Completed
225 - Attention U-net. What is attention and why is it needed for U-Net?
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Image Processing With Python
Automatically move to the next video in the Classroom when playback concludes
- 1 16 - Understanding digital images for Python processing
- 2 17 - Reading images in Python
- 3 18 - Image processing using pillow in Python
- 4 19 - image processing using scipy in Python
- 5 20 - Introduction to image processing using scikit-image in Python
- 6 21 - Scratch assay analysis with just 5 lines code in Python
- 7 22 - Denoising microscope images in Python
- 8 23 - Histogram based image segmentation in Python
- 9 24 - Random Walker segmentation in Python
- 10 25 - Reading Images, Splitting Channels, Resizing using openCV in Python
- 11 26 - Denoising and edge detection using opencv in Python
- 12 27 - CLAHE and Thresholding using opencv in Python
- 13 28 - Thresholding and morphological operations using openCV in Python
- 14 29 - Key points, detectors and descriptors in openCV
- 15 30 - Image registration using homography in openCV
- 16 32 - Grain size analysis in Python using a microscope image
- 17 33 - Grain size analysis in Python using watershed
- 18 34 - Grain size analysis in Python using watershed - multiple images
- 19 35 - Cell Nuclei analysis in Python using watershed segmentation
- 20 94 - Denoising MRI images (also CT & microscopy images)
- 21 95 - What is digital image filtering and image convolution?
- 22 96 - What is Gaussian Denoising Filter?
- 23 97 - What is median denoising filter?
- 24 98 - What is bilateral denoising filter?
- 25 99 - What is Non-local means (NLM) denoising filter?
- 26 100 - What is total variation (TV) denoising filter?
- 27 101 - What is block matching and 3D filtering (BM3D)?
- 28 102 - What is unsharp mask?
- 29 103 - Edge filters for image processing
- 30 104 - Ridge Filters to detect tube like structures in images
- 31 105 - What is Fourier Transform?
- 32 106 - Image filters using discrete Fourier transform (DFT)
- 33 112 - Averaging image stack in real and DCT space for denoising
- 34 113 - Histogram equalization and CLAHE
- 35 114 - Automatic image quality assessment using BRISQUE
- 36 115 - Auto segmentation using multi-otsu
- 37 Effect of Social Distancing on the spread of COVID-19 pandemic - A quick Python simulation
- 38 107 - Analysis of COVID-19 data using Python - Part 1
- 39 108 - Analysis of COVID-19 data using Python - Part 2
- 40 109 - Predicting COVID-19 cases using Python
- 41 110 - Visualizing COVID-19 cases & death information using Python and plotly
- 42 111 - What are the top 10 countries with highest COVID-19 cases and deaths?
- 43 116 - Measuring properties of labeled / segmented regions
- 44 117 - Shading correction using rolling ball background subtraction
- 45 118 - Object detection by template matching
- 46 119 - Sub-pixel image registration in Python
- 47 123 - Reference based image quality metrics
- 48 124 - Image quality by estimating sharpness
- 49 146 - Raspberry Pi - Learning python and deep learning on a tight budget
- 50 182 - How to batch process multiple images in python?
- 51 183 - OCR in python using keras-ocr
- 52 191 - Measuring image similarity in python
- 53 192 - Working with 3D and multi-dimensional images in python
- 54 199 - Detecting straight lines using Hough transform in python
- 55 200 - Image classification using gray-level co-occurrence matrix (GLCM) features and LGBM classifier
- 56 201 - Working with geotiff files using rasterio in python (also quick demo of NDVI calculation)
- 57 202 - Two ways to read HAM10000 dataset into python for skin cancer lesion classification
- 58 203 - Skin cancer lesion classification using the HAM10000 dataset
- 59 204 - U-Net for semantic segmentation of mitochondria
- 60 205 - U-Net plus watershed for instance segmentation
- 61 206 - The right way to segment large images by applying a trained U-Net model on smaller patches
- 62 207 - Using IoU (Jaccard) as loss function to train U-Net for semantic segmentation
- 63 208 - Multiclass semantic segmentation using U-Net
- 64 209 - Multiclass semantic segmentation using U-Net: Large images and 3D volumes (slice by slice)
- 65 210 - Multiclass U-Net using VGG, ResNet, and Inception as backbones
- 66 69 - Image classification using Bag of Visual Words (BOVW)
- 67 211 - U-Net vs LinkNet for multiclass semantic segmentation
- 68 212 - Classification of mnist sign language alphabets using deep learning
- 69 213 - Ensemble of networks for improved accuracy in deep learning
- 70 214 - Improving semantic segmentation (U-Net) performance via ensemble of multiple trained networks
- 71 215 - 3D U-Net for semantic segmentation
- 72 216 - Semantic segmentation using a small dataset for training (& U-Net)
- 73 218 - Difference between UpSampling2D and Conv2DTranspose used in U-Net and GAN
- 74 219 - Understanding U-Net architecture and building it from scratch
- 75 220 - What is the best loss function for semantic segmentation?
- 76 221 - Easy way to split data on your disk into train, test, and validation?
- 77 222 - Working with large data that doesn't fit your system memory - Semantic Segmentation
- 78 223 - Test time augmentation for semantic segmentation
- 79 224 - Recurrent and Residual U-net
- 80 225 - Attention U-net. What is attention and why is it needed for U-Net?
- 81 226 - U-Net vs Attention U-Net vs Attention Residual U-Net - should you care?
- 82 227 - Various U-Net models using keras unet collection library - for semantic image segmentation
- 83 228 - Semantic segmentation of aerial (satellite) imagery using U-net
- 84 229 - Smooth blending of patches for semantic segmentation of large images (using U-Net)
- 85 230 - Semantic Segmentation of Landcover Dataset using U-Net
- 86 231 - Semantic Segmentation of BraTS2020 - Part 0 - Introduction (and plan)
