Differences

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

--- pipeline:window:cryolo [2018/12/27 20:35]
twagner [Visualize the results]
+++ pipeline:window:cryolo [2019/09/17 13:40]
twagner [Advanced parameters]
@@ Line 7: / Line 7: @@
   * crYOLO makes picking **smart** -- The network learns the context of particles (e.g. not to pick particles on carbon or within ice contamination )
   * crYOLO makes training **easy** -- You might use a general network model and skip training completely. However, if the general model doesn't give you satisfactory results or if you would like to improve them, you might want to train a specialized model specific for your data set by selecting __particles__ (no selection of negative examples necessary) on a small number of micrographs.
+  * crYOLO makes training **tolerant** -- Don't worry if you miss quite a lot particles during creation of your training set. [[:cryolo_picking_unlabeled|crYOLO will still do the job.]]
-In this tutorial we explain our recommended configurations for single particle and filament projects. You can find more information about supported networks and about the config file in the following articles:
+In this tutorial we explain our recommended configurations for single particle and filament projects. You can find more information how to use crYOLO, about supported networks and about the config file in the following articles:
+  * [[https://www.youtube.com/embed/JTgldM4wAAk|crYOLO talk at SBGrid]]
   * [[:cryolo_nets|crYOLO networks]]
   * [[:cryolo_config|crYOLO configuration file]]
+<note>
+You can find more technical details in our paper:
+[[https://doi.org/10.1038/s42003-019-0437-z|Wagner, T. et al. SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM. Communications Biology 2, (2019). ]]
+----
+We are also proud that crYOLO was recommended by F1000:
+//"CrYOLO works amazingly well in identifying the true particles and distinguishing them from other high-contrast features. Thus, crYOLO provides a fast, automated tool, which gives similar reliable results as careful manual selection and outperforms template based selection procedures."//
+<html></html>
+<html>
+<a href="https://f1000.com/prime/733517098?bd=1" target="_blank"><img src="https://s3.amazonaws.com/cdn.f1000.com/images/badges/badgef1000.gif" alt="Access the recommendation on F1000Prime" id="bg" />&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Bettina Böttcher, Biochemistry, University Würzburg</a>
+</html>
+</note>
 ===== Installation =====
 You can find the download and installation instructions here: [[howto:download_latest_cryolo|Download and Installation]]
-===== Picking - Using a model trained for your data =====
+===== Tutorials =====
+Depending what you want to do, you can follow one of these self-contained Tutorials:
-==== Data preparation ====
+  - I would like to train a model from scratch for picking my particles
-CrYOLO supports MRC, TIF and JPG files. It can work with 32 bit data, 8 bit data and 16 bit data.
+  - I would like to train a model from scratch for picking filaments.
-It will work on original MRC files, but it will probably improve when the data are filtered. Therefore you should low-pass filter them to a reasonable level. Since Version 1.2 crYOLO can automatically do that for you. You just have to add
+  - I would like to refine a general model for my particles.
-<code>
-"filter":               [0.1,"filtered"]
+The **first and the second tutorial** are the most common use cases and well tested. The **third tutorial** is still experimental but might give you better results in less time and less training data.
-</code>
-to the model section in your config file to filter your images down to an absolute frequency of 0.1. The filtered images are saved in folder ''filtered''.
+===== Picking particles - Using a model trained for your data =====
+This tutorial explains you how to train a model specific for you dataset.
 If you followed the installation instructions, you now have to activate the cryolo virtual environment with
@@ Line 31: / Line 57: @@
 source activate cryolo
 </code>
+==== Data preparation ====
+{{page>pipeline:window:cryolo:data_preparation}}
-In the following I will assume that your image data is in the folder ''full_data''.
+==== Start crYOLO ====
+{{page>pipeline:window:cryolo:start_cryolo}}
-The next step is to create training data. To do so, we have to pick single particles manually in several micrographs. Ideally, the micrographs are picked to completion. One may ask how many micrographs have to be picked? It depends! Typically 10 micrographs are a good start. However, that number may increase / decrease due to several factors:
+==== Configuration ====
-  * A very heterogenous background could make it necessary to pick more micrographs.
+{{page>pipeline:window:cryolo:configuration}}
-  * If your micrograph is only sparsely decorated, you may need to pick more micrographs.
