Meng-Jiun Chiou

Following the author's instruction, if anyone use `./experiments/caption_lstm/train.sh` to train the network without enough RAM, it won't result in meaningful error message -- just produce some empty `caffemodel.h5` files and...

Initial Model Release

1

The models have been reelased. Feel free to play around with the code!

Issue about the performance

4

Hi @ruotianluo Thank you for your fantastic work. I followed your implementation to train the captioning model (TopDown) with the top 36 features I downloaded from the author. And below...

minor update to package name `opencv-python`

About filtering duplicate relations for VG dataset

3

It seems to me the following code snippet doesn't work as expected: https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch/blob/d0ffa40d92133d7d865e531146de82c8c8a344c0/maskrcnn_benchmark/data/datasets/visual_genome.py#L148-L156 I was thinking filtering out duplicate relations means for those exactly repeated relation triplets (i.e., not only...

Fix issue https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch/issues/129

Transformer model details

2

## ❓ Questions and Help Hi @KaihuaTang, thanks for your awesome work! I am wondering where I can find the details or an illustration of the Transformer model, as I...

remove redundant "evaluate.py"

Hi @genp I am wondering what license is COCO Attributes labels under. How about commercial use? Thanks!

Releasing baseline models

10

Hi @JingweiJ Thanks for the wonderful work. Do you plan to release the baseline models for the proposed tasks, i.e. (few-shot) action recognition, spatial-temporal scene graph prediction? That would greatly...