taldatech · mkimhi · Oct 25, 2021 · Oct 25, 2021 · Oct 25, 2021 · Oct 26, 2021
diff --git a/.gitignore b/.gitignore
@@ -1 +1,6 @@
-/.ipynb_checkpoints
+/.ipynb_checkpoints
+/datasets
+/checkpoints
+/models
+/goturn.caffemodel
+/goturn.prototxt
diff --git a/README.md b/README.md
@@ -8,19 +8,22 @@ Technion EE 046746 - Computer Vision
 </h1>
   <p align="center">
     <a href="https://taldatech.github.io">Tal Daniel</a> •
+    <a href="https://github.com/mkimhi">Moshe Kimhi</a> • 
+    <a href="https://github.com/HilaManor">Hila Manor</a> •
     <a href="https://eliasnehme.github.io/">Elias Nehme</a> •
     <a href="https://github.com/dahliau">Dalia Urbach</a> •
-  <a href="https://webee.technion.ac.il/people/anat.levin/">Anat Levin</a>
+    <a href="https://webee.technion.ac.il/people/anat.levin/">Anat Levin</a> •
+    <a href="https://lihi.net.technion.ac.il/">Lihi Zelnik-Manor</a>
   </p>
 
 Jupyter Notebook tutorials for the Technion's EE 046746 Computer Vision course
 
-Previous semesters: <a href="https://github.com/taldatech/ee046746-computer-vision/tree/spring20">Spring 2020</a>
+Previous semesters: <a href="https://github.com/taldatech/ee046746-computer-vision/tree/spring20">Spring 2020</a>, <a href="https://github.com/taldatech/ee046746-computer-vision">Spring 2021</a>, <a href="https://github.com/hilamanor/ee046746-computer-vision/tree/winter22">Winter 2021-2022</a>
 
 <h4 align="center">
-    <a href="https://colab.research.google.com/github/taldatech/ee046746-computer-vision"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
-    <a href="https://nbviewer.jupyter.org/github/taldatech/ee046746-computer-vision/tree/master/"><img src="https://raw.githubusercontent.com/taldatech/ee046211-deep-learning/main/assets/nbviewer_badge.svg" alt="Open In NBViewer"/></a>
-    <a href="https://mybinder.org/v2/gh/taldatech/ee046746-computer-vision/master"><img src="https://mybinder.org/badge_logo.svg" alt="Open In Binder"/></a>
+    <a href="https://colab.research.google.com/github/HilaManor/ee046746-computer-vision"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+    <a href="https://nbviewer.jupyter.org/github/HilaManor/ee046746-computer-vision/tree/master/"><img src="https://raw.githubusercontent.com/taldatech/ee046211-deep-learning/main/assets/nbviewer_badge.svg" alt="Open In NBViewer"/></a>
+    <a href="https://mybinder.org/v2/gh/HilaManor/ee046746-computer-vision/master"><img src="https://mybinder.org/badge_logo.svg" alt="Open In Binder"/></a>
 
 </h4>
 
@@ -40,19 +43,18 @@ Previous semesters: <a href="https://github.com/taldatech/ee046746-computer-visi
 |`Setting Up The Working Environment.pdf`| Guide for installing Anaconda locally with Python 3 and PyTorch, integration with PyCharm and using GPU on Google Colab |
 |`ee046746_tut_01_intro_image_processing_python.ipynb\pdf`| Python basics: NumPy, Matplotlib, OpenCV basics: Reading and Writing Images, Basic Image Manipulations, Image Processing 101: Thresholding, Blurring |
 |`ee046746_tut_01_2_deep_learning_pytorch_basics.ipynb\pdf`| Deep Learning and PyTorch basics, MNIST, Fashion-MNIST, MULTI-layer Perceptron (MLP), Fully-Connected (FC) |
-|`ee046746_tut_02_edge_and_line_detection.ipynb\pdf`| Edge and Line detection, Canny, Hough transform, RANSAC, and SCNN |
-|`ee046746_tut_03_04_convolutional_neural_networks.ipynb\pdf`| 2D Convolution (Cross-corelation), Convolution-based Classification, Convolutional Neural Networks (CNNs), Regularization and Overfitting, Dropout, Data Augmentation, CIFAR-10 dataset, Visualizing Filters, The history of CNNs, Applications of CNNs, The problems with CNNs (adversarial attacks, poor generalization, fairness-undesirable biases) |
+|`ee046746_tut_02_probabilistic_discriminative_learning.ipynb\pdf`| Intro to Machine Learning, Discriminative vs Generative Models, Probabilistic Discriminative Models |
+|`ee046746_tut_03_04_convolutional_neural_networks.ipynb\pdf`| 2D Convolution (Cross-corelation), Convolution-based Classification, Convolutional Neural Networks (CNNs), Regularization and Overfitting, Dropout, Data Augmentation, SVHN dataset, Visualizing Filters, The history of CNNs, Applications of CNNs, The problems with CNNs (adversarial attacks, poor generalization, fairness-undesirable biases) |
 |`ee046746_tut_03_04_appndx_visualizing_cnn_filters.ipynb\pdf`| Appendix - How to visualize CNN filters and filter activations given image with PyTorch |
-|`ee046746_tut_05_deep_semantic_segmentation.ipynb\pdf`| Semantic Segmentation, Intersection over Union (IoU), Average Precision (AP), PASCAL Visual Object Classes, Common Objects in COntext (COCO), Fully Convolutional Network (FCN),Up-Convolution / Transposed-Convolution, Skip connections, Pyramid Scene Parsing Network (PSPNet), 1x1 convolution, Mask R-CNN, DeepLab, Atrous convolution, Conditional Random Field (CRF) |
-|`ee046746_tut_06_generative_adversarial_networks_gan.ipynb\pdf`| Generative Adversarial Network (GAN), Explicit/Implicit density estimation, Nash Equilibrium, Mode Collapse, Vanishing/Diminishing Gradient, Conditional GANs, WGAN, EBGAN, BEGAN, Tips for Training GANs, Pix2Pix, CycleGAN |
-|`ee046746_tut_07_alignment.ipynb\pdf`| Feature Matching, Parametric Transformations, Image Warping, Image Blending, Panorama Stitching, Kornia |
-|`ee046746_tut_08_deep_uncertainty.ipynb\pdf`| Need for Uncertainty, Epistemic and Aleatoric Uncertainty, Logelikihood Modelling, Bayesian Neural Networks, Dropout, Evidental Deep Learning |
-|`ee046746_tut_09_deep_object_detection.ipynb\pdf`|Deep Object Detection, Localization, Sliding Windows, IoU, AP, Region-based Convolutional Neural Networks (R-CNN) Family, Fast/er R-CNN, Selective Search, Non-Maximum Supression (NMS), Region of Interest Pooling Layer (RoI), Region Proposal Network (RPN), Anchor boxes, Detectron2, You Only Look Once (YOLO) Family, YOLO V1-V4, Single Shot Multibox Detection (SSD) |
-|`ee046746_tut_10_geometry_review.ipynb\pdf`| Camera Models, Camera Matrix, Intrinsic and Extrinsic Parameters, Distortion Models, Camera Calibration, Homography Edge Cases, Epipolar Geometry, Essential/Fundamental Matrix, 8-point Algorithm |
-|`ee046746_tut_11_stereo_imaging.ipynb\pdf`| Triangulation, Disparity Maps, Stereo Concept, Stereo Rectification, Stereo Matching, Depth Smoothing, Point Cloud Visualization |
-|`ee046746_tut_12_3d_deep_learning.ipynb\pdf`| Time-of-Flight Cameras, 3D Representations, Voxnet, Multi-view CNNs, Point Clouds, PointNet, PointNet++, 3D Generative Models |
-|`ee046746_tut_13_deep_object_tracking.ipynb\pdf`| Object Detection vs Object Tracking, Detection Failure Cases, Motion Model, Visual Appearance Model, Detection-Based Vs. Detection-Free, Offline Vs. Online Tracking, Generic Object Tracking Using Regression Networks (GOTURN), Multi-Domain Convolutional Neural Network Tracker (MDNet), Deep Simple Online and Realtime Tracking (Deep SORT) |
-|`ee046746_tut_14_deep_computational_imaging.ipynb\pdf`| Computational Imaging, Compressive Sensing, Depth Encoding PSFs, Computer Vision Pipelines, Differentiable Optics, Deep Optics, Extended Depth of Field, Monocular Depth Estimation, High Dynamic Range Imaging, Video Compressive Sensing |
+|`ee046746_tut_05_deep_object_detection.ipynb\pdf`| Deep Object Detection, Localization, Sliding Windows, Intersection over Union (IoU), Average Precision (AP), Region-based Convolutional Neural Networks (R-CNN) Family, Fast/er R-CNN, Selective Search, Non-Maximum Supression (NMS), Region of Interest Pooling Layer (RoI), Region Proposal Network (RPN), Anchor boxes, Detectron2, You Only Look Once (YOLO) Family, YOLO V1-V4, Single Shot Multibox Detection (SSD) |
+|`ee046746_tut_06_deep_semantic_segmentation.ipynb\pdf`| Semantic Segmentation, IoU, AP, PASCAL Visual Object Classes, Common Objects in COntext (COCO), Fully Convolutional Network (FCN),Up-Convolution / Transposed-Convolution, Skip connections, Pyramid Scene Parsing Network (PSPNet), 1x1 convolution, Mask R-CNN, DeepLab, Atrous convolution, Conditional Random Field (CRF) |
+|`ee046746_tut_07_deep_object_tracking.ipynb\pdf` | Object Detection vs Object Tracking, Detection Failure Cases, Motion Model, Visual Appearance Model, Detection-Based Vs. Detection-Free, Offline Vs. Online Tracking, Generic Object Tracking Using Regression Networks (GOTURN), Multi-Domain Convolutional Neural Network Tracker (MDNet), Deep Simple Online and Realtime Tracking (Deep SORT) |
+|`ee046746_tut_08_edge_and_line_detection.ipynb\pdf` | Edge and Line detection, Canny, Hough transform, RANSAC, and SCNN |	
+|`ee046746_tut_09_homography_alignment_panoramas.ipynb\pdf` | Feature Matching, Parametric Transformations, RANSAC, Image Warping, Image Blending, Panorama Stitching, Kornia |
+|`ee046746_tut_10_geometry_review.ipynb\pdf`|Camera Models, Camera Matrix, Intrinsic and Extrinsic Parameters, Distortion Models, Camera Calibration, Homography Edge Cases, Epipolar Geometry, Essential/Fundamental Matrix, 8-point Algorithm|
+|`ee046746_tut_11_structure_from_motion.ipynb\pdf`|Pose Estimation, Triangulation, Reconstruction, Two-view Structure from Motion, Bundle Adjustment, Incremental Smoothing and Mapping|
+|`ee046746_tut_12_self_supervised_learning.ipynb\pdf`|Representation and Self-Supervised Learning, Autoencoders, Self-Supervised Learning, Corrupted Version Reconstruction & Visual Common Sense Tasks, Contrastive Methods, Simple Framework for Contrastive Learning of Visual Representations (SimCLR), Using the learned Representation for Downstream Tasks, Momentum Contrast (MoCo), Contrastive Predictive Coding (CPC)|
+|`ee046746_tut_13_generative_adversarial_networks_gan.ipynb\pdf`|Generative Adversarial Network (GAN), Explicit/Implicit density estimation, Nash Equilibrium, Mode Collapse, Vanishing/Diminishing Gradient, Conditional GANs, WGAN, EBGAN, BEGAN, Tips for Training GANs, Pix2Pix, CycleGAN|
 