-We recommend that you start with 10 micrographs, then autopick your data, check the results and finally decide whether to add more micrographs to your training set.
+<html>
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
+<b>You can now press the Start button to create you configuration file.</b>
+</div>
+</html>
-{{:pipeline:window:box_manager.png?direct&400 |}}
-To create your training data, crYOLO is shipped with a tool called "boxmanager". However, you can also use tools like e2boxer to create your training data.
-Start the box manager with the following command:
+{{page>pipeline:window:cryolo:configuration_cmdl_normal}}
-<code>
-cryolo_boxmanager.py
-</code>
-Now press //File -> Open image folder// and the select the ''full_data'' directory. The first image should pop up. You can navigate in the directory tree through the images. Here is how to pick particles:
+==== Training ====
-  * LEFT MOUSE BUTTON: Place a box
+{{page>pipeline:window:cryolo:training}}
-  * HOLD LEFT MOUSE BUTTON: Move a box
+==== Picking ====
-  * CONTROL + LEFT MOUSE BUTTON: Remove a box
+{{page>pipeline:window:cryolo:picking}}
-You can change the box size in the main window, by changing the number in the text field labeled //Box size://. Press //Set// to apply it to all picked particles. For picking, you should the use minimum sized square which encloses your particle.
-If you finished picking from your micrographs, you can export your box files with //Files -> Write box files//.
+==== Visualize the results ====
-Create a new directory called ''train_annotation'' and save it there. Close boxmanager.
+{{page>pipeline:window:cryolo:visualize}}
-Now create a third folder with the name ''train_image''. Now for each box file, copy the corresponding image from ''full_data'' into ''train_image''. crYOLO will detect image / box file pairs by search taking the box file an searching for an image filename which contains the box filename.
+==== Evaluate your results ====
+{{page>pipeline:window:cryolo:evaluate_results}}
+===== Picking particles - Without training using a general model =====
+Here you can find how to apply the general models we trained for you. If you would like to train your own general model, please see our extra wiki page: [[:cryolo_train_general_model|How to train your own general model]]
+Our general models can be found and downloaded here: [[howto:download_latest_cryolo|Download and Installation]].
+If you followed the installation instructions, you now have to activate the cryolo virtual environment with
-==== Configuration ====
-You now have to create a config file your picking project. To do this type:
 <code>
-touch config.json
+source activate cryolo
 </code>
+==== Start crYOLO ====
+{{page>pipeline:window:cryolo:start_cryolo}}
-To use the [[:cryolo_nets#network_3_phosaurusnet|Phosaurus network]] copy the following lines into that file:
+==== Configuration====
-<code json config.json>
+In the GUI choose the //config// action. Fill in your target box size and leave the //train_image_folder// and //train_annot_folder// fields empty.
-{
-    "model" : {
-        "architecture":         "PhosaurusNet",
-        "input_size":           1024,
-        "anchors":              [160,160],
-        "max_box_per_image":    600,
-        "num_patches":          1,
-        "filter":               [0.1,"filtered"]
-    },
-    "train": {
+{{ :pipeline:window:cryolo_filter_options.png?300|}}
-        "train_image_folder":   "train_image/",
-        "train_annot_folder":   "train_annotation/",
-        "train_times":          10,
-        "pretrained_weights":   "model.h5",
-        "batch_size":           6,
-        "learning_rate":        1e-4,
-        "nb_epoch":             50,
-        "warmup_epochs":        0,
-        "object_scale":         5.0 ,
+[[:downloads:cryolo_1#general_phosaurusnet_models|There are three general models available]]. It is important that you choose the same filtering options in //"Model/denoising options"// tab as we did during training the general models:
-        "no_object_scale":      1.0,
-        "coord_scale":          1.0,
-        "class_scale":          1.0,
-        "log_path":             "logs/",
-        "saved_weights_name":   "model.h5",
-        "debug":                true
-    },
-    "valid": {
+  * General model trained for low-pass filtered images : Select //filter// "LOWPASS" and //low_pass_cutoff// of 0.1
-        "valid_image_folder":   "",
+  * General model trained for JANNI-denoised images: Select //filter// "JANNI" and the [[:janni_tutorial#download|janni general model]] for //janni_model//. Keep the defaults for //janni_overlap// and //janni_batches//
-        "valid_annot_folder":   "",
+  * General model for negative stain images: Select filter "NONE"
-        "valid_times":          1
+<html>
-    }
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
-}
+<b>Press the Start button to write the configuration file to disk.  </b>
+</div>
+</html>
+<hidden **Create the configuration file using the command line**>
+In the following I assume that you target box size is 220. Please adapt if necessary.
