def progress(self, current, total): # Create the progress logger once we know the total number of steps if self.logger is None: self.logger = ProgressLogger(total) # Display progress output to the user self.logger.progress(current, 'Performing inference...', sameLine = True)
class SegmentationProgress(object): def __init__(self): self.logger = None def progress(self, current, total): # Create the progress logger once we know the total number of steps if self.logger is None: self.logger = ProgressLogger(total) # Display progress output to the user self.logger.progress(current, 'Performing inference...', sameLine = True)
# so we remove it from our list to ensure all data is completely unseen
originalImages = sorted(originalImages)[1:]
# Load the network from the last saved checkpoint and compute our overall validation accuracy
model, metadata = SegmentationNetwork.load()
accuracy = ValidationUtils.computeValidationAccuracy(model, validationData)
# Progress output
numImages = len(originalImages)
print(
'Generating validation report for the segmentation network ({} images)...'.
format(numImages))
# Keep track of processing progress and timing
timer = TimeLogger(numImages, 'image')
progress = ProgressLogger(numImages)
# Process each input file
tableRows = []
for filenum, infile in enumerate(originalImages):
# Progress output
progress.progress(filenum,
'Processing validation image "{}"...'.format(infile))
# Split the ground-truth binary mask from the other image channels
raster = cv2.imread(infile, cv2.IMREAD_UNCHANGED)
channels, groundTruth = maskutils.splitAlphaMask(raster)
# Perform inference on the image data
probabilities = SegmentationNetwork.infer(model, metadata, channels)
MASK_LAYER = 0
# Retrieve the list of input files
inputDir = Configuration.path('segmentation_data_raw')
outputDir = Configuration.path('segmentation_data_preprocessed')
inputFiles = natsorted(glob.glob(os.path.join(inputDir, '**', '*.tif')))
# Progress output
print(
'Preprocessing raw data for the segmentation network ({} files)...'.format(
len(inputFiles)))
# Keep track of processing progress and timing
numFiles = len(inputFiles)
timer = TimeLogger(numFiles, 'file')
progress = ProgressLogger(numFiles)
# Process each input file
for filenum, infile in enumerate(inputFiles):
# Progress output
progress.progress(filenum,
'Preprocessing input file "{}"...'.format(infile))
# Create a temporary directory to hold our intermediate files
with tempfile.TemporaryDirectory() as tempDir:
# Create the filenames for our intermediate files and output file
channelsFile = os.path.join(tempDir, 'channels.tif')
maskFile = os.path.join(tempDir, 'mask.tif')
outfile = os.path.join(
#!/usr/bin/env python3
from common import Configuration, Logger, TimeLogger, ProgressLogger, SegmentationNetwork
from natsort import natsorted
import glob, os
# Retrieve the list of input files
inputDir = Configuration.path('segmentation_data_sliced')
outputDir = Configuration.path('segmentation_data_windowed')
inputFiles = natsorted(glob.glob(os.path.join(inputDir, '*.png')))
# Progress output
print('Windowing sliced data for the segmentation network ({} files)...'.format(len(inputFiles)))
# Keep track of processing progress and timing
numFiles = len(inputFiles)
timer = TimeLogger(numFiles, 'file')
progress = ProgressLogger(numFiles)
# Process each input file
for filenum, infile in enumerate(inputFiles):
# Progress output
progress.progress(filenum, 'Windowing input file "{}"...'.format(infile))
# Slice the file
SegmentationNetwork.windowToDir(infile, outputDir, warnOnOverwrite=True)
# Progress output
timer.end()
Logger.success('windowing complete ({}).'.format(timer.report()))