steermomo

def classifier(input_shape, kernel_size, pool_size):
    model = Sequential()

    model.add(Convolution3D(16, kernel_size=kernel_size,
                            padding='valid',
                            input_shape=input_shape))
    model.add(Activation('relu'))
    model.add(MaxPooling3D(pool_size=pool_size))
    model.add(Convolution3D(32, kernel_size=kernel_size))
    model.add(Activation('relu'))

steermomo

import qupath.lib.scripting.QP
import qupath.lib.geom.Point2
import qupath.lib.roi.PolygonROI
import qupath.lib.objects.PathAnnotationObject
import qupath.lib.images.servers.ImageServer


//Aperio Image Scope displays images in a different orientation
def rotated = false

steermomo

# Importing core libraries
import numpy as np
import pandas as pd
from time import time
import pprint
import joblib

# Suppressing warnings because of skopt verbosity
import warnings
warnings.filterwarnings("ignore")

steermomo

import lightgbm as lgb
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import accuracy_score, auc, roc_auc_score
import datetime
import argparse
import pickle
import data_loader
import warnings

steermomo

fuser -v /dev/nvidia* |awk '{for(i=1;i<=NF;i++)print "kill -9 " $i;}' | sh

steermomo

  from keras.utils.data_utils import OrderedEnqueuer  
  val_generator = DataGenerator(target=target, dataset_type='test', batch_size=12,
                                dim=img_dim, shuffle=False)
  steps_per_epoch = len(val_generator)
  val_enqueuer = OrderedEnqueuer(
                      val_generator,
                      use_multiprocessing=use_multiprocessing)
  val_enqueuer.start(workers=workers,
                                 max_queue_size=max_queue_size)
  val_enqueuer_gen = val_enqueuer.get()  # 无限循环 ref:https://github.com/keras-team/keras/blob/master/keras/engine/training_generator.py#L180

steermomo

import subprocess, re

# Nvidia-smi GPU memory parsing.
# Tested on nvidia-smi 370.23

def run_command(cmd):
    """Run command, return output as string."""
    output = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True).communicate()[0]
    return output.decode("ascii")

steermomo

import sys
def pretty_print(header,col, data, file=sys.stdout):
    row_format ="{:<40}" + "{:<15}" * (len(header)) # format
    print(row_format.format("", *header), file=file) # print header
    for team, row in zip(col, data):  # print data part
        print(row_format.format(team, *row),file=file)
    print('-' * (40 + 15 * len(header)), file=file) # print end line

steermomo

def hist_match(source, template):
    """
    Adjust the pixel values of a grayscale image such that its histogram
    matches that of a target image

    Arguments:
    -----------
        source: np.ndarray
            Image to transform; the histogram is computed over the flattened
            array

steermomo

import numpy as np
import keras

class DataGenerator(keras.utils.Sequence):
    'Generates data for Keras'
    def __init__(self, list_IDs, labels, batch_size=32, dim=(32,32,32), n_channels=1,
                 n_classes=10, shuffle=True):
        'Initialization'
        self.dim = dim
        self.batch_size = batch_size