the trained weights** on that task....