Add files via upload

tutorials/classification_pathmnist_notebook/config (3).yaml

@@ -0,0 +1,200 @@
+# affix version
+version:
+  {
+    minimum: 0.0.14,
+    maximum: 0.0.14 # this should NOT be made a variable, but should be tested after every tag is created
+  }
+# Choose the model parameters here
+
+model:
+  {
+    dimension: 2, # the dimension of the model and dataset: defines dimensionality of computations
+    base_filters: 32, # Set base filters: number of filters present in the initial module of the U-Net convolution; for IncU-Net, keep this divisible by 4
+    architecture: vgg, # options: unet, resunet, fcn, uinc, vgg, densenet
+    batch_norm: True, # this is only used for vgg
+    norm_type: batch,
+    final_layer: sigmoid, # can be either sigmoid, softmax or none (none == regression)
+    amp: False, # Set if you want to use Automatic Mixed Precision for your operations or not - options: True, False
+    n_channels: 3, # set the input channels - useful when reading RGB or images that have vectored pixel types
+    class_list: ["0", "1", "2", "3", "4", "5", "6", "7", "8"] # changed for pathmnist
+  }
+# this is to enable or disable lazy loading - setting to true reads all data once during data loading, resulting in improvements
+# in I/O at the expense of memory consumption
+in_memory: False
+# this will save the generated masks for validation and testing data for qualitative analysis
+save_masks: False
+# Set the Modality : rad for radiology, path for histopathology
+modality: rad
+# Patch size during training - 2D patch for breast images since third dimension is not patched 
+patch_size: [256, 256]
+# uniform: UniformSampler or label: LabelSampler
+patch_sampler: uniform
+#metrics: ["classification_accuracy"]
+#metrics: ["accuracy"]
+metrics:
+  #- cel
+  - classification_accuracy
+  - f1: {
+      average: weighted,
+     }
+  - accuracy
+  - balanced_accuracy
+  # - precision: {
+  #     average: weighted,
+  #   }
+  # - recall
+  # - iou: {
+  #     reduction: sum,
+  #   }
+# Number of epochs
+num_epochs: 5
+# Set the patience - measured in number of epochs after which, if the performance metric does not improve, exit the training loop - defaults to the number of epochs
+patience: 5
+# Set the batch size
+batch_size: 16
+# Set the initial learning rate
+learning_rate: 0.001
+# Learning rate scheduler - options: triangle, triangle_modified, exp, reduce-on-lr, step, more to come soon - default hyperparameters can be changed thru code
+scheduler: triangle
+# Set which loss function you want to use - options : 'dc' - for dice only, 'dcce' - for sum of dice and CE and you can guess the next (only lower-case please)
+# options: dc (dice only), dc_log (-log of dice), ce (), dcce (sum of dice and ce), mse () ...
+# mse is the MSE defined by torch and can define a variable 'reduction'; see https://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html#torch.nn.MSELoss
+# use mse_torch for regression/classification problems and dice for segmentation
+loss_function: cel
+# this parameter weights the loss to handle imbalanced losses better
+weighted_loss: True
+#loss_function:
+#  {
+#    'mse':{
+#      'reduction': 'mean' # see https://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html#torch.nn.MSELoss for all options
+#    }
+#  }
+# Which optimizer do you want to use - adam/sgd
+opt: adam
+# this parameter controls the nested training process
+# performs randomized k-fold cross-validation
+# split is performed using sklearn's KFold method
+# for single fold run, use '-' before the fold number
+nested_training:
+  {
+    testing: 1, # this controls the testing data splits for final model evaluation; use '1' if this is to be disabled
+    validation: -5 # this controls the validation data splits for model training
+  }
+## pre-processing
+# this constructs an order of transformations, which is applied to all images in the data loader
+# order: resize --> threshold/clip --> resample --> normalize
+# 'threshold': performs intensity thresholding; i.e., if x[i] < min: x[i] = 0; and if x[i] > max: x[i] = 0
+# 'clip': performs intensity clipping; i.e., if x[i] < min: x[i] = min; and if x[i] > max: x[i] = max
+# 'threshold'/'clip': if either min/max is not defined, it is taken as the minimum/maximum of the image, respectively
+# 'normalize': performs z-score normalization: https://torchio.readthedocs.io/transforms/preprocessing.html?highlight=ToCanonical#torchio.transforms.ZNormalization
+# 'normalize_nonZero': perform z-score normalize but with mean and std-dev calculated on only non-zero pixels
+# 'normalize_nonZero_masked': perform z-score normalize but with mean and std-dev calculated on only non-zero pixels with the stats applied on non-zero pixels
