Studijní materiály (lectures)
1 - Intro: Autonomous Vehicle, Object Detection, Image Features1.1 face-haar-example.zip
1.2 sliding_window.mp4
1.3 AdaBoost.xlsx
2 - Convolutional Networks: LeNet, PyTorch
2.1 nn-from-scratch-pytorch.py
2.2 nn-simple-classification-model.py
2.3 sgd-example.py
2.4 loss-example.py
3 - CNN Architectures: AlexNet, ZFNet, VGG, GoogLeNet
3.1 ResNet, DenseNet, MobileNet, SqueezeNet, EfficientNet
3.2 Dropout, Pytorch Dataset
3.3 feature-map-visu.py
3.4 dropout-example.py
3.5 batch-norm_example.py
3.6 1x1-example.py
3.7 3x3x3-1x7x7-example.py
3.8 depthwise-pointwise.py
4 - Object Detection: RCNN, YOLO, SSD
4.1 car_detection.mp4
4.2 RCNN.zip
5 - ViT (Vision Transformer)
6 - Generative Adversarial Networks (GANs)
6.1 - Neural Style Transfer (NST)
6.2 parking_gan.mp4
6.3 parking_dcgan.mp4
6.4 img2img-turbo
6.5 AnimeGAN
6.6 fast-neural-style
7 - Convolutional Neural Networks for Image Segmentation
8 - Human Pose Estimation Methods
Cvičení (exercises)
| Name | Description | References |
|---|---|---|
| 2.12.2025 9.12.2025 |
In-person task presentation. Assessment will also take into account the presentation of the individual solution and the understanding of the subject matter. |
|
| 1. Parking Lot Analysis (6p) | Experiment with classical edge detection, Haar/HOG/LBP for parking lot analysis. |
● slides ● video ● template.zip ● scikit-image ● trainimages |
| 2. Neural Network (Pytorch) (4p) | Experiment with neural networks for parking lot analysis (use data from from the previous exercise). You can combine the following files to create a basic classifier. |
● 01-torch-dataset.py ● 02-torch-model0.py ● 03-torch-trainloop.py |
| 3. CNN (Pytorch) (10p) | CNN for parking lot analysis (use data from from the previous exercise). Experiment with different CNN architechtures (e.g. VGG, ResNet, GoogLeNet). Try to design (implement) and test your own architecture (e.g. My-VGG, My-ResNet, My-GoogLeNet). Experiment with layers, learning rate, number of epochs, normalization, dropout, loss function, data augmentation. Create a report (e.g. document with graphs, tables, configurations) that maps the performed experiments (max. 5 pages). |
● cnn tutorial ● alexnet.py ● vgg.py ● inception.py ● resnet.py ● tensorb.py ● netron.py ● t-learning.py ● depthwise-pointwise.py |
| 4. RCNN/SSD/YOLO/DeepLab/Unet (5p) | Experiment with different detection and segmentation approaches to improve parking space analysis. You can use already trained (available) models - but try to combine the detection/segmentation results with the recognition results (from the previous exercises) to produce the output prediction. |
● Pytorch Object Detection ● Pytorch Semantic Segmentation ● Ultralytics YOLO11 |
| 5. Custom YOLO Training (5p) | + The addition to the previous exercise 4: Experiment with different yolo parameters to train your own YOLO model for vehicle detection to improve parking space analysis. For annotation, you can use the annotation program included in yolov11.zip archive or some other ways (e.g. https://www.makesense.ai/). For the training data, you can use attached train-images-for-yolo.zip |
● yolov11.zip ● train-images-for-yolo.zip ● example-of-train-batch0.jpg |
| 6. Vision Transformer (Pytorch) (5p) | ViT - Vision Transformer: try to design (implement) and test ViT architecture for parking lot analysis (use data from from the previous exercise). |
● slides |
| 7. GAN (5p) | Experiment with GAN to extend the parking lot training dataset. Compare results with and without the extended set. |
● video ● training-data ● DCGAN Tutorial |
