This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
cryolo_nets [2018/12/18 15:16] twagner [Introduction] |
cryolo_nets [2019/04/26 22:07] twagner [Network #3 PhosaurusNet] |
||
---|---|---|---|
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. | ||
Line 107: | Line 107: | ||
==== Network #3 PhosaurusNet ==== | ==== Network #3 PhosaurusNet ==== | ||
- | At some point, we realized that the patch mode introduced a problem on images | + | At some point, we realized that the patch mode introduced a problem on images with particles on the carbon |
{{ : | {{ : | ||
- | We recommend to use this network for single particle | + | We recommend to use this network for picking |