This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | Last revision Both sides next revision | ||
cryolo_nets [2018/12/21 15:16] twagner [Network #3 PhosaurusNet] |
cryolo_nets [2018/12/24 10:15] twagner [Introduction] |
||
---|---|---|---|
Line 6: | Line 6: | ||
The main components are **convolutional operations** and **max pooling operations**: | The main components are **convolutional operations** and **max pooling operations**: | ||
- | * Convolutional layer: A convolutional learn local patterns. For 2D images, these are patterns in small region | + | * Convolutional layer: A convolutional learn local patterns. For 2D images, these are patterns in a small region of the input image. In the YOLO architecture, |
* Max-pooling operation: Max-pooling operations downsampling the feature maps of previous layers. This enables the following convolutional layers to see a larger extends of the input image. | * Max-pooling operation: Max-pooling operations downsampling the feature maps of previous layers. This enables the following convolutional layers to see a larger extends of the input image. | ||
Another characteristic of this architecture is the passthrough connection between 13 and 21. it helps the network to utilize low level features during detection. | Another characteristic of this architecture is the passthrough connection between 13 and 21. it helps the network to utilize low level features during detection. |