Freddy Lécué, Chief AI Scientist, Thales Group
Work smarter with actionable insights to quickly improve and validate your machine learning models.
Conduct rigorous testing and auditing to ensure robust and trustable AI.
Achieve buy-in from clients and decision-makers with fully explainable and understandable Proof-Of-Concepts (POCs), Minimal Viable Products (MVPs) or Demos.
Monitor your model performance and confidence level in production.
Using the free Zetane Viewer, you can open and inspect models from the Zetane Gallery or load your own models. We have a gallery of popular, pre-trained models to get you started.
ResNet50 is a convolutional neural network with 50 layers used for image classification. Deep neural networks are difficult to train, residual blocks of this model facilitate the training of deep networks and help increase accuracy.
Use this model for segmentation of images-- medical images in particular. It has an encoding/decoding structure, with some skip connections in between. It is well-suited for small datasets and quickly provides precise segmentations.
This object detection model predicts the presence of one or more objects, along with their classes and bounding boxes. YOLO (You Only Look Once) is a state-of-the-art model that conducts object detection in real-time with high accuracy.
Get started with the free Zetane Viewer (no email required).