auto2d_tutorial

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
auto2d_tutorial [2019/07/10 13:43]
twagner [Classify]
auto2d_tutorial [2019/07/10 13:46] (current)
twagner [Classify]
Line 39: Line 39:
   * **learning_rate**:​ Defines the step size during training. Default should be kept.   * **learning_rate**:​ Defines the step size during training. Default should be kept.
   * **nb_epoch**:​ Maximum number of epochs the network will train. It might not reach this number, as Cinderella stops training if it recognize that the validation loss is not improving anymore.   * **nb_epoch**:​ Maximum number of epochs the network will train. It might not reach this number, as Cinderella stops training if it recognize that the validation loss is not improving anymore.
-  * **nb_early_stop**:​ +  * **nb_early_stop**: ​If the validation loss did not improve that number in a row, it will stop training. 
-  * **train_valid_thresh**:​ +  * **train_valid_thresh**: ​Fraction of images that are used for training from each stack file. The remaining images are used for validation. 
-  * **max_valid_img_per_file**:​+  * **max_valid_img_per_file**: ​Maximum number of validation images per stack file that should be used. -1 means that it is not used.
  
 Copy this into a new file called ''​config.json''​. During classification,​ the options in the "​train"​ section are ignored. Copy this into a new file called ''​config.json''​. During classification,​ the options in the "​train"​ section are ignored.
  • auto2d_tutorial.txt
  • Last modified: 2019/07/10 13:46
  • by twagner