 ## Running The Notebooks
 You can view the tutorials online or download and run locally.
@@ -68,23 +70,23 @@ You can view the tutorials online or download and run locally.
 
 Jupyter Nbviewer:
 
-[![nbviewer](https://raw.githubusercontent.com/taldatech/ee046211-deep-learning/main/assets/nbviewer_badge.svg)](https://nbviewer.jupyter.org/github/taldatech/ee046746-computer-vision/tree/master/)
+[![nbviewer](https://raw.githubusercontent.com/taldatech/ee046211-deep-learning/main/assets/nbviewer_badge.svg)](https://nbviewer.jupyter.org/github/HilaManor/ee046746-computer-vision/tree/master/)
 
 
 Press on the "Open in Colab" button below to use Google Colab:
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/taldatech/ee046746-computer-vision)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/HilaManor/ee046746-computer-vision)
 
 Or press on the "launch binder" button below to launch in Binder:
 
-[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/taldatech/ee046746-computer-vision/master)
+[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/HilaManor/ee046746-computer-vision/master)
 
 Note: creating the Binder instance takes about ~5-10 minutes, so be patient
 
 ### Running Locally
 
 Press "Download ZIP" under the green button `Clone or download` or use `git` to clone the repository using the 
-following command: `git clone https://github.com/taldatech/ee046746-computer-vision.git` (in cmd/PowerShell in Windows or in the Terminal in Linux/Mac)
+following command: `git clone https://github.com/HilaManor/ee046746-computer-vision.git` (in cmd/PowerShell in Windows or in the Terminal in Linux/Mac)
 
 Open the folder in Jupyter Notebook (it is recommended to use Anaconda). Installation instructions can be found in `Setting Up The Working Environment.pdf`.
 
@@ -116,4 +118,4 @@ In Windows open `Anaconda Prompt` from the start menu, in Mac/Linux open the ter
 |`pytorch` (gpu)| `conda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch` |
 
