def predict(img_path, evaluator, cfg, debug=False):
# detect objects in single image
regressed_rois, cls_probs = evaluator.process_image(img_path)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs,
cfg)
# visualize detections on image
if debug:
od.visualize_results(img_path,
bboxes,
labels,
scores,
cfg,
store_to_path=img_path + "o.jpg")
# write detection results to output
fg_boxes = np.where(labels > 0)
result = []
for i in fg_boxes[0]:
# print (cfg["DATA"].CLASSES)
# print(labels)
result.append({
'label': cfg["DATA"].CLASSES[labels[i]],
'score': '%.3f' % (scores[i]),
'box': [int(v) for v in bboxes[i]]
})
return result
def evaluate_model(eval_model, detector_name):
cfg = get_configuration(detector_name)
cfg['NUM_CHANNELS'] = 3
print("Map file = ", cfg["DATA"].CLASS_MAP_FILE)
cfg["DATA"].CLASSES = parse_class_map_file(
os.path.join("Steer_Bad_Relevant_output", cfg["DATA"].CLASS_MAP_FILE))
cfg["DATA"].NUM_CLASSES = len(cfg["DATA"].CLASSES)
# detect objects in single image
img_path = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
r"Steer_Bad_Relevant_output/testImages/Steer_Bad_Front_Zoom (269).jpg")
regressed_rois, cls_probs = od.evaluate_single_image(
eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(
len(regressed_rois), len(bboxes), len(fg_boxes[0])))
for i in fg_boxes[0]:
print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i],
[int(v) for v in bboxes[i]]))
od.visualize_results(img_path,
bboxes,
labels,
scores,
cfg,
store_to_path="Steer_Bad_Relevant_output/output.jpg")
def test_detection_demo(device_id):
if cntk_device(device_id).type() != DeviceKind_GPU:
pytest.skip('test only runs on GPU') # it runs very slow in CPU
try_set_default_device(cntk_device(device_id))
from prepare_test_data import prepare_Grocery_data, prepare_alexnet_v0_model
grocery_path = prepare_Grocery_data()
prepare_alexnet_v0_model()
from FastRCNN.install_data_and_model import create_grocery_mappings
create_grocery_mappings(grocery_path)
from DetectionDemo import get_configuration
import utils.od_utils as od
cfg = get_configuration('FasterRCNN')
cfg["CNTK"].FORCE_DETERMINISTIC = True
cfg["CNTK"].DEBUG_OUTPUT = False
cfg["CNTK"].MAKE_MODE = False
cfg["CNTK"].FAST_MODE = False
cfg.CNTK.E2E_MAX_EPOCHS = 3
cfg.CNTK.RPN_EPOCHS = 2
cfg.CNTK.FRCN_EPOCHS = 2
cfg.IMAGE_WIDTH = 400
cfg.IMAGE_HEIGHT = 400
cfg["CNTK"].TRAIN_E2E = True
cfg.USE_GPU_NMS = False
cfg.VISUALIZE_RESULTS = False
cfg["DATA"].MAP_FILE_PATH = grocery_path
externalData = 'CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY' in os.environ
if externalData:
extPath = os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY']
cfg['BASE_MODEL_PATH'] = os.path.join(extPath, "PreTrainedModels",
"AlexNet", "v1",
"AlexNet_ImageNet_Caffe.model")
else:
cfg['BASE_MODEL_PATH'] = os.path.join(
abs_path,
*"../../../../PretrainedModels/AlexNet_ImageNet_Caffe.model".split(
"/"))
# train and test
eval_model = od.train_object_detector(cfg)
eval_results = od.evaluate_test_set(eval_model, cfg)
meanAP = np.nanmean(list(eval_results.values()))
print('meanAP={}'.format(meanAP))
assert meanAP > 0.01
# detect objects in single image
img_path = os.path.join(grocery_path, "testImages",
"WIN_20160803_11_28_42_Pro.jpg")
regressed_rois, cls_probs = od.evaluate_single_image(
eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
assert bboxes.shape[0] == labels.shape[0]
def test_detection_demo(device_id):
if cntk_device(device_id).type() != DeviceKind_GPU:
pytest.skip('test only runs on GPU') # it runs very slow in CPU
