Differences

This shows you the differences between two versions of the page.

--- eman2:e2tomo_more [2025/06/19 01:22] – created steveludtke
+++ eman2:e2tomo_more [2025/08/05 02:17] (current) – steveludtke
@@ Line 22: / Line 22: @@
 ===== Automated particle selection =====
-A new tool (post 2.91) is implemented for CNN guided automated particle selection from tomograms. The concept is similar to the tomogram segmentation protocol, but a number of changes have been made to improve the accuracy and throughput of the process. A new GUI has been made to simplify the training process. Note that this requires a CUDA compatible GPU and tensorflow setup to work. To use see //Subtomogram Averaging -> Convnet based auto-boxing// or manually run
+A new tool (post 2.91) is implemented for CNN guided automated particle selection from tomograms. The concept is similar to the tomogram segmentation protocol, but a number of changes have been made to improve the accuracy and throughput of the process. A new GUI has been made to simplify the training process. Note that this requires a CUDA compatible GPU and tensorflow setup to work.
+In the GUI: //Subtomogram Averaging -> Convnet based auto-boxing// or you can manually run
  <code>
  e2spt_boxer_convnet.py --label xxx
 </code>
 Here **label** will be the label of the newly selected particle. This will bring up three windows: the main window with various options and a list of tomograms, and two windows (should be empty in the beginning) for positive and negative samples. Clicking any tomogram in the list will bring up two other windows: the slice view of the tomogram and the list of particles under the given label. Here is a simple workflow.
@@ Line 36: / Line 39: @@
 . Go through all tomograms in the list and apply the network to select the particles. These particles can be viewed and modified in //e2spt_boxer.py//, and extracted through the particle extraction steps of the main workflow.
- {{http://blake.bcm.edu/dl/EMAN2/sptboxer_convnet.png| Automated particle selection |width=600}}
+ {{https://blake.bcm.edu/dl/EMAN2/sptboxer_convnet.png}}
 Description of items on the GUI:
   * **New/Save/Load**: Initialize a new CNN / save the current trained network to disk / load a trained network from disk.
-  * **!ChangeBx** : Change the box size of positive/negative samples. Ideally, the particles should be recognizable visually from the reference images. The process can be slow if the references come from multiple tomograms.
+  * **ChangeBx** : Change the box size of positive/negative samples. Ideally, the particles should be recognizable visually from the reference images. The process can be slow if the references come from multiple tomograms.
   * **Reference/Particle** selection box: Display circles of references or particles in the tomogram slice view.
-  * **!TargetSize** : This controls the size of target area used for CNN training. i.e. particles should be centered in this region in positive samples, and there should not be particle features in this region in negative samples. The region is defined as a Gaussian function and value here is the sigma of the Gaussian.
+  * **TargetSize** : This controls the size of target area used for CNN training. i.e. particles should be centered in this region in positive samples, and there should not be particle features in this region in negative samples. The region is defined as a Gaussian function and value here is the sigma of the Gaussian.
   * **Learnrate** : Learning rate for the CNN training. Normally no need to change this...
-  * **!PtclThresh** : The intensity threshold in the neural network output to be recognized as a particle. The target of positive samples should be 1 and negative samples should be 0.
+  * **PtclThresh** : The intensity threshold in the neural network output to be recognized as a particle. The target of positive samples should be 1 and negative samples should be 0.
-  * **!CircleSize** : The radius of circles in pixels on the tomogram slice view. This also controls the closest distance between particles.
+  * **CircleSize** : The radius of circles in pixels on the tomogram slice view. This also controls the closest distance between particles.
   * **Sum/Max** selection box : Choose between different modes of the loss function. **Sum** is used for globular particles that are generally confined in the target area. In **Max** mode, the CNN only assume there are particle features that exist within the region. It is harder to train than the **Sum** mode, but allows particles of irregular shapes, such as protein fibers.