+# 'crop_external_zero_planes': crops all non-zero planes from input tensor to reduce image search space
+# 'resample: resolution: X,Y,Z': resample the voxel resolution: https://torchio.readthedocs.io/transforms/preprocessing.html?highlight=ToCanonical#torchio.transforms.Resample
+# 'resample: resolution: X': resample the voxel resolution in an isotropic manner: https://torchio.readthedocs.io/transforms/preprocessing.html?highlight=ToCanonical#torchio.transforms.Resample
+# resize the image(s) and mask (this should be greater than or equal to patch_size); resize is done ONLY when resample is not defined
+
+
+# data_augmentation:
+#   {
+#   # 'spatial':{
+#   #   'probability': 0.5
+#   # },
+#   # 'kspace':{
+#   #   'probability': 0.5
+#   # },
+#   'bias':{
+#     'probability': 0.5
+#   },
+#   'blur':{
+#     'probability': 0.5
+#   },
+#   'noise':{
+#     'probability': 0.5
+#   },
+#   'swap':{
+#     'probability': 0.5
+#   }
+#   }
+
+data_preprocessing:
+  {
+    #'normalize_div_by_255',
+    # 'threshold':{
+    #   'min': 10, 
+    #   'max': 75
+    # },
+    # 'clip':{
+    #   'min': 10, 
+    #   'max': 75
+    # }, 
+    #'normalize_imagenet',
+    # 'resample':{
+    #   'resolution': [1,2,3]
+    # },
+    'resize': [256,256], # this is generally not recommended, as it changes image properties in unexpected ways
+    #'resize_image': [256,256], #resizes the image and mask BEFORE applying any another operation
+    #'resize_patch': [256,256] #resizes the image and mask AFTER extracting the patch
+  }
+# data_preprocessing:
+#   {
+#     # 'normalize',
+#     # # 'normalize_nonZero', # this performs z-score normalization only on non-zero pixels
+#     # 'resample':{
+#     #   'resolution': [1,2,3]
+#     # },
+      #'resize': [128, 128], # this is generally not recommended, as it changes image properties in unexpected ways
+#     # 'crop_external_zero_planes', # this will crop all zero-valued planes across all axes
+#   }
+# various data augmentation techniques
+# options: affine, elastic, downsample, motion, ghosting, bias, blur, gaussianNoise, swap
+# keep/edit as needed
+# all transforms: https://torchio.readthedocs.io/transforms/transforms.html?highlight=transforms
+# 'kspace': one of motion, ghosting or spiking is picked (randomly) for augmentation
+# 'probability' subkey adds the probability of the particular augmentation getting added during training (this is always 1 for normalize and resampling)
+# data_augmentation: 
+  # {
+    # default_probability: 0.5,
+    # 'affine',
+    # 'elastic',
+    # 'kspace':{
+    #   'probability': 1
+    # },
+    # 'bias',
+    # 'blur': {
+    #   'std': [0, 1] # default std-dev range, for details, see https://torchio.readthedocs.io/transforms/augmentation.html?highlight=randomblur#torchio.transforms.RandomBlur
+    # },
+    # 'noise': { # for details, see https://torchio.readthedocs.io/transforms/augmentation.html?highlight=randomblur#torchio.transforms.RandomNoise
+    #   'mean': 0, # default mean
+    #   'std': [0, 1] # default std-dev range
+    # },
+    # 'anisotropic':{
+    #   'axis': [0,1],
+    #   'downsampling': [2,2.5]
+    # },
+  # }
+# parallel training on HPC - here goes the command to prepend to send to a high performance computing
+# cluster for parallel computing during multi-fold training
+# not used for single fold training
+# this gets passed before the training_loop, so ensure enough memory is provided along with other parameters
+# that your HPC would expect
+# ${outputDir} will be changed to the outputDir you pass in CLI + '/${fold_number}'
+# ensure that the correct location of the virtual environment is getting invoked, otherwise it would pick up the system python, which might not have all dependencies
+
+# UB_commented: parallel_compute_command: 'qsub -b y -l gpu -l h_vmem=32G -cwd -o ${outputDir}/\$JOB_ID.stdout -e ${outputDir}/\$JOB_ID.stderr `pwd`/sge_wrapper _correct_location_of_virtual_environment_/venv/bin/python',
+#parallel_compute_command: ''
+## queue configuration - https://torchio.readthedocs.io/data/patch_training.html?#queue
+# this determines the maximum number of patches that can be stored in the queue. Using a large number means that the queue needs to be filled less often, but more CPU memory is needed to store the patches
+
+q_max_length: 5
+
+# this determines the number of patches to extract from each volume. A small number of patches ensures a large variability in the queue, but training will be slower
+
+q_samples_per_volume: 1
+
+# this determines the number subprocesses to use for data loading; '0' means main process is used
+
+q_num_workers: 0 # scale this according to available CPU resources (was 16)
+
+# used for debugging
+q_verbose: False