Machine Learning without PhD :)

Байрам Аннаков @ MoscowPython Meetup 49

"Расскажем и покажем, как обучать машины и нейросети для решения простых и не очень задач классификации и распознавания".

Видео: http://www.moscowpython.ru/meetup/49/ml-no-phd/

Transcript

1. Machine Learning without PHD App in the Air
2. It all started with…
3. How? Reproduce the same in Python Train your own model
4. Reproduce
5. ImageNet
7. Recognize image from keras.applications.resnet50 import ResNet50 from keras.preprocessing import image from keras.applications.resnet50 import preprocess_input, decode_predictions import numpy as np model = ResNet50(weights='imagenet')
8. Recognize image img_path = 'elephant.jpg' img = image.load_img(img_path, target_size=(224, 224)) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x)
9. Recognize image preds = model.predict(x) # decode the results into a list of tuples (class, description, probability) # (one such list for each sample in the batch) print('Predicted:', decode_predictions(preds, top=3)[0]) # Predicted: [(u'n02504013', u'Indian_elephant', 0.82658225), (u'n01871265', u'tusker', 0.1122357), (u'n02504458', u'African_elephant', 0.061040461)]
10. CNN
12. Train your own
13. https:/ /blog.keras.io/
14. 72%
15. VGG16
16. +2 months —> 90% GPU!! Re-training more layers Different architecture Data augmentation Dropout
17. 2 internal seminars
18. Passport Scanner 87% Rhythmic Gymnastics 98,9%
19. Rhythmic Gymnastics
20. Approach • Collect data
 Simple iPhone app that helps draw and export • Prepare data
 Image = Grid. Each cell = 1 (black) or 0 (white)
 Convert Grid to Line
 Image = 000100011000011100011… • Train + Analyze
 Until satisfied with the score
22. Prepare data import skimage
 import numpy
23. Train and Analyze 1. K-neighbors 78% from sklearn.neighbors import KNeighborsClassifier clf = KNeighborsClassifier(n_neighbors=1) clf.fit(x_train, y_train) clf.score(x_test, y_test)
24. Train and Analyze 2. K-neighbors + PCA 81% from sklearn.decomposition import PCA pca = PCA(n_components=40, whiten=True) pca.fit(x_train) x_train_pca = pca.transform(x_train) x_test_pca = pca.transform(x_test) //repeat KNN
25. May be someone has already solved it?
26. MNIST http://yann.lecun.com/exdb/mnist/
27. 3. SVM 90% from sklearn import svm classifier = svm.SVC(gamma=0.001) classifier.fit(x_train, y_train) predicted = classifier.predict(x_test)
28. Passport OCR Data char74 icdar2003 Architecture Modified MNIST
29. http:/ /course.fast.ai
30. python@appintheair.mobi