Studijní materiály (lectures)
1 - Intro: Autonomous Vehicle, Object Detection, Image Features (en) (.pdf)face-haar-example.zip
sliding_window.mp4
AdaBoost.xlsx
2 - Convolutional Networks - PyTorch (en) (.pdf)
0-intro-NN (cz) (.md)
1-(s)gd-example.py
2-loss-example.py
3-nn-from-scratch-pytorch.py
4-nn-simple-classification-model.py
3 - CNN Architectures: AlexNet, ZFNet, VGG, GoogLeNet (en) (.pdf)
3.1 ResNet, DenseNet, MobileNet, SqueezeNet, EfficientNet (en) (.pdf)
3.2 Dropout, Pytorch Dataset (en) (.pdf)
List of CNNs
Pytorch-CNN-Example.zip
alexnet.py
vgg-3x3x3-1x7x7.py
vgg.py
1x1.py
dropout.py
batch-norm.py
depthwise-pointwise.py
4 - Object Detection: RCNN, YOLO, SSD (en) (.pdf)
RCNN.zip (R-CNN, Fast R-CNN, Faster R-CNN, Cascade R-CNN, Sparse R-CNN)
YOLOv1 - Architektura (cz) (.md)
YOLOv1 - Trénování (cz) (.md)
YOLOv1 - Inference/Detekce (cz) (.md)
YOLOv1 - Ukázka implementace (.py)
YOLOv1-v26 - Další verze (cz) (.md)
YOLO26 (.pdf)
car_detection.mp4
5 - Transformer: Intro (cz) (.md)
5.1 - Transformer: ViT (Vision Transformer) (en) (.pdf)
5.2 - Transformer: Detection (cz) (.md)
ViT (cz) (.zip)
6 - Generative Adversarial Networks (GANs) (en) (.pdf)
GAN (cz) (.md)
GAN (cz) (.py)
GAN (.pdf)
DCGAN (.pdf)
Self-Attention GAN (.pdf)
7 - Neural Style Transfer (NST) (en) (.pdf)
Neural style transfer (cz) (.py)
fast-neural-style
img2img-turbo
AnimeGAN
8 - Convolutional Neural Networks for Image Segmentation (en) (.pdf)
Sematic segmentation (cz) (.py)
9 - Human Pose Estimation Methods (en) (.md)
Cvičení (exercises)
| Name | Description | References |
|---|---|---|
| 1.12.2026 8.12.2026 |
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 ViT-Examples.zip |
| 7. GAN (5p) | Experiment with GANs (e.g. try implementing DCGAN) to augment the parking lot training dataset. Compare the performance with and without the augmented data. |
video training-data DCGAN Tutorial parking_gan.mp4 parking_dcgan.mp4 |
