def load_and_run_detector(options, detector=None):
imageFileNames = options_to_images(options)
if options.forceCpu:
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
print('Running detector on {} images'.format(len(imageFileNames)))
if len(imageFileNames) == 0:
print('Warning: no files available')
return
# Load detector if necessary
if detector is None:
startTime = time.time()
print('Loading model...')
detector = TFDetector(options.detectorFile)
elapsed = time.time() - startTime
print("Loaded model in {}".format(
humanfriendly.format_timespan(elapsed)))
# Run detector on target images
boxes, scores, classes, imageFileNames = generate_detections(
detector, imageFileNames, options)
assert len(boxes) == len(imageFileNames)
print('Writing output...')
df = detector_output_to_api_output(imageFileNames, options, boxes, scores,
classes)
# PERF: iterrows is the wrong way to do this for large files
if options.outputPathReplacements is not None:
for iRow, row in df.iterrows():
for query in options.outputPathReplacements:
replacement = options.outputPathReplacements[query]
row['image_path'] = row['image_path'].replace(
query, replacement)
if options.outputRelativeFilenames and os.path.isdir(options.imageFile):
for iRow, row in df.iterrows():
row['image_path'] = os.path.relpath(row['image_path'],
options.imageFile)
if options.outputFile.endswith('.csv'):
write_api_results_csv(df, options.outputFile)
else:
# While we're in transition between formats, write out the old format and
# convert to the new format if .json is requested
tempfilename = next(tempfile._get_candidate_names()) + '.csv'
write_api_results_csv(df, tempfilename)
convert_output_format.convert_csv_to_json(tempfilename,
options.outputFile)
os.remove(tempfilename)
return boxes, scores, classes, imageFileNames
options = BatchDetectionOptions()
options.detectorFile = r'D:\temp\models\megadetector_v3.pb'
options.imageFile = r'D:\temp\demo_images\ssmini'
options.outputFile = r'D:\temp\demo_images\ssmini\detector_out.json'
options.outputPathReplacements = {'D:\\temp\\demo_images\\ssmini\\': ''}
options.recursive = False
# options.checkpointFrequency = -1
options.forceCpu = True
options.resumeFromCheckpoint = None # r'C:\Users\dan\AppData\Local\Temp\detector_batch\tmp77xdq9dp'
if options.forceCpu:
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
print('Loading model...', end='')
detector = TFDetector(options.detectorFile)
print('...done')
boxes, scores, classes, imageFileNames = load_and_run_detector(
options, detector)
#%% Post-processing with process_batch_results... this can also be run from the
# command line.
from api.batch_processing.postprocess_batch_results import PostProcessingOptions
from api.batch_processing.postprocess_batch_results import process_batch_results
ppoptions = PostProcessingOptions()
ppoptions.image_base_dir = options.imageFile
ppoptions.detector_output_file = options.outputFile
ppoptions.output_dir = os.path.join(ppoptions.image_base_dir,
