2_Image Classification.pdf
0 likes63 views
This document provides a summary of image classification using deep learning. It begins with an introduction to the speaker and their background. It then discusses key concepts in image classification like image types (e.g. raster, vector), feature extraction using convolutional and pooling layers, classification using dense layers and activation functions, and model training. It provides examples of datasets like cats vs dogs and how to balance classes. Finally, it discusses model saving, transformers, and provides homework on modifying the image classification code.
![Vector/ Raster image
• Input image: bitmap(raster)/ vector images
• Channels: RGB: black[0,0,0] - white[255,255,255]; gray[0-255]
32](https://image.slidesharecdn.com/2imageclassification-220609070802-1d9a68a7/85/2_Image-Classification-pdf-32-320.jpg)
![Hint
• one-hot-encoded for the label/classes like [0, 0, 0, 0, 0, 0, 1]
• categorical_crossentropy
• sparse label/classes like [1, 2, 3, 4, 5, 6, 7]
• sparse_categorical_crossentropy
55](https://image.slidesharecdn.com/2imageclassification-220609070802-1d9a68a7/85/2_Image-Classification-pdf-55-320.jpg)
2_Image Classification.pdf
- 1. 國立臺北護理健康大學 NTUNHS Image Classification Orozco Hsu 2022-03-28 1
- 2. About me • Education • NCU (MIS)、NCCU (CS) • Work Experience • Telecom big data Innovation • AI projects • Retail marketing technology • User Group • TW Spark User Group • TW Hadoop User Group • Taiwan Data Engineer Association Director • Research • Big Data/ ML/ AIOT/ AI Columnist 2
- 3. Tutorial Content 3 Image in AI process types Overall technologies Homework Deep Learning history timeline Exercise in image classification
- 4. Code • Download code • https://github.com/orozcohsu/ntunhs_2022_01.git • Folder/file • 20220328_inter_master/run.ipynb 4
- 5. Code 5 Click button Open it with Colab Copy it to your google drive Check your google drive
- 6. Deep Learning history timeline • From 1943-2019 6 Ref: https://machinelearningknowledge.ai/brief-history-of-deep-learning/
- 7. Deep Learning history timeline • 2018 Turing Award • Bengio, Hinton, and LeCun, are sometimes referred to as the "Godfathers of AI" and "Godfathers of Deep Learning 7 Ref: https://awards.acm.org/about/2018-turing
- 8. Deep Learning history timeline • ImageNet dataset • Over 15 million images with more than 22,000 categories • ILSVRC 8 Ref: https://image-net.org/about.php Ref: https://www.cs.princeton.edu/courses/archiv e/spr18/cos598B/slides/cos598b_7feb18_ima genet.pdf
- 9. Deep Learning history timeline • ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 9 Ref: https://medium.com/nanonets/how-to-automate-surveillance-with-deep-learning-c8dea1d6387f Ref: https://image-net.org/index.php
- 10. Deep Learning history timeline • Object detection 10 val top-1: Probability of predicting only once and being error val top-5: Predict five times, as long as one guess is error, the probability of being error
- 11. Deep Learning history timeline • Object localization 11
- 12. Deep Learning history timeline • Object detection from video • IoU (Intersection over Union) • IoU > 0.5 (we set it as TP) • IoU < 0.5 (we set it as FP) 12
- 13. More 13 Ref: https://chih-sheng-huang821.medium.com/%E6%B7%B1%E5%BA%A6%E5%AD%B8%E7%BF%92%E7%B3%BB%E5%88%97- %E4%BB%80%E9%BA%BC%E6%98%AFap-map-aaf089920848 Precision = TP/(TP + FP) Recall = TP/(TP + FN)
- 14. More • AP (Average Precision): used to object detection • mAP (more Average Precision): more objects detection 14 precision-recall curve AP = area under curve, AUC IS dog possibility Precision:3/4 =0.75 Recall:3/8= 0.375 Precision:5/10 =0.5 Recall:5/8= 0.625
- 15. Deep Learning history timeline • CS231n: • Convolutional Neural Networks for Visual Recognition 15 Ref: http://cs231n.stanford.edu/index.html
- 16. More • How to Automate Surveillance with Deep Learning? 16 Ref: https://medium.com/nanonets/how-to-automate-surveillance-with-deep-learning-c8dea1d6387f
- 17. Image for deep learning process flow 17 Ref: https://www.aldec.com/en/solutions/embedded/deep-learning-using-fpga
- 18. Main type of AI image recognition • Image classification • Image detection • Image segmentation 18 Can you tell the difference?
