Differences

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

--- pipeline:window:cryolo:picking_general_refine [2019/09/17 15:40]
twagner [Configuration]
+++ pipeline:window:cryolo:picking_general_refine [2019/09/17 17:38]
shaikh [Picking particles - Using the general model refined for your data]
@@ Line 6: / Line 6: @@
 What does //fine-tuning// mean?
-The general model was trained on a lot of particles with a variety of shapes and therefore learned a very good set of generic features. The last layers, however, learn a pretty abstract representation of the particles and it might be that they do not perfectly fit for your particle at hand. Fine-tuning only traines the last two convolutional layers, but keep the others fixed. This adjusts the more abstract representation for your specific problem.
+The general model was trained on a lot of particles with a variety of shapes and therefore learned a very good set of generic features. The last layers, however, learn a fairly abstract representation of the particles and it might be that they do not perfectly fit for your particle at hand. Fine-tuning only trains the last two convolutional layers, but keeps the others fixed. This adjusts the more abstract representation for your specific problem.
 Why should I //fine-tune// my model instead of training from scratch?
@@ Line 21: / Line 21: @@
 </code>
-==== Data preparation ====
+==== 1. Data preparation ====
 {{page>pipeline:window:cryolo:data_preparation}}
-==== Start crYOLO ====
+==== 2. Start crYOLO ====
 {{page>pipeline:window:cryolo:start_cryolo}}
-==== Configuration ====
+==== 3. Configuration ====
 {{page>pipeline:window:cryolo:configuration}}
@@ Line 60: / Line 60: @@
 </hidden>
-==== Training ====
+==== 4. Training ====
 Now you are ready to train the model. In case you have multiple GPUs, you should first select a free GPU. The following command will show the status of all GPUs:
@@ Line 86: / Line 86: @@
 The fine tune mode is especially useful if you want to [[downloads:cryolo_1#run_it_on_the_cpu|train crYOLO on the CPU]]. On my local machine it reduced the time for training cryolo on 14 micrographs from 12-15 hours to 4-5 hours.
 </note>
+<html>
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
+<b>&#9658; You can now press the [Start] button to start training.  </b>
+</div>
+</html>
 <hidden **Run training with the command line**>
@@ Line 95: / Line 102: @@
 </hidden>
-==== Picking ====
+==== 5. Picking ====
 {{page>pipeline:window:cryolo:picking}}
-==== Visualize the results ====
+==== 6. Visualize the results ====
 {{page>pipeline:window:cryolo:visualize}}
-==== Evaluate your results ====
+==== 7. Evaluate your results ====
 {{page>pipeline:window:cryolo:evaluate_results}}

User Tools

Site Tools

Differences

Page Tools