+For the general **[[:cryolo_nets#network_3_phosaurusnet|Phosaurus network]]** trained for **low-pass filtered cryo images** run:
+<code>
+cryoloo.py config config_cryolo_.json 220 --filter LOWPASS --low_pass_cutoff 0.1
 </code>
-//[[:cryolo_config|Click here to get more information about the configuration file]]//
-Please set the value in the //"anchors"// field to your desired box size. It should be size of the minimum enclosing square in pixels. Furthermore check if the fields //"train_image_folder"// and //"train_annot_folder"// have the correct values. Typically, 20% of the training data are randomly chosen as validation data. If you want to use specific images as validation data, you can move the images and the corresponding box files to the folders specified in //"valid_image_folder"// and //"valid_annot_folder"//. Make sure that they are removed from the original training folder! With the line below, crYOLO automatically filters your images to an absolute frequence 0.1 and write them into a folder "filtered".
+For the general model trained with **neural-network denoised cryo images** (with [[:janni_tutorial#download|JANNI's general model]]) run:
 <code>
-"filter":               [0.1,"filtered"].
+cryoloo.py config config_cryolo_.json 220 --filter JANNI --janni_model /path/to/janni_general_model.h5
 </code>
-crYOLO will automatically check if an image in full_data is available in the ''filtered'' directory. The filtering is done in parallel. If you don't want to use crYOLO's internal filtering, just remove the line and filter them manually. If you remove the line, don't forget to remove the comma at the end of the line above.
-Please note the wiki entry about the [[:cryolo_config|crYOLO configuration file]] if you want to know more details.
+For the general model for **negative stain data** please run:
+<code>
+cryoloo.py config config_cryolo_.json 220 --filter NONE
+</code>
+</hidden>
+==== Picking ====
+{{page>pipeline:window:cryolo:picking}}
+==== Visualize the results ====
+{{page>pipeline:window:cryolo:visualize}}
+===== Picking particles - Using the general model refined for your data =====
-==== 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:
+Since crYOLO 1.3 you can train a model for your data by //fine-tuning// the general model.
-<code>
-nvidia-smi
-</code>
-For this tutorial, we assume that you have either a single GPU or want to use GPU 0. Therefore we add '-g 0' after each command below. However, if you have multiple (e.g GPU 0 and GPU 1) you could also use both by adding '-g 0 1' after each command.
-Navigate to the folder with ''config.json'' file, ''train_image'' folder, etc.
+What does //fine-tuning// mean?
-**1. Warm up your network**
+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.
-<code>
+Why should I //fine-tune// my model instead of training from scratch?
-cryolo_train.py -c config.json -w 3 -g 0
+  -  From theory, using fine-tuning should reduce the risk of overfitting ((Overfitting means, that the model works good on the training micrographs, but not on new unseen micrographs. The model just memorized what it saw instead of learning generic features.)) and the amount of training data.
-</code>
+  - The training is much faster, as not all layers have to be trained.
+  - 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 if see more advantages or disadvantages.
-**2. Train your network**
+If you followed the installation instructions, you now have to activate the cryolo virtual environment with
 <code>
-cryolo_train.py -c config.json -w 0 -g 0
+source activate cryolo
 </code>
-The final model will be called ''model.h5''
+==== Data preparation ====
+{{page>pipeline:window:cryolo:data_preparation}}
+==== Start crYOLO ====
+{{page>pipeline:window:cryolo:start_cryolo}}
+==== Configuration ====
+{{page>pipeline:window:cryolo:configuration}}
+{{ :pipeline:window:cryolo_pretrained_weights.png?300|}}
+Furthermore, you have to select the model you want to refine. Download the the general model you want to refine specify in the field pretrained_weights in the //"Training options"// tab.
