Differences

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

--- cinderella_micrographs [2019/12/10 08:51]
twagner
+++ cinderella_micrographs [2020/08/28 07:35]
twagner [Training]
@@ Line 1: / Line 1: @@
 ====== How to use SPHIRE's Cinderella for micrograph selection ======
-This tutorial describes how to use Cinderella to sort micrographs. Unfortunately, we cannot provide a pretrained model yet. Therefore the first step is to train a model (see section //Training//) and to apply a model (see section //Classify//)
+This tutorial describes how to use Cinderella to sort micrographs. Unfortunately, we cannot provide a pretrained model yet. Therefore the first step is to train a model (see section //Training//) and to apply a model (see section //Classify//).
@@ Line 10: / Line 10: @@
 ==== Training ====
+The first step is to train Cinderella with manually selected good and bad micrographs. Create two folders, one containing manually selected good micrographs (e.g ''GOOD_MICS/'') and one contain bad micrographs (e.g ''BAD_MICS/''). Both folders can contain subfolders.
+<note question>
+**How many micrographs do I need?**
+We typically start with 30 good and 30 bad micrographs.
+</note>
+Then specify the paths into a config file like this:
+<code json config.json>
+{
+	"model": {
+		"input_size": [512,512]
+	},
+	"train": {
+		"batch_size": 6,
+		"good_path": "GOOD_MICS/",
+		"bad_path": "BAD_MICS/",
+		"pretrained_weights": "",
+		"saved_weights_name": "my_model.h5",
+		"learning_rate": 1e-4,
+		"nb_epoch": 100,
+		"nb_early_stop": 15
+	}
+}
+</code>
+The fields in the section **model** have the following meaning:
+  * **input_size**: This is the image size to which each micrograph is resized to.
+  * **mask_radius**: (Optional) Circular mask radius which is applied after resizing to the input size. If not given, it uses 0.4 * **input_size** as default.
+The fields in the section **train** have the following meaning:
+  * **batch_size**: How many micrographs are in one mini-batch. If you have memory problems, you can try to reduce this value.
+  * **good_path**: Path to folder with good micrographs.
+  * **bad_path**: Path to folder with bad micrographs.
+  * **pretrained_weights**: Path to weights that are used to initialize the network. It can be empty. As Cinderella is using the same network architecture as crYOLO, we are typically using the [[downloads:cryolo_1#general_phosaurusnet_models|general network of crYOLO]] as pretrained weights.
+  * **saved_weights_name**: Final model filename
+  * **learning_rate**: Learning rate, should not be changed.
+  * **nb_epoch**: Maximum number of epochs to train. However, it will stop earlier (see nb_early_stop).
+  * **nb_early_stop**: If the validation loss did not improve "nb_early_stop" times in a row, the training will stop automatically.
+The next step is to run the training:
+<code>
+sp_cinderella_train.py -c example_config.json --gpu 1
+</code>
+This will train a classification network on the GPU with ID=1. After the training finishes, you get a ''my_model.h5'' file. This can then be used to classfiy micrographs into good / bad categories.
 ==== Classify ====
+Suppose you want to separate good and bad micrographs in the folder ''micrographs'' and you want to save a list with the filenames of the good / bad micrographgs into the folder ''output_folder''. Furthermore you want to use the model ''my_model.h5'' and the GPU with ID=1. Micrographs with a confidence bigger than 0.5 should be classified as good micrograph.
+This is the command to run:
+<code>
+sp_cinderella_predict.py -i micrographs/ -w model.h5 -o output_folder/ -t 0.5 --gpu 1
+</code>
+You will find the files ''bad.txt'' and ''good.txt'' in  your ''output_folder''.

User Tools

Site Tools

Differences

Page Tools