mmfashion
fashion-segmentation
| mmfashion | fashion-segmentation | |
|---|---|---|
| 1 | 1 | |
| 1,202 | 33 | |
| 0.0% | - | |
| 0.0 | 0.0 | |
| almost 2 years ago | over 1 year ago | |
| Python | Python | |
| Apache License 2.0 | - |
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.
mmfashion
-
Help with DeepFashion dataset
I am trying to find a good dataset that I can use for various ML applications involving fashion/clothing and I came across the DeepFashion dataset. I was blown away when I saw it... it has the exact type of functionality that I am looking for. I found this toolbox called mmfashion that uses the DeepFashion dataset and I cloned it and tried to get it set up, but I have been unsuccessful. I have also come across the Fashion-MNIST dataset that can help with classifying images, but DeepFashion seems to be full-featured and solves all of my use cases.
fashion-segmentation
What are some alternatives?
SEAM-Match-RCNN - Official code of paper: MovingFashion: a Benchmark for the Video-to-Shop Challenge
PixelLib - Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
ailia-models - The collection of pre-trained, state-of-the-art AI models for ailia SDK
pix2pix - This project uses a conditional generative adversarial network (cGAN) named Pix2Pix for the Image to image translation task.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Entity - EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
stable-diffusion-webui - Stable Diffusion web UI
caer - High-performance Vision library in Python. Scale your research, not boilerplate.