+<html>
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
+<b>You can now press the Start button to create configuration file.  </b>
+</div>
+</html>
+<hidden **Create the configuration file using the command line:**>
+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:
-The training stops when the "loss" metric on the validation data does not improve 5 times in a row. This is typically enough. However, you might want to give the training more time to find the best model. You might increase the "not changed in a row" parameter to, for example, 10 by adding the flag //-e 10//:
 <code>
-cryolo_train.py -c config.json -w 0 -g 0 -e 10
+cryoloo.py config config_cryolo.json 160 --train_image_folder train_image --train_annot_folder train_annot --pretrained_weights gmodel_phosnet_20190516.h5
 </code>
-to the training command.
-==== Picking ====
+To get a full description of all available options type:
-You can now use the model weights saved in ''model.h5'' to pick all your images in the directory ''full_data''. To do this, run:
 <code>
-cryolo_predict.py -c config.json -w model.h5 -i full_data/ -g 0 -o boxfiles/
+cryoloo.py config -h
 </code>
-You will find the picked particles in the directory ''boxfiles''
+If you want to specify seperate validation folders you can use the %%--%%valid_image_folder and %%--%%valid_annot_folder options:
-If you want to pick less conservatively or more conservatively you might want to change the selection threshold from the default of 0.3 to a less conservative value like 0.2 or more conservative value like 0.4 using the //-t// parameter:
 <code>
-cryolo_predict.py -c config.json -w model.h5 -i full_data/ -g 0 -o boxfiles/ -t 0.2
+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
 </code>
-==== Visualize the results ====
+</hidden>
+==== 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:
-To visualize your results you can use the box manager:
 <code>
-cryolo_boxmanager.py
+nvidia-smi
 </code>
-Now press //File -> Open image// folder and the select the ''full_data'' directory. The first image should pop up. Then you import the box files with //File -> Import box files// and select in the ''boxfiles'' folder the ''EMAN'' directory.
+For this tutorial, we assume that you have either a single GPU or want to use GPU 0.
+In the GUI choose the action //train//. In the //"Required arguments"// tab select the configuration file we created in the previous step and set the number of warmup periods to zero.
+{{ :pipeline:window:cryolo_refine.png?600 |}}
-===== Picking - Without training using a general model =====
+In the //"Optional arguments"// tab please check the fine_tune box.
+{{ :pipeline:window:cryolo_refine_02.png?300 |}}
+<note important>
+The number of layers to fine tune (specified by layers_fine_tune in the //"Optional arguments"// tab) is still experimental. The default value of 2 worked for us but you might need more layers..
+</note>
-The general model can be found here: [[howto:download_latest_cryolo|Download and Installation]].
-==== Configuration====
-The next step is to create a configuration file. Type:
-<code>
-touch config.json
-</code>
-Open the file with your preferred editor.
+<note tip>
-For the general **[[:cryolo_nets#network_3_phosaurusnet|Phosaurus network]]** enter the following inside:
+**Training on CPU**
-<code json config.json>
-    {
-    "model" : {
-        "architecture":         "PhosaurusNet",
-        "input_size":           1024,
-        "anchors":              [205,205],
-        "max_box_per_image":    700,
-        "num_patches":          1,
-        "filter":               [0.1,"tmp_filtered"]
-    }
-</code>
-Please set the value in the //"anchors"// field to your desired box size. It should be size of the minimum particle enclosing square in pixel.
+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>
+<hidden **Run training with the command line**>
+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 ):
+<code>
+cryolo_train.py -c config.json -w 0 -g 0 --fine_tune -lft 2
+</code>
+</hidden>
 ==== Picking ====
-Just follow the description given [[pipeline:window:cryolo#Picking|above]]
+{{page>pipeline:window:cryolo:picking}}
-As for a direct trained model, you might want to play around with the -t parameter to make picking less or more conservative.
+==== Visualize the results ====
+{{page>pipeline:window:cryolo:visualize}}
+==== Evaluate your results ====
+{{page>pipeline:window:cryolo:evaluate_results}}
 ===== Picking filaments - Using a model trained for your data =====
 Since version 1.1.0 crYOLO supports picking filaments.
@@ Line 211: / Line 257: @@
 {{:pipeline:window:filament_tracing_02.png?300|}}  {{:pipeline:window:filament_tracing_03.png?300|}}
+If you followed the installation instructions, you now have to activate the cryolo virtual environment with
+<code>
+source activate cryolo
+</code>
 ==== Data preparation ====
-{{ :pipeline:window:settings_e2helixboxer.png?300|}} As described [[pipeline:window:cryolo#data_preparation|previously]], filtering your image using a low-pass filter is probably a good idea.
+{{ :pipeline:window:settings_e2helixboxer.png?300|}}
-After this is done, you have to prepare training data for your model.
+The first step is to create the training data for your model. Right now, you have to use the e2helixboxer.py for this:
- Right now, you have to use the e2helixboxer.py to generate the training data:
 <code>
 e2helixboxer.py --gui my_images/*.mrc
@@ Line 223: / Line 275: @@
 After tracing your training data in e2helixboxer, export them using //File -> Save//. Make sure that you export particle coordinates as this the only format supported right now (see screenshot). In the following example, it is expected that you exported into a folder called "train_annotation".
-==== Configuration ====
+For projects with roughly 20 filaments per image we successfully trained on 40 images (=> 800 filaments).
-You can configure it the same way as for a "normal" project. We recommend to use [[:cryolo_nets#network_2_yolo_with_patches|YOLO in "patch mode" with 3x3 patches]]:
-<code json config.json>
-{
-    "model" : {
-        "architecture":         "YOLO",
-        "input_size":           768,
-        "anchors":              [200,200],
-        "max_box_per_image":    600,
-        "num_patches":          3,
-        "filter":               [0.1,"tmp_filtered"]
-    },
-    "train": {
+==== Start crYOLO ====
-        "train_image_folder":   "train_image/",
+{{page>pipeline:window:cryolo:start_cryolo}}
-        "train_annot_folder":   "train_annotation/",
-        "train_times":          10,
-        "pretrained_weights":   "model.h5",
-        "batch_size":           6,
-        "learning_rate":        1e-4,
-        "nb_epoch":             50,
-        "warmup_epochs":        0,
-        "object_scale":         5.0 ,
-        "no_object_scale":      1.0,
-        "coord_scale":          1.0,
-        "class_scale":          1.0,
-        "log_path":             "logs/",
-        "saved_weights_name":   "model.h5",
-        "debug":                true
-    },
-    "valid": {
+==== Configuration ====
-        "valid_image_folder":   "",
+{{page>pipeline:window:cryolo:configuration}}
-        "valid_annot_folder":   "",
-        "valid_times":          1
-    }
-}
-</code>
-//[[:cryolo_config|Click here to get more information about the configuration file]]//
-Just adapt the anchors accordingly to your box size.
+<html>
+<div style="background-color: #cfc ; padding: 10px; border: 1px solid green;">
+<b>You can now press the Start button to create you configuration file. </b>
+</div>
+</html>
+{{page>pipeline:window:cryolo:configuration_cmdl_normal}}
 ==== Training ====
-In principle, there is not much difference in training crYOLO for filament picking and particle picking. For project with roughly 20 filaments per image we successfully trained on 40 images (=> 800 filaments). However, in our experience the warm-up phase and training need a little bit more time:
+{{page>pipeline:window:cryolo:training}}
+==== Picking ====
+Select the action prediction and fill all arguments in the “Required arguments” tab:
+{{ :pipeline:window:cryolo:cryolo_prediction.png?600 |}}
-**1. Warm up your network**
+Now select the "Filament options" tab and check "Activate filament mode", specifiy the filament width (e.g. 100) and define the box distance (e.g. 20 for 90% overlap when using a box size if 200):
-<code>
+{{ :pipeline:window:cryolo_filament.png?700 |}}
-cryolo_train.py -c config.json -w 10 -g 0
-</code>
-**2. Train your network**
+Press the start button to start the picking. The directory ''output_boxes'' will be created and all results are saved there. The format is the eman2 helix format with particle coordinates.
-<code>
+You can find a detailed description [[:cryolo_filament_import_relion|how to import crYOLO filament coordinates into Relion here]].
-cryolo_train.py -c config.json -w 0 -g 0 -e 10
-</code>
-The final model will be called ''model.h5''
-==== Picking ====
-The biggest difference in picking filaments with crYOLO is during prediction. However, there are just three additional parameters needed:
-  * //- -filament//: Option that tells crYOLO that you want to predict filaments
-  * //-fw//: Filament width (pixels)
-  * //-bd//: Inter-Box distance (pixels).