try_set_default_device(cntk_device(device_id))
from prepare_test_data import prepare_Grocery_data, prepare_alexnet_v0_model
grocery_path = prepare_Grocery_data()
prepare_alexnet_v0_model()
from FastRCNN.install_data_and_model import create_grocery_mappings
create_grocery_mappings(grocery_path)
from DetectionDemo import get_configuration
import utils.od_utils as od
cfg = get_configuration('FasterRCNN')
cfg["CNTK"].FORCE_DETERMINISTIC = True
cfg["CNTK"].DEBUG_OUTPUT = False
cfg["CNTK"].MAKE_MODE = False
cfg["CNTK"].FAST_MODE = False
cfg.CNTK.E2E_MAX_EPOCHS = 3
cfg.CNTK.RPN_EPOCHS = 2
cfg.CNTK.FRCN_EPOCHS = 2
cfg.IMAGE_WIDTH = 400
cfg.IMAGE_HEIGHT = 400
cfg["CNTK"].TRAIN_E2E = True
cfg.USE_GPU_NMS = False
cfg.VISUALIZE_RESULTS = False
cfg["DATA"].MAP_FILE_PATH = grocery_path
externalData = 'CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY' in os.environ
if externalData:
extPath = os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY']
cfg['BASE_MODEL_PATH'] = os.path.join(extPath, "PreTrainedModels", "AlexNet", "v1", "AlexNet_ImageNet_Caffe.model")
else:
cfg['BASE_MODEL_PATH'] = os.path.join(abs_path, *"../../../../PretrainedModels/AlexNet_ImageNet_Caffe.model".split("/"))
# train and test
eval_model = od.train_object_detector(cfg)
eval_results = od.evaluate_test_set(eval_model, cfg)
meanAP = np.nanmean(list(eval_results.values()))
print('meanAP={}'.format(meanAP))
assert meanAP > 0.01
# detect objects in single image
img_path = os.path.join(grocery_path, "testImages", "WIN_20160803_11_28_42_Pro.jpg")
regressed_rois, cls_probs = od.evaluate_single_image(eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
assert bboxes.shape[0] == labels.shape[0]
def _eval_single_image(self, img_buf):
regressed_rois, cls_probs = self.evaluator.process_image_mem(img_buf)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs,
self.cfg)
# write detection results to output
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(
len(regressed_rois), len(bboxes), len(fg_boxes[0])))
fg = fg_boxes[0]
predictions = []
if len(fg) == 0:
print("Nothing found in current image.")
predictions.append({
"TagId": 0,
"Tag": 'Empty',
"Probability": 1.0,
"Region": {
"Left": 0.0,
"Top": 0.0,
"Width": 0.0,
"Height": 0.0
}
})
else:
for i in fg:
print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
self.cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i],
[int(v) for v in bboxes[i]]))
left, top, right, bottom = [int(v) for v in bboxes[i]]
predictions.append({
"TagId": np.asscalar(labels[i]),
"Tag": self.cfg["DATA"].CLASSES[labels[i]],
"Probability": np.asscalar(scores[i]),
"Region": {
"Left": float(left / _image_width),
"Top": float(top / _image_height),
"Width": float((right - left) / _image_width),
"Height": float((bottom - top) / _image_height)
}
})
return predictions
def run(input_df):
print(str(input_df))
startTime = dt.datetime.now()
# convert input back to image and save to disk
base64ImgString = input_df['image base64 string'][0]
imgPath = base64ToImage(base64ImgString, workingDir)
# load configuration
cfg = getConfiguration(detectorName)
# load model
od.prepareOnly_object_detector(cfg)
eval_model = load_model(os.path.join(workingDir), pretrainnedModelName))
# score image
regressed_rois, cls_probs = od.evaluate_single_image(eval_model, imgPath, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
return toJson(bboxes, labels, scores)
def get_result(filename, eval_model):
names = filename.split('/')
name = names[len(names) - 1]
print(name)
data_path = os.environ['AZUREML_NATIVE_SHARE_DIRECTORY'] + '/output'
