AIbase
EN
Home
Resnet101 Clip.yfcc15m
R

Resnet101 Clip.yfcc15m

Developed by timm
CLIP-style dual-modal model trained on YFCC-15M dataset, compatible with both open_clip and timm frameworks
Image Classification
Safetensors
Open Source License:MIT#Zero-shot Image Classification#Dual Framework Compatibility#Quick GELU Activation
Downloads 134
Release Time : 10/23/2024

Model Overview

This model is a vision-language dual-modal model capable of performing zero-shot image classification tasks, supporting usage under both open_clip and timm frameworks

Model Features

Dual Framework Compatibility
Supports both open_clip and timm frameworks, providing more flexible usage options
Zero-shot Learning
Performs image classification on new categories without specific training
Quick GELU Activation
Uses quickgelu variant which may improve model training and inference efficiency

Model Capabilities

Zero-shot Image Classification
Cross-modal Retrieval
Image Feature Extraction

Use Cases

Image Understanding
Open-domain Image Classification
Classify images of arbitrary categories without retraining
Image-Text Matching
Calculate similarity between images and text descriptions
Content Moderation
Inappropriate Content Detection
Identify image content that violates policy requirements
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase