Compare pre-trained ImageNet models

Upload an image or paste image URL to classify the image

ImageNet results

Comparison of Deep Convolutional Neural Network Architectures

We are using canned architectures with pre-trained weights provided by TensorFlow Keras.
Here's a comparison between the SOTA ImageNet architectures.

Input Size224 x 224224 x 224224 x 224299 x 299299 x 299
Size14 MB98 MB548 MB92 MB88 MB
Parameters3.5 M25.6 M143.6 M23.8 M22.9 M
Top-1 Accuracy71.30%74.90%71.30%77.90%79.00%
Top-5 Accuracy90.10%92.10%90.00%93.70%94.50%
Inference Time1.1512.452.354

How to use the API?

# Provide `url` of the image to classify and ImageNet `model` architectures list 
import requests
url = "" data = {"url": "", "model": ["MobileNetV2", "ResNet50", "VGG19", "InceptionV3", "Xception"]} requests.get(url, data=data).json()