 
-5. To open the notbooks, open Ananconda Navigator or run `jupyter notebook` in the terminal (or `Anaconda Prompt` in Windows) while the `deep_learn` environment is activated.
+5. To open the notbooks, open Ananconda Navigator or run `jupyter notebook` in the terminal (or `Anaconda Prompt` in Windows) while the `deep_learn` environment is activated.
diff --git a/assets/MnistExamples.png b/assets/MnistExamples.png
diff --git a/assets/SSCL_probelm.png b/assets/SSCL_probelm.png
diff --git a/assets/autoencoder_1.jpeg b/assets/autoencoder_1.jpeg
diff --git a/assets/autoencoder_2.jpeg b/assets/autoencoder_2.jpeg
diff --git a/assets/calibration-patterns.gif b/assets/calibration-patterns.gif
diff --git a/assets/canny_nonmax.png b/assets/canny_nonmax.png
diff --git a/assets/context_encoder.PNG b/assets/context_encoder.PNG
diff --git a/assets/context_encoder_NN1.png b/assets/context_encoder_NN1.png
diff --git a/assets/context_encoder_NN2.png b/assets/context_encoder_NN2.png
diff --git a/assets/context_encoder_res.png b/assets/context_encoder_res.png
diff --git a/assets/contrastive_1.png b/assets/contrastive_1.png
diff --git a/assets/contrastive_puzzle.gif b/assets/contrastive_puzzle.gif
diff --git a/assets/cpc.png b/assets/cpc.png
diff --git a/assets/cpc2.png b/assets/cpc2.png
diff --git a/assets/cpc_future.gif b/assets/cpc_future.gif
diff --git a/assets/cpc_images.png b/assets/cpc_images.png
diff --git a/assets/gradient_descent_lr.png b/assets/gradient_descent_lr.png
diff --git a/assets/infonce_loss.png b/assets/infonce_loss.png
diff --git a/assets/ml_tut_data_vs_prior.png b/assets/ml_tut_data_vs_prior.png
diff --git a/assets/ml_tut_missing_number.png b/assets/ml_tut_missing_number.png
diff --git a/assets/ml_tut_model_comp.png b/assets/ml_tut_model_comp.png
diff --git a/assets/ml_tut_nn1.png b/assets/ml_tut_nn1.png
diff --git a/assets/ml_tut_nn1_test.png b/assets/ml_tut_nn1_test.png
diff --git a/assets/ml_tut_nn5_test.png b/assets/ml_tut_nn5_test.png
diff --git a/assets/ml_tut_reinforcement_learning.png b/assets/ml_tut_reinforcement_learning.png
diff --git a/assets/ml_tut_sigmoid.png b/assets/ml_tut_sigmoid.png
diff --git a/assets/ml_tut_supervised_learning.png b/assets/ml_tut_supervised_learning.png
diff --git a/assets/ml_tut_supervised_learning2.png b/assets/ml_tut_supervised_learning2.png
diff --git a/assets/ml_tut_transactions_dataset.png b/assets/ml_tut_transactions_dataset.png
diff --git a/assets/ml_tut_transactions_example.png b/assets/ml_tut_transactions_example.png
diff --git a/assets/ml_tut_transactions_half_data.png b/assets/ml_tut_transactions_half_data.png
diff --git a/assets/ml_tut_transactions_logistic_linear.png b/assets/ml_tut_transactions_logistic_linear.png
diff --git a/assets/ml_tut_transactions_logistic_poly.png b/assets/ml_tut_transactions_logistic_poly.png
diff --git a/assets/ml_tut_transactions_qda.png b/assets/ml_tut_transactions_qda.png
diff --git a/assets/ml_tut_transactions_train.png b/assets/ml_tut_transactions_train.png
diff --git a/assets/ml_tut_transactions_train_test.png b/assets/ml_tut_transactions_train_test.png
diff --git a/assets/ml_tut_transactions_train_y0.png b/assets/ml_tut_transactions_train_y0.png
diff --git a/assets/ml_tut_unsupervised_learning.png b/assets/ml_tut_unsupervised_learning.png
