meshed-memory-transformer
Meshed-Memory Transformer for Image Captioning. CVPR 2020 (by aimagelab)
py-bottom-up-attention
PyTorch bottom-up attention with Detectron2 (by airsplay)
meshed-memory-transformer | py-bottom-up-attention | |
---|---|---|
2 | 1 | |
497 | 227 | |
0.0% | - | |
0.0 | 1.8 | |
over 1 year ago | over 2 years ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
meshed-memory-transformer
Posts with mentions or reviews of meshed-memory-transformer.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-06-03.
- [D] Data transfer(image features) between different models in separate docker containers
-
[R] end-to-end image captioning
I could use some up-to-date models (e.g, this one: https://github.com/aimagelab/meshed-memory-transformer), but all those I looked into require pre-processing step of features/bounding-boxes generation. The problem is that I can't use an off-the shelf bounding-box extraction model as it would not perform well on the dataset I have (images are not like COCO at all). So I was wondering if there is a relatively up-to-date architecture that I can use that will not require this processing step. That is, an implementation that requires only inputs (images) and outputs (sentences).
py-bottom-up-attention
Posts with mentions or reviews of py-bottom-up-attention.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-06-03.
What are some alternatives?
When comparing meshed-memory-transformer and py-bottom-up-attention you can also consider the following projects:
a-PyTorch-Tutorial-to-Image-Captioning - Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning
clip-glass - Repository for "Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search"
stargan-v2 - StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
BLIP - PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
catr - Image Captioning Using Transformer