Содержание
- 2. Deep Learning on large images Cat? (0/1) 64x64
- 3. Computer Vision Problem vertical edges horizontal edges
- 4. Vertical edge detection 1 1 1 -1 -1 -1 0 0 0 1 1 1 -1
- 5. Vertical edge detection examples
- 6. Valid and Same convolutions “Valid”: “Same”: Pad so that output size is the same as the
- 7. Summary of convolutions padding p stride s
- 8. Multiple filters 6 x 6 x 3 4 x 4 3 x 3 x 3 3
- 9. Pooling layer: Max pooling
- 10. Pooling layer: Average pooling
- 11. Types of layer in a convolutional network: - Convolution - Pooling - Fully connected
- 12. Outline Classic networks: LeNet-5 ResNet Inception AlexNet VGG
- 13. LeNet - 5 120 84 f = 2 s = 2 avg pool avg pool f
- 14. AlexNet = 9216 4096 4096 MAX-POOL MAX-POOL 3 3 MAX-POOL Softmax 1000 [Krizhevsky et al., 2012.
- 15. VGG - 16 224x224x 3 CONV = 33 filter, s = 1, same POOL [CONV 128]
- 16. Inception network [Szegedy et al., 2014, Going Deeper with Convolutions]
- 17. What are localization and detection? Image classification Classification with localization Detection
- 18. Classification with localization 1 - pedestrian 2 - car 3 - motorcycle 4 - background
- 19. Defining the target label y 1 - pedestrian 2 - car 3 - motorcycle 4 -
- 20. Sliding windows detection
- 21. Evaluating object localization “Correct” if IoU 0.5 More generally, IoU is a measure of the overlap
- 22. Non-max suppression example
- 23. Non-max suppression algorithm Discard all boxes with While there are any remaining boxes: Pick the box
- 24. Non-max suppression example 0.8 0.7 0.6 0.9 0.7
- 26. Скачать презентацию