diff --git a/assets/ml_tut_unsupervised_learning2.png b/assets/ml_tut_unsupervised_learning2.png
diff --git a/assets/moco.png b/assets/moco.png
diff --git a/assets/orthographic_camera.png b/assets/orthographic_camera.png
diff --git a/assets/rep_data.png b/assets/rep_data.png
diff --git a/assets/rotation_prediction.png b/assets/rotation_prediction.png
diff --git a/assets/rotation_prediction_NN1.png b/assets/rotation_prediction_NN1.png
diff --git a/assets/rotation_prediction_NN2.png b/assets/rotation_prediction_NN2.png
diff --git a/assets/self_sup_seg.png b/assets/self_sup_seg.png
diff --git a/assets/self_supervised_perf1.png b/assets/self_supervised_perf1.png
diff --git a/assets/self_supervised_perf2.png b/assets/self_supervised_perf2.png
diff --git a/assets/semantic_seg_context.png b/assets/semantic_seg_context.png
diff --git a/assets/sfm_2view1.jpg b/assets/sfm_2view1.jpg
diff --git a/assets/sfm_2view2.jpg b/assets/sfm_2view2.jpg
diff --git a/assets/sfm_2view3.jpg b/assets/sfm_2view3.jpg
diff --git a/assets/sfm_ambiguity.jpg b/assets/sfm_ambiguity.jpg
diff --git a/assets/sfm_bundle1.jpg b/assets/sfm_bundle1.jpg
diff --git a/assets/sfm_gtsam1.png b/assets/sfm_gtsam1.png
diff --git a/assets/sfm_gtsam2.png b/assets/sfm_gtsam2.png
diff --git a/assets/sfm_intro.jpg b/assets/sfm_intro.jpg
diff --git a/assets/sfm_matopts.jpg b/assets/sfm_matopts.jpg
diff --git a/assets/sfm_mview1.jpg b/assets/sfm_mview1.jpg
diff --git a/assets/sfm_mview2.jpg b/assets/sfm_mview2.jpg
diff --git a/assets/sfm_mview3.jpg b/assets/sfm_mview3.jpg
diff --git a/assets/sfm_problems.jpg b/assets/sfm_problems.jpg
diff --git a/assets/sfm_process1.jpg b/assets/sfm_process1.jpg
diff --git a/assets/sfm_process2.jpg b/assets/sfm_process2.jpg
diff --git a/assets/sfm_process3.jpg b/assets/sfm_process3.jpg
diff --git a/assets/sfm_process4.jpg b/assets/sfm_process4.jpg
diff --git a/assets/sfm_process5.jpg b/assets/sfm_process5.jpg
diff --git a/assets/sfm_rec.jpg b/assets/sfm_rec.jpg
diff --git a/assets/sfm_rec2.jpg b/assets/sfm_rec2.jpg
diff --git a/assets/sfm_reprojerr.jpg b/assets/sfm_reprojerr.jpg
diff --git a/assets/sfm_tri5.jpg b/assets/sfm_tri5.jpg
diff --git a/assets/simclr.png b/assets/simclr.png
diff --git a/assets/simclr_NN1.png b/assets/simclr_NN1.png
diff --git a/assets/simclr_NN2.png b/assets/simclr_NN2.png
diff --git a/assets/simclr_anim.gif b/assets/simclr_anim.gif
diff --git a/assets/tut12_Beethoven.mat b/assets/tut12_Beethoven.mat
diff --git a/assets/tut12_Geometry-for-the-definition-of-the-BRDF.png b/assets/tut12_Geometry-for-the-definition-of-the-BRDF.png
diff --git a/assets/tut12_Lambert_Cosine_Law.png b/assets/tut12_Lambert_Cosine_Law.png
diff --git a/assets/tut12_ambig1.jpg b/assets/tut12_ambig1.jpg
diff --git a/assets/tut12_reflect_bet/tut_reflect_bet1.png b/assets/tut12_reflect_bet/tut_reflect_bet1.png
diff --git a/assets/tut12_reflect_bet/tut_reflect_bet2.png b/assets/tut12_reflect_bet/tut_reflect_bet2.png
diff --git a/assets/tut12_reflect_bet/tut_reflect_bet3.png b/assets/tut12_reflect_bet/tut_reflect_bet3.png
diff --git a/assets/tut12_reflect_bet_mask.png b/assets/tut12_reflect_bet_mask.png
diff --git a/assets/tut12_reflection_types.png b/assets/tut12_reflection_types.png
