User Tools

Site Tools


pipeline:window:cryolo:picking_general_refine

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Next revision Both sides next revision
pipeline:window:cryolo:picking_general_refine [2019/09/18 12:53]
twagner [Picking particles - Using the general model refined for your data]
pipeline:window:cryolo:picking_general_refine [2019/12/02 16:28]
twagner [Picking particles - Using the general model refined for your data]
Line 13: Line 13:
   - The training will need less GPU memory ((We are testing crYOLO with its default configuration on graphic cards with >= 8 GB memory. Using the fine tune mode, it should also work with GPUs with 4 GB memory)) and therefore is usable with NVIDIA cards with less memory.    - The training will need less GPU memory ((We are testing crYOLO with its default configuration on graphic cards with >= 8 GB memory. Using the fine tune mode, it should also work with GPUs with 4 GB memory)) and therefore is usable with NVIDIA cards with less memory. 
    
-However, the fine tune mode is still somewhat experimental and we will update this section as crYOLO develops over time. +<note important> 
 +The fine tune mode is still somewhat experimental and we will update this section as crYOLO develops over time. 
 +</note>
 If you followed the installation instructions, you now have to activate the cryolo virtual environment with If you followed the installation instructions, you now have to activate the cryolo virtual environment with
  
Line 39: Line 40:
 </html> </html>
  
-<hidden **Create the configuration file using the command line:**>+<html> 
 +<div style="background-color: LightCyan ; padding: 10px; border: 1px solid Black;">  
 +<b>Alternative: Create the configuration file using the command line</b> 
 +</div> 
 +</html> 
 +<hidden>
  
 I assume your box files for training are in the folder ''train_annotation'' and the corresponding images in ''train_image''. I furthermore assume that your box size in your box files is 160 and the model you want to refine is ''gmodel_phosnet_20190516.h5''. To create the config config_cryolo.json simply run: I assume your box files for training are in the folder ''train_annotation'' and the corresponding images in ''train_image''. I furthermore assume that your box size in your box files is 160 and the model you want to refine is ''gmodel_phosnet_20190516.h5''. To create the config config_cryolo.json simply run:
  
 <code> <code>
-cryoloo.py config config_cryolo.json 160 --train_image_folder train_image --train_annot_folder train_annot --pretrained_weights gmodel_phosnet_20190516.h5+cryolo_gui.py config config_cryolo.json 160 --train_image_folder train_image --train_annot_folder train_annot --pretrained_weights gmodel_phosnet_20190516.h5
 </code> </code>
  
 To get a full description of all available options type: To get a full description of all available options type:
 <code> <code>
-cryoloo.py config -h+cryolo_gui.py config -h
 </code> </code>
  
Line 55: Line 61:
  
 <code> <code>
-cryoloo.py config config_cryolo.json 160 --train_image_folder train_image --train_annot_folder train_annot --pretrained_weights gmodel_phosnet_20190516.h5 --valid_image_folder valid_img --valid_annot_folder valid_annot +cryolo_gui.py config config_cryolo.json 160 --train_image_folder train_image --train_annot_folder train_annot --pretrained_weights gmodel_phosnet_20190516.h5 --valid_image_folder valid_img --valid_annot_folder valid_annot 
 </code> </code>
  
 </hidden> </hidden>
 +<html> 
 +<div style="background-color: LightCyan ; padding: 10px; border: 1px solid Black;">  
 +<b> </b> 
 +</div> 
 +</html>
 ==== 4. Training ==== ==== 4. Training ====
  
Line 95: Line 105:
 </html> </html>
  
- +<html> 
-<hidden **Alternative:** Run training with the command line>+<div style="background-color: LightCyan ; padding: 10px; border: 1px solid Black;">  
 +<b>Alternative: Run training with the command line</b> 
 +</div> 
 +</html> 
 +<hidden>
 In comparison to the training from scratch, you can skip the warm up training ( -w 0 ). Moreover you have to add the //%%--%%fine_tune// flag to tell crYOLO that it should do fine tuning. You can also tell crYOLO how many layers it should fine tune (default is two layers with -lft 2 ): In comparison to the training from scratch, you can skip the warm up training ( -w 0 ). Moreover you have to add the //%%--%%fine_tune// flag to tell crYOLO that it should do fine tuning. You can also tell crYOLO how many layers it should fine tune (default is two layers with -lft 2 ):
  
Line 103: Line 117:
 </code> </code>
 </hidden> </hidden>
 +<html> 
 +<div style="background-color: LightCyan ; padding: 10px; border: 1px solid Black;">  
 +<b> </b> 
 +</div> 
 +</html>
 ==== 5. Picking ==== ==== 5. Picking ====
 {{page>pipeline:window:cryolo:picking}} {{page>pipeline:window:cryolo:picking}}
pipeline/window/cryolo/picking_general_refine.txt · Last modified: 2020/06/05 09:05 by twagner