Turi Create and Concept Behind Image Classification

CocoaHead Berlin

Transcript

1. TURI CREATE CONCEPT BEHIND IMAGE CLASSIFICATION
2. WHAT WE WANT TO ACHIEVE?
5. CORE ML
6. INFERENCE
8. FROM WHERE WE GET THE CORE ML FORMAT MODELS?
9. > Apple ready-to-use Core ML Models.
10. > Apple tool (Python Package) to convert known model formats to Core ML model format. That is covered in that blog post
11. import coremltools caffe_model = ('EmotiW_VGG_S.caffemodel', 'deploy.prototxt') labels = 'labels.txt' coreml_model = coremltools.converters.caffe.convert(caffe_model, class_labels=labels, image_input_names='data') coreml_model.save('EmotiW_VGG_S.mlmodel')
12. WHAT IS A MODEL?
13. TRAINING
14. TURI CREATE
15. > Under the hood of Turi Create is Apache’s MXNet > Python 2.7, 3.5, 3.6 conda create -n turi python=3.6 source activate turi pip install -U turicreate import turicreate fails on macOS 10.12.6 conda create -n turi python=2.7 pip install -Iv turicreate==4.0
16. CONVOLUTIONAL NEURAL NETWORKS CNN MODEL Feature extraction part + Classification part
24. VISUALIZING FEATURE / ACTIVATION MAPS
25. TRANSFER LEARNING
27. CREATE AND TRAIN A MODEL USING TURI CREATE
28. SQUEEZENET_V1.1
34. 15 min.
35. 44 min.
36. ResNet50
37. 9 min.
38. 17 min.
39. 66 min.
40. IMAGE AUGMENTATION Invariant Representation Scale Rotation Translation
42. RESOURCES CODE Turi Create Sample Code and Demo Apps
43. RESOURCES TOOLS Turi Create Anaconda Miniconda
44. RESOURCES APPLE Turi Create User Guide Turi Create API Documentation Sample Code: Classifying Images with Vision and Core ML Apple Machine Learning
45. RESOURCES ARTICLES Convolutional Neural Networks Image Augmentation in Keras
46. RESOURCES PHOTOS Photo by Gift Habeshaw on Unsplash Elon Musk SpaceX launch footage
47. THANK YOU ❤ @_MeroCode_ LET’S LEARN ABOUT MACHINE LEARNING.