diff --git a/assets/tut12_reflectometry.png b/assets/tut12_reflectometry.png
diff --git a/assets/tut14_autoencoder1.jpg b/assets/tut14_autoencoder1.jpg
diff --git a/assets/tut14_autoencoder2.jpg b/assets/tut14_autoencoder2.jpg
diff --git a/assets/tut14_autoencoder3.jpg b/assets/tut14_autoencoder3.jpg
diff --git a/assets/tut14_autoencoder4.jpg b/assets/tut14_autoencoder4.jpg
diff --git a/assets/tut14_autoencoder5.jpg b/assets/tut14_autoencoder5.jpg
diff --git a/assets/tut14_ci_1.jpg b/assets/tut14_ci_1.jpg
diff --git a/assets/tut14_ci_2.jpg b/assets/tut14_ci_2.jpg
diff --git a/assets/tut14_cs_11.jpg b/assets/tut14_cs_11.jpg
diff --git a/assets/tut14_cs_6.jpg b/assets/tut14_cs_6.jpg
diff --git a/assets/tut14_cs_7.jpg b/assets/tut14_cs_7.jpg
diff --git a/assets/tut14_cs_8.jpg b/assets/tut14_cs_8.jpg
diff --git a/assets/tut14_cs_9.jpg b/assets/tut14_cs_9.jpg
diff --git a/assets/tut14_cv_pipe_12.jpg b/assets/tut14_cv_pipe_12.jpg
diff --git a/assets/tut14_cv_pipe_13.jpg b/assets/tut14_cv_pipe_13.jpg
diff --git a/assets/tut14_cv_pipe_14.jpg b/assets/tut14_cv_pipe_14.jpg
diff --git a/assets/tut14_diff_opt_1.jpg b/assets/tut14_diff_opt_1.jpg
diff --git a/assets/tut14_diff_opt_10.jpg b/assets/tut14_diff_opt_10.jpg
diff --git a/assets/tut14_diff_opt_11.jpg b/assets/tut14_diff_opt_11.jpg
diff --git a/assets/tut14_diff_opt_12.jpg b/assets/tut14_diff_opt_12.jpg
diff --git a/assets/tut14_diff_opt_14.jpg b/assets/tut14_diff_opt_14.jpg
diff --git a/assets/tut14_diff_opt_2.jpg b/assets/tut14_diff_opt_2.jpg
diff --git a/assets/tut14_diff_opt_3.jpg b/assets/tut14_diff_opt_3.jpg
diff --git a/assets/tut14_diff_opt_4.jpg b/assets/tut14_diff_opt_4.jpg
diff --git a/assets/tut14_diff_opt_5.jpg b/assets/tut14_diff_opt_5.jpg
diff --git a/assets/tut14_diff_opt_6.jpg b/assets/tut14_diff_opt_6.jpg
diff --git a/assets/tut14_diff_opt_7.jpg b/assets/tut14_diff_opt_7.jpg
diff --git a/assets/tut14_diff_opt_8.jpg b/assets/tut14_diff_opt_8.jpg
diff --git a/assets/tut_8_alignment4.hidden1.png b/assets/tut_8_alignment4.hidden1.png
diff --git a/assets/tut_8_alignment4.hidden2.png b/assets/tut_8_alignment4.hidden2.png
diff --git a/assets/tut_conv_ilv_22.PNG b/assets/tut_conv_ilv_22.PNG
diff --git a/assets/tut_objdet_rcnn-family-summary.png b/assets/tut_objdet_rcnn-family-summary.png
diff --git a/ee046746_tut_01-2_deep_learning_pytorch_basics.ipynb b/ee046746_tut_01-2_deep_learning_pytorch_basics.ipynb
@@ -10,7 +10,7 @@
    "source": [
     "# <img src=\"https://img.icons8.com/bubbles/100/000000/3d-glasses.png\" style=\"height:50px;display:inline\"> EE 046746 - Technion - Computer Vision\n",
     "---\n",
-    "#### Tal Daniel\n",
+    "#### <a href=\"https://taldatech.github.io/\">Tal Daniel</a> \n",
     "\n",
     "## Tutorial 1.5 - Deep Learning - PyTorch Basics\n",
     "---\n",
@@ -830,7 +830,7 @@
    "source": [
     "## <img src=\"https://img.icons8.com/dusk/64/000000/prize.png\" style=\"height:50px;display:inline\"> Credits\n",
     "---\n",
-    "\n",
+    "* EE 046746 Spring 21 - <a href=\"https://taldatech.github.io/\">Tal Daniel</a> \n",
     "* Icons from <a href=\"https://icons8.com/\">Icon8.com</a> - https://icons8.com"
    ]
   }
@@ -851,7 +851,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.9"
+   "version": "3.6.15"
   }
  },
  "nbformat": 4,

