Differences

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

--- auto2d_tutorial [2019/05/29 09:45]
twagner [Classify]
+++ auto2d_tutorial [2019/08/15 15:35]
twagner [Classify]
@@ Line 23: / Line 23: @@
 		"learning_rate": 1e-4,
 		"nb_epoch": 100,
-		"nb_early_stop": 5
+		"nb_early_stop": 5,
+                "train_valid_thresh":   0.8,
+                "max_valid_img_per_file": -1
 	}
 }
 </code>
+The fields have the following meaning:
+  * **input_size**: Size to which the classes are internally downsampled.
+  * **batch_size**: Number images that used in in one batch during training.
+  * **good_classes**: Path to folder with good classes saved as stacks in .mrc or .hdf format
+  * **bad_classes**: Path to folder with bad classes saved as stacks in .mrc or .hdf format
+  * **pretrained_weights**: Path to a model that should be used to initialize the training.
+  * **saved_weights_name**: Everytime the network improves in terms of validation loss, it will save the model into the file specified here.
+  * **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_early_stop**: If the validation loss did not improve that number in a row, it will stop training.
+  * **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**: 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.
@@ Line 35: / Line 50: @@
 <code>
-sp_cinderella_predict.py -i path/to/classes_after_isac.hdf -w model.h5 -o output_folder/ -c config.json -t 0.7 --gpu 1
+sp_cinderella_predict.py -i path/to/classes_after_isac.hdf -w model.h5 -o output_folder/ -t 0.7 --gpu 1
 </code>
@@ Line 60: / Line 75: @@
 		"learning_rate": 1e-4,
 		"nb_epoch": 100,
-		"nb_early_stop": 5
+		"nb_early_stop": 15
 	}
 }

User Tools

Site Tools

Differences

Page Tools