Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
👗 Ven: AI-Powered Community Fashion Marketplace
|
| 2 |
Ven is a community-driven platform designed to foster a circular economy by enabling neighbors to swap and share clothing items. By leveraging advanced Machine Learning, Ven automates the organization of community inventory and provides a seamless, intuitive recommendation experience.
|
| 3 |
|
|
|
|
|
|
|
| 4 |
🌟 Mission
|
| 5 |
Our goal is to reduce textile waste and strengthen community ties. Ven allows users to discover local fashion gems using AI that "understands" style, texture, and garment types without requiring manual tagging from users.
|
| 6 |
|
|
@@ -12,6 +14,14 @@ Smart Matching: Get the Top 3 most similar items from the community inventory ba
|
|
| 12 |
1. Data & EDA
|
| 13 |
We utilized a curated subset of 5,050 images from the Fashionpedia dataset. Our Exploratory Data Analysis (EDA) revealed a high visual complexity with an average of ~7 items per image, necessitating a robust visual model.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
2. Embeddings (The AI Brain)
|
| 16 |
To represent fashion items mathematically, we used the CLIP (Contrastive Language-Image Pre-training) model (clip-ViT-B-32).
|
| 17 |
Vector Space: Every item is converted into a normalized 512-dimensional vector.
|
|
@@ -34,6 +44,8 @@ Dimensionality Reduction: We used t-SNE to project the high-dimensional data int
|
|
| 34 |
4. Efficient Retrieval
|
| 35 |
For production readiness, we store our pre-computed embeddings in a Parquet file. This allows the Space to load the inventory instantly and perform Cosine Similarity matching in milliseconds.
|
| 36 |
|
|
|
|
|
|
|
| 37 |
🛠️ Built With
|
| 38 |
Gradio: For the interactive web interface.
|
| 39 |
Hugging Face Datasets: For seamless data streaming.
|
|
|
|
| 1 |
👗 Ven: AI-Powered Community Fashion Marketplace
|
| 2 |
Ven is a community-driven platform designed to foster a circular economy by enabling neighbors to swap and share clothing items. By leveraging advanced Machine Learning, Ven automates the organization of community inventory and provides a seamless, intuitive recommendation experience.
|
| 3 |
|
| 4 |
+
SEE OUR PRESENTATION HERE -> https://youtu.be/znXkEe9WqvQ
|
| 5 |
+
|
| 6 |
🌟 Mission
|
| 7 |
Our goal is to reduce textile waste and strengthen community ties. Ven allows users to discover local fashion gems using AI that "understands" style, texture, and garment types without requiring manual tagging from users.
|
| 8 |
|
|
|
|
| 14 |
1. Data & EDA
|
| 15 |
We utilized a curated subset of 5,050 images from the Fashionpedia dataset. Our Exploratory Data Analysis (EDA) revealed a high visual complexity with an average of ~7 items per image, necessitating a robust visual model.
|
| 16 |
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
2. Embeddings (The AI Brain)
|
| 26 |
To represent fashion items mathematically, we used the CLIP (Contrastive Language-Image Pre-training) model (clip-ViT-B-32).
|
| 27 |
Vector Space: Every item is converted into a normalized 512-dimensional vector.
|
|
|
|
| 44 |
4. Efficient Retrieval
|
| 45 |
For production readiness, we store our pre-computed embeddings in a Parquet file. This allows the Space to load the inventory instantly and perform Cosine Similarity matching in milliseconds.
|
| 46 |
|
| 47 |
+
|
| 48 |
+
|
| 49 |
🛠️ Built With
|
| 50 |
Gradio: For the interactive web interface.
|
| 51 |
Hugging Face Datasets: For seamless data streaming.
|