diff --git a/ee046746_tut_01_intro_image_processing_python.ipynb b/ee046746_tut_01_intro_image_processing_python.ipynb
@@ -10,7 +10,7 @@
    "source": [
     "# <img src=\"https://img.icons8.com/bubbles/100/000000/3d-glasses.png\" style=\"height:50px;display:inline\"> EE 046746 - Technion - Computer Vision\n",
     "----\n",
-    "#### Tal Daniel\n",
+    "#### <a href=\"https://taldatech.github.io/\">Tal Daniel</a> \n",
     "\n",
     "## Tutorial 01 - Python & Image Processing\n",
     "---\n",
@@ -2255,6 +2255,7 @@
    "source": [
     "## <img src=\"https://img.icons8.com/dusk/64/000000/prize.png\" style=\"height:50px;display:inline\"> Credits\n",
     "---\n",
+    "* EE 046746 Spring 21 - <a href=\"https://taldatech.github.io/\">Tal Daniel</a> \n",
     "* 6.819/6.869: Advances in Computer Vision, MIT CSAIL, Julie Ganeshan (MIT).\n",
     "* <a href=\"http://cs231n.github.io/python-numpy-tutorial/\">Python Numpy Tutorial</a> - CS231n Convolutional Neural Networks for Visual Recognition, Justin Johnson.\n",
     "* <a href=\"https://github.com/piratefsh/image-processing-101\"> Image Processing 101 </a>\n",
@@ -2278,7 +2279,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.10"
+   "version": "3.6.15"
   }
  },
  "nbformat": 4,