def classify(uploaded_file: 'SimpleUploadedFile', **options):
"""
Function to classify images based on selected algorithm in settings,
only works in *unix systems*
"""
try:
from imageai.Classification import ImageClassification
except ImportError as e:
logger.warning(
'"ImageClassification" Import not found, please import to use classify functions'
)
raise e
model_options = settings.MODEL_OPTIONS[settings.IMAGE_CLASSIFY_MODEL]
prediction = ImageClassification()
prediction.setModelTypeAsInceptionV3()
prediction.setModelPath(model_options['path'])
prediction.loadModel()
result = {}
new_uploaded_file = compress(uploaded_file, quality=100)
# Write file to tmp to get path
temp = tempfile.NamedTemporaryFile(suffix='.png')
temp.write(new_uploaded_file.read())
temp.seek(0)
predictions, probabilities = prediction.classifyImage(temp.name,
result_count=5)
for eachPrediction, eachProbability in zip(predictions, probabilities):
result[eachPrediction] = eachProbability
return {'classification': result}
def test_recognition_model_densenet():
predictor = ImageClassification()
predictor.setModelTypeAsDenseNet121()
predictor.setModelPath(os.path.join(main_folder, "data-models", "DenseNet-BC-121-32.h5"))
predictor.loadModel()
predictions, probabilities = predictor.classifyImage(image_input=os.path.join(main_folder, main_folder, "data-images", "1.jpg"))
assert isinstance(predictions, list)
assert isinstance(probabilities, list)
assert isinstance(predictions[0], str)
assert isinstance(probabilities[0], float)
def test_recognition_model_inceptionv3():
predictor = ImageClassification()
predictor.setModelTypeAsInceptionV3()
predictor.setModelPath(os.path.join(main_folder, "data-models", "inception_v3_weights_tf_dim_ordering_tf_kernels.h5"))
predictor.loadModel()
predictions, probabilities = predictor.classifyImage(image_input=os.path.join(main_folder, main_folder, "data-images", "1.jpg"))
assert isinstance(predictions, list)
assert isinstance(probabilities, list)
assert isinstance(predictions[0], str)
assert isinstance(probabilities[0], float)
def test_recognition_model_resnet():
predictor = ImageClassification()
predictor.setModelTypeAsResNet50()
predictor.setModelPath(os.path.join(main_folder, "data-models", "resnet50_imagenet_tf.2.0.h5"))
predictor.loadModel()
predictions, probabilities = predictor.classifyImage(image_input=os.path.join(main_folder, main_folder, "data-images", "1.jpg"))
assert isinstance(predictions, list)
assert isinstance(probabilities, list)
assert isinstance(predictions[0], str)
assert isinstance(probabilities[0], float)
class AI:
def __init__(self):
self.execution_path = os.getcwd()
def init_object_detection(self):
#import the model
self.detector = ObjectDetection()
self.detector.setModelTypeAsRetinaNet()
self.detector.setModelPath(
os.path.join(self.execution_path, "resnet50_coco_best_v2.1.0.h5"))
self.detector.loadModel()
def grab_object_tags(self, frame, timestamp):
detections = self.detector.detectObjectsFromImage(
input_image=frame,
output_image_path=frame,
minimum_percentage_probability=30)
tags = []
for eachObject in detections:
t = {
"tag": eachObject["name"],
"probability": eachObject["percentage_probability"],
"location": eachObject["box_points"]
}
tags.append(t)
return {"timestamp": timestamp, "tags": tags}
def init_image_classification(self):
# import the model
self.prediction = ImageClassification()
self.prediction.setModelTypeAsResNet50()
self.prediction.setModelPath(
os.path.join(self.execution_path, "resnet50_imagenet_tf.2.0.h5"))
self.prediction.loadModel()
def grab_image_tags(self, frame, timestamp):
predictions, probabilities = self.prediction.classifyImage(
frame, result_count=10)
for eachPrediction, eachProbability in zip(predictions, probabilities):
print(eachPrediction, " : ", eachProbability)
def detectobjectinimage():
path = os.getcwd()
image_prediction = ImageClassification()
image_prediction.setModelTypeAsResNet50()
image_prediction.setModelPath(
os.path.join(path, "resnet50_imagenet_tf.2.0.h5"))
image_prediction.loadModel()
predictions, percentage_probabilities = image_prediction.classifyImage(
os.path.join(path, "/home/akwa/PycharmProjects/remindme/img.jpg"),
result_count=10)
for eachPrediction, eachProbability in zip(predictions,
percentage_probabilities):
print(eachPrediction, " : ", eachProbability)
result = "Cup wasn't detected, hence, user hasn't drank water today"
vampire = 'Raid come to our aid, we are dying!!!'
if eachPrediction == "mosquito_net":
detection_window(vampire)
break
import os
from imageai.Classification import ImageClassification
# get current directory
execution_path = os.getcwd()
prediction = ImageClassification()
prediction.setModelTypeAsMobileNetV2()
prediction.setModelPath(os.path.join(execution_path, "mobilenet_v2.h5"))
prediction.loadModel()
predictions, probabilities = prediction.classifyImage(os.path.join(
execution_path, "giraffe.jpg"),
result_count=5)
for eachPrediction, eachProbability in zip(predictions, probabilities):
print(eachPrediction, " : ", eachProbability)
from imageai.Classification import ImageClassification
import os
executionpath = os.getcwd()
print(executionpath)
detection = ImageClassification()
detection.setModelTypeAsResNet50()
detection.setModelPath(executionpath + "/resnet50_imagenet_tf.2.0.h5")
detection.loadModel()
detections, percentageprobabilites = detection.classifyImage("Testimage.jpg",
result_count=5)
for Index in range(len(detections)):
print(detections[Index], ":", percentageprobabilites[Index])
from imageai.Classification import ImageClassification
import os
execution_path = os.getcwd()
prediction = ImageClassification()
prediction.setModelTypeAsDenseNet121()
prediction.setModelPath(os.path.join(execution_path, "DenseNet-BC-121-32.h5"))
prediction.loadModel()
predictions, probabilities = prediction.classifyImage(os.path.join(
execution_path + "/images", "1.jpg"),
result_count=5)
for eachPrediction, eachProbability in zip(predictions, probabilities):
print(eachPrediction, " : ", eachProbability)
