Lecture 'Multimodal Sensor Systems'
Course datesAll lecture and exercise dates for summer term 2019
Slides and lecture code
02 - Einführung in ConvNets
Code example: A simple MLP for classification of 2D data points with Keras
Code example: Trying to use a MLP as a classifer for images
Code example: Setting a custom convolution filter in Keras and applying it to a test image
Code example: Max-pooling filter in Keras and applying it to a test image
Code example: "Digit image classification experiment reloaded:" Is a CNN better than a MLP?
Code example: A CNN for classification of cars vs. bikes
Hint: GitHub does not support downloading single files directly. Instead, you can just download the whole repository.
Download this Jupyter notebook and fill in the missing code cells!
--> Solution for exercise 01 Besprechung 17.04.19: Exercise 02: Keras and MLP
Besprechung 24.04.19: Exercise 03: Experimenting with CNNs
- Great visualization of a small CNN by Adam Harley
- Precision and Recall by Boris Babenko
- Understanding the mAP Evaluation Metric for Object Detection
- mAP (mean Average Precision) for Object Detection
- How to calculate mAP for detection task for the PASCAL VOC Challenge?
- Real-time Object Detection with YOLO, YOLOv2 and now YOLOv3 (article from March 2018)
- Understanding the Basis of the Kalman Filter
- Object detection models (from 42m:40s), Stanford Lecture 11 | Detection and Segmentation of CS 231n: Convolutional Neural Networks for Visual Recognition Excellent lecture by Justin Johnson.
- All lecture videos from 2017 version of Stanford Lecture "CS 231n: Convolutional Neural Networks for Visual Recognition"