if os.path.isdir(data_path) == False:
os.makedirs(data_path)
img_path = ''
if load_file_from_blob(os.environ['STORAGE_ACCOUNT_NAME'], \
os.environ['TESTIMAGESCONTAINER'], filename, data_path + '/' + name) is True:
print(name)
img_path = data_path + '/' + name
print(img_path)
#print('detector_name: {}'.format(os.environ["DETECTOR_NAME"]))
#print('img_path: {}'.format(img_path))
cfg = get_configuration('FasterRCNN') #os.environ["DETECTOR_NAME"])
# detect objects in single image
regressed_rois, cls_probs = evaluate_single_image(eval_model, img_path,
cfg)
bboxes, labels, scores = filter_results(regressed_rois, cls_probs, cfg)
# write detection results to output
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(
len(regressed_rois), len(bboxes), len(fg_boxes[0])))
result = []
for i in fg_boxes[0]:
#print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
#cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i], [int(v) for v in bboxes[i]]))
result.append({
'label': cfg["DATA"].CLASSES[labels[i]],
'score': '%.3f' % (scores[i]),
'box': [int(v) for v in bboxes[i]]
})
return json.dumps(result)
eval_model = od.train_object_detector(cfg)
eval_results = od.evaluate_test_set(eval_model, cfg)
# write AP results to output
for class_name in eval_results:
print('AP for {:>15} = {:.4f}'.format(class_name,
eval_results[class_name]))
print('Mean AP = {:.4f}'.format(np.nanmean(list(eval_results.values()))))
# detect objects in single image
img_path = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
r"../DataSets/Grocery/testImages/WIN_20160803_11_28_42_Pro.jpg")
regressed_rois, cls_probs = od.evaluate_single_image(
eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
# write detection results to output
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(
len(regressed_rois), len(bboxes), len(fg_boxes[0])))
for i in fg_boxes[0]:
print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i],
[int(v) for v in bboxes[i]]))
# visualize detections on image
od.visualize_results(img_path, bboxes, labels, scores, cfg)
# measure inference time
od.measure_inference_time(eval_model, img_path, cfg, num_repetitions=100)
if __name__ == '__main__':
# Currently supported detectors: 'FastRCNN', 'FasterRCNN'
args = sys.argv
detector_name = get_detector_name(args)
cfg = get_configuration(detector_name)
# train and test
eval_model = od.train_object_detector(cfg)
eval_results = od.evaluate_test_set(eval_model, cfg)
# write AP results to output
for class_name in eval_results: print('AP for {:>15} = {:.4f}'.format(class_name, eval_results[class_name]))
print('Mean AP = {:.4f}'.format(np.nanmean(list(eval_results.values()))))
# detect objects in single image
img_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), r"../DataSets/Grocery/testImages/WIN_20160803_11_28_42_Pro.jpg")
regressed_rois, cls_probs = od.evaluate_single_image(eval_model, img_path, cfg)
bboxes, labels, scores = od.filter_results(regressed_rois, cls_probs, cfg)
# write detection results to output
fg_boxes = np.where(labels > 0)
print("#bboxes: before nms: {}, after nms: {}, foreground: {}".format(len(regressed_rois), len(bboxes), len(fg_boxes[0])))
for i in fg_boxes[0]: print("{:<12} (label: {:<2}), score: {:.3f}, box: {}".format(
cfg["DATA"].CLASSES[labels[i]], labels[i], scores[i], [int(v) for v in bboxes[i]]))
# visualize detections on image
od.visualize_results(img_path, bboxes, labels, scores, cfg)
# measure inference time
od.measure_inference_time(eval_model, img_path, cfg, num_repetitions=100)