Models are provided for image and text classification

Generic image models

These models are pre-trained on the 1000 classes of the ImageNet ILSVRC Challenge. They can be used a is or finetuned to more targeted applications.

Caffe Tensorflow Source Top-1 Accuracy (ImageNet)
AlexNet Y N BVLC 57.1%
SqueezeNet Y N DeepScale 59.5%
Inception v1 / GoogleNet Y Y BVLC / Google 67.9%
Inception v2 N Y Google 72.2%
Inception v3 N Y Google 76.9%
ResNet 50 Y Y MSR 75.3%
ResNet 101 Y Y MSR 76.4%
ResNet 152 Y Y MSR 77%
Inception-ResNet-v2 N Y Google 79.79%
VGG-16 Y Y Oxford 70.5%
VGG-19 Y Y Oxford 71.3%

Custom images models

Below are free to use image models for a range of tasks.

Drawing

Models for image classification:

  • Fashion
  • Gender
  • Sports
  • Cars
  • Buildings

Text

Models for efficient text classification:

  • Sentiment analysis in over 10 languages
  • Reviews analysis
  • Ad-blocking

All models are free, even for commercial use.


DeepDetect documentation