+<hidden **Run prediction in commmand line**>
 Let's assume you want to pick a filament with a width of 100 pixels (-fw 100). The box size is 200x200 and you want a 90% overlap (-bd 20). Moreover, you wish that each filament has at least 6 boxes (-mn 6). The micrographs are in the ''full_data'' directory. Than the picking command would be:
 <code>
-cryolo_predict.py -c config.json -w model.h5 -i full_data --filament -fw 100 -bd 20 -o boxes/ -g 0 -mn 6
+cryolo_predict.py -c cryolo_config.json -w cryolo_model.h5 -i full_data --filament -fw 100 -bd 20 -o boxes/ -g 0 -mn 6
 </code>
+</hidden>
-The directory ''boxes'' will be created and all results are saved there. The format is the eman2 helix format with particle coordinates. You can find a detailed description [[:cryolo_filament_import_relion|how to import crYOLO filament coordinates into Relion here]].
 ==== Visualize the results ====
-You can use the boxmanager as described [[pipeline:window:cryolo#visualize_the_results|previously]].
+{{page>pipeline:window:cryolo:visualize}}
-===== Evaluate your results =====
-The evaluation tool allows you, based on your validation data, to get statistics about your training. Unfortunately, this script **does not work for filamental data**.
-If you followed the tutorial, the validation data are selected randomly. With crYOLO 1.1.0 a run file for each training is created and saved into the folder runfiles/ in your project directory. This run file contains which files were selected for validation, and you can run your evaluation as follows:
-<code>
-cryolo_evaluation.py -c config.json -w model.h5 -r runfiles/run_YearMonthDay-HourMinuteSecond.json -g 0
-</code>
-The result looks like this:
-{{:pipeline:window:eval_example.png?900 |}}
-The table contains several statistics:
-  * AUC: Area under curve of the precision-recall curve. Overall summary statistics. Perfect classifier = 1, Worst classifier = 0
-  * Topt: Optimal confidence threshold with respect to the F1 score. It might not be ideal for your picking, as the F1 score weighs recall and precision equally. However in SPA, recall is often more important than the precision.
-  * R (Topt): Recall using the optimal confidence threshold.
-  * R (0.3): Recall using a confidence threshold of 0.3.
-  * R (0.2): Recall using a confidence threshold of 0.2.
-  * P (Topt): Precision using the optimal confidence threshold.
-  * P (0.3): Precision using a confidence threshold of 0.3.
-  * P (0.2): Precision using a confidence threshold of 0.2.
-  * F1 (Topt): Harmonic mean of precision and recall using the optimal confidence threshold.
-  * F1 (0.3): Harmonic mean of precision and recall using a confidence threshold of 0.3.
-  * F1 (0.2): Harmonic mean of precision and recall using a confidence threshold of 0.2.
-  * IOU (Topt): Intersection over union of the auto-picked particles and the corresponding ground-truth boxes. The higher, the better -- evaluated with the optimal confidence threshold.
-  * IOU (0.3): Intersection over union of the auto-picked particles and the corresponding ground-truth boxes. The higher, the better -- evaluated with a confidence threshold of 0.3.
-  * IOU (0.2): Intersection over union of the auto-picked particles and the corresponding ground-truth boxes. The higher, the better -- evaluated with a confidence threshold of 0.2.
-If the training data consists of multiple folders, then evaluation will be done for each folder separately.
-Furthermore, crYOLO estimates the optimal picking threshold regarding the F1 Score and F2 Score. Both are basically average values of the recall and prediction, whereas the F2 score puts more weights on the recall, which is in the cryo-em often more important.
-===== Advanced parameters =====
-During **training** (//cryolo_train//), there is the following advanced parameter:
-  * //--warm_restarts//: With this option the learning rate is decreasing after each epoch and then reset after a couple of epochs.
-During **picking** (//cryolo_predict//), there are two advanced parameters:
-  * //-t confidence_threshold//: With the -t parameter, you can let the crYOLO pick more conservative (e.g by adding -t 0.4 to the picking command) or less conservative (e.g by adding -t 0.2 to the picking command). The valid parameter range is 0 to 1.
-  * //-d distance_in_pixel//: With the -d parameter you can filter your picked particles. Boxes with a distance (pixel) less than this value will be removed.
-  * //-pbs prediction_batch_size//: With the -pbs parameter you can set the number of images picked as batch. Default is 3.
 ===== Help =====

User Tools

Site Tools

Differences

Page Tools