- 23. More • Object Detection Raspberry Pi using OpenCV • Online computer vision courses 23 Ref: https://www.youtube.com/watch?v=Vg9rrOFmwHo Ref: https://www.computervision.zone/course-list/ Ref: https://www.youtube.com/watch?v=46TBBb5rAy4 Ref: https://circuitdigest.com/microcontroller-projects/license-plate-recognition-using-raspberry-pi-and- opencv
- 24. The input is fed to the network of stacked Conv, Pool and Dense layers 24 Ref: https://learnopencv.com/image-classification-using-convolutional-neural-networks-in-keras/ Output can be a Softmax layer indication
- 26. More 26
- 27. 27
- 30. Grey images 30 Support format: jpeg, png, bmp, gif
- 31. Raster image 31
- 32. Vector/ Raster image • Input image: bitmap(raster)/ vector images • Channels: RGB: black[0,0,0] - white[255,255,255]; gray[0-255] 32
- 33. Improving model prediction accuracy • Different geometric transformations 33 Ref: https://medium.com/analytics-vidhya/data-augmentation-is-it-really-necessary-b3cb12ab3c3f
- 34. Feature extractor • Kernel map: image edge-detection, sharpen… called image Filters • Convolutional: Convolutional and pooling layers which act as the feature extractor • Feature maps: The output of kernel map process 34 Feature maps1 Feature maps2
- 37. More • What if you want the feature map to be of the same size as the input image? Using zero padding on it. 37 Ref: https://towardsdatascience.com/convolution-neural-networks-a-beginners-guide-implementing-a-mnist-hand-written-digit-8aa60330d022
- 38. feature extractor • Pooling • Max • Average 38 Ref: https://www.researchgate.net/figure/Toy-example-illustrating-the-drawbacks-of- max-pooling-and-average-pooling_fig2_300020038
- 39. Feature extractor • Spatial Contextual Module (pixel wise) 39 Ref: https://www.researchgate.net/figure/The-sum-pooling-strategy-for-feature-maps-in-a-convolutional-layer-a-Input-cloud-image_fig2_323433191
- 40. Classifier • Flatten Layer • It is used to convert the data into 1D arrays to create a single feature vector. After flattening we forward the data to a fully connected layer for final classification 40 Ref: https://data-flair.training/blogs/keras-convolution-neural-network/
- 41. Classifier • Dense Layer • It is a fully connected layer. Each node in this layer is connected to the previous layer • This layer is used at the final stage of CNN to perform classification 41 Ref: https://data-flair.training/blogs/keras-convolution-neural-network/
- 43. Classifier • Activation function • It enables neural networks to become non-linear • It has two main roles • One is the function itself involving in feed forward step • Two is the derivative of the function involving in backpropagation step • You can think feed forward as prediction and backpropagation as training or learning 43 Ref: https://sefiks.com/2020/02/02/dance-moves-of-deep-learning-activation-functions/
- 44. Classifier • Dropout Layer • It is used to prevent the network from overfitting 44 Ref: https://data-flair.training/blogs/keras-convolution-neural-network/
- 45. Keras framework • Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. • It was developed with a focus on enabling fast experimentation • Integrates with TensorFlow2 • Efficiently executing low-level tensor operations on CPU, GPU, or TPU • Faster developing for deep-learning networks • Provides FULL Connection, Convolutional, Pooling, RNN, LSTM… • The latest version: 2.8 (2022-02-03) 45 Ref: https://keras.io/about/
- 46. Dog and cat image dataset • This example shows how to do image classification from scratch, starting from JPEG image files on disk, without leveraging pre-trained weights or a pre-made Keras Application model • We demonstrate the workflow on Cats vs Dogs binary classification dataset 46 What is the pre-trained weights?
- 47. Dog and cat image dataset • Cat and Dog: 23,422 images • Training: 18,738 images • Validation: 4,684 images • Image size are not fixed! • 350X320 • 448X329 • … • … 47
- 48. More • Data imbalance • If a dataset consists of 100 cat and 900 dog images. If we train the neural network on this data, it will just learn to predict dog every time • In this case, we can easily balance the data using sampling techniques • Down-sampling • By removing some dog examples • Up-sampling • By creating more cat examples using image augmentation or any other method 48 Ref: Multi-Label Image Classification with Neural Network | Keras | by Shiva Verma | Towards Data Science
- 49. Dog and cat image dataset • Network Calculator 49 Ref: https://madebyollin.github.io/convnet-calculator/
- 50. Dog and cat image dataset • epochs = 50 50 …
- 51. More • Install the conda package if it happens to error 51 !conda uninstall pydot !conda uninstall pydotplus !conda uninstall graphviz !conda install pydot !conda install pydotplus Graphviz is open source graph visualization software. Graph visualization is a way of representing structural information as diagrams of abstract graphs and networks. https://graphviz.org
- 52. More • Model progress can be saved during and after training. This means a model can resume where it left off and avoid long training times. Saving also means you can share your model and others can recreate your work • https://www.tensorflow.org/tutorials/keras/save_and_load 52
- 53. More • Transformer model (Transformers Replace CNNs, RNNs) 53 Ref: https://blogs.nvidia.com/blog/2022/03/25/what-is-a-transformer-model/
- 54. Homework • Try to reduce the Cat and Dog images to 500 separately, and check the result of performance. • Try to add additional bird images as the third image label • Download the bird images • https://drive.google.com/file/d/1NgmjVrRug_qPqlfU_Zb2O- kyd5Hblaat/view?usp=sharing • Modify the code, build the model to multi-class prediction 54
- 55. Hint • one-hot-encoded for the label/classes like [0, 0, 0, 0, 0, 0, 1] • categorical_crossentropy • sparse label/classes like [1, 2, 3, 4, 5, 6, 7] • sparse_categorical_crossentropy 55