CoCa-pytorch
x-clip
CoCa-pytorch | x-clip | |
---|---|---|
1 | 1 | |
975 | 649 | |
- | - | |
6.2 | 5.8 | |
5 months ago | 7 months ago | |
Python | Python | |
MIT License | MIT License |
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.
CoCa-pytorch
x-clip
-
[D] Problems with proprietary datasets
Now is it possible that some of these images were a part of train set of these models ? Maybe, but we can't really be sure without having access to the original dataset. To this end, are there any works that study this phenomenon more deeply and technically (with metrics etc.) ? I know few attempts to reproduce DALL-E and CLIP on open datasets but not sure whether such studies have been performed. Unfortunately I lack both the resources as well as technical competency to perform such studies myself but would love to see if you folks know anything about this.
What are some alternatives?
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
DALLE2-pytorch - Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
RETRO-pytorch - Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
CapDec - CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)
TimeSformer-pytorch - Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification
VehicleFinder-CTIM
PaLM-pytorch - Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways
performer-pytorch - An implementation of Performer, a linear attention-based transformer, in Pytorch
InternVideo - Video Foundation Models & Data for Multimodal Understanding
vectorrvnn - Data Driven method for hierarchical grouping of paths in Vector Graphics.