def get_results_from_automl(filepath):
project_id = "numeric-polygon-283403"
model_id = "ICN2007288218877165568"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Read the file.
with open(filepath, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters, score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.5"}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
results = []
for result in response.payload:
results.append([result.display_name, result.classification.score])
return results
def predict(filePath):
project_id = "762814515048"
model_id = "ICN244084984296505344"
file_path = filePath
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Read the file.
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.7"}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
print("Prediction results:")
results = []
for result in response.payload:
results.append(result.display_name)
results.append(result.classification.score)
print("Predicted class name: {}".format(result.display_name))
print("Predicted class score: {}".format(result.classification.score))
return (results)
def isWearingMask(file_path):
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Read the file.
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.1"}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
#print("Prediction results:")
print(len(response.payload))
for result in response.payload:
print("Predicted class name: {}".format(result.display_name))
print("Predicted class score: {}".format(result.classification.score))
return True if (result.display_name == "with_mask"
and result.classification.score > 0.9999) else False
return False
def predict(content):
"""
Predict labels
"""
project_id = c.PROJECT_ID
model_id = c.MODEL_ID
location = c.LOCATION
predictor = automl.PredictionServiceClient.from_service_account_json(
"service_account.json")
model_full_id = automl.AutoMlClient.model_path(project_id, location,
model_id)
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
request = automl.PredictRequest(name=model_full_id, payload=payload)
response = predictor.predict(request=request)
pred_sum = 0
prediction = {}
for result in response.payload:
prediction[result.display_name] = result.classification.score
pred_sum += result.classification.score
if pred_sum != 0:
for pred in prediction:
prediction[pred] /= pred_sum
return prediction
def predict(project_id, model_id, file_path):
"""Predict."""
# [START automl_vision_classification_predict]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# file_path = "path_to_local_file.jpg"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)
# Read the file.
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.8"}
request = automl.PredictRequest(name=model_full_id, payload=payload, params=params)
response = prediction_client.predict(request=request)
print("Prediction results:")
for result in response.payload:
print("Predicted class name: {}".format(result.display_name))
print("Predicted class score: {}".format(result.classification.score))
def vision_predict(self,
model_id: (str, 'the id of the deployed vision model'),
image: (bytes, 'the image as a byte array'),
score_threshold: float = 0.7):
response_payload = None
try:
model_full_id = self.automl_client.model_path(
self.project_id, self.region, model_id)
payload = {"image": {"image_bytes": image}}
if score_threshold:
params = {"score_threshold": str(score_threshold)}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = self.prediction_client.predict(request=request)
response_payload = response.payload
except Exception:
logger.exception("")
return response_payload
def input_symptoms():
if request.method == 'POST':
try:
travel = int(request.form['travel'])
except:
travel = 0
try:
tiredcough = int(request.form['commonsym'])
except:
tiredcough = 0
try:
breath = int(request.form['majorsym'])
except:
breath = 0
try:
exposure = int(request.form['exposure'])
except:
exposure = 0
try:
image = request.files['image']
image.save('beach1.bmp')
except:
return render_template('index.html', results="No File Found")
file_path = "beach1.bmp"
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.8"}
request2 = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
# 'content' is base-64-encoded image data.
response = prediction_client.predict(request=request2)
for result in response.payload:
var1 = result.display_name
var2 = result.classification
result2 = 'Disease: ', var1, ' Probability of disease: ', var2
result = travel + tiredcough + breath + exposure
if result >= 3:
result = 'You have high chances of being covid positive'
else:
result = 'Please take care of yourself(wear a mask :D)'
return render_template('index.html', results=result, result2=result2)
return None
def predictionCall(file_path_image):
#returns faces detected in image
faces = detectFaces(file_path_image)
count = 0
for face in faces:
count = count + 1
im = Image.open(file_path_image)
xTopLeft = face[0]
yTopLeft = face[1]
xBotRight = face[2]
yBotRight = face[3]
im1 = im.crop((xTopLeft, yTopLeft, xBotRight, yBotRight))
img_path = "Predict" + str(count) + ".jpg"
im1 = im1.save(img_path)
# Read the file.
with open(img_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
params = {"score_threshold": "0.8"}
request = automl.PredictRequest(
name=model_full_id,
payload=payload,
params=params
)
response = prediction_client.predict(request=request)
mask = False
unmask = False
both = False
print("Prediction results:")
for result in response.payload:
if "UnmaskedPeople" == result.display_name:
unmask = True
if "MaskedPeople" == result.display_name:
mask = True
#print("Predicted class name: {}".format(result.display_name))
#print("Predicted class score: {}".format(result.classification.score))
if mask == True and unmask == True:
both = True
if both == True:
print("Person " + str(count) + ": Error. Both Mask and Unmask detected")
elif mask == True:
print("Person " + str(count) + " is wearing mask :)")
else:
print("Person " + str(count) + " is NOT wearing a mask :(")
def get_prediction(img):
with open(img, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
request = automl.PredictRequest(name=model_full_id, payload=payload, params={})
response = prediction_client.predict(request=request)
t = response.payload[0]
if t.display_name == 'negative':
return 1-t.classification.score
else:
return t.classification.score
def predict(filepath):
threshold = "0.1"
with open(filepath, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
params = {"score_threshold": threshold}
request = automl.PredictRequest(
name=model_full_id,
payload=payload,
params=params
)
response = prediction_client.predict(request=request)
return {**{result.display_name.capitalize(): result.classification.score for result in response.payload},
**{'Name': os.path.basename(filepath)}}
def get_prediction(file_path):
project_id = "msds-434-final"
model_id = "ICN7344581542892535808"
# file_path = "uploads/city.png" ## for local image testing
credentials = service_account.Credentials.from_service_account_file("/home/jesse_lybianto/msds-434-final/msds-434-final-f32a0ccc78d5.json")
prediction_client = automl.PredictionServiceClient(credentials=credentials)
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(
project_id, "us-central1", model_id
)
# Read the file.
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.0"}
request = automl.PredictRequest(
name=model_full_id,
payload=payload,
params=params
)
response = prediction_client.predict(request=request)
print(response.payload)
return response.payload
# For non-modular console output
# print("Prediction results:")
# for result in response.payload:
# print("Predicted class name: {}".format(result.display_name))
# print("Predicted class score: {}".format(result.classification.score))
def get_prediction(self, text, model_name=None):
if model_name is None:
model_name = self.model_name
options = ClientOptions(api_endpoint='automl.googleapis.com')
prediction_client = automl_v1.PredictionServiceClient(
client_options=options)
model_full_id = automl.AutoMlClient.model_path(project_id,
"us-central1", model_id)
payload = self.__inline_text_payload(text)
params = {}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
prtt = "Response"
print(prtt)
print(request.payload[0].text_sentiment.sentiment)
return request.payload[
0].text_sentiment.sentiment # waits until request is returned
def home_page():
# from flask import request
if request.method == 'GET':
context = {"done": False}
return render_template('site.html', **context)
else:
# get image content from POST request inputs
file = request.files["myFile"]
image_content = b''
for data in file.stream: # read image as a stream
image_content += data
# google api variables
project_id = "alpine-infinity-290102"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id,
"us-central1", model_id)
image = automl.Image(image_bytes=image_content)
payload = automl.ExamplePayload(image=image)
req = automl.PredictRequest(
name=model_full_id,
payload=payload,
)
response = prediction_client.predict(request=req)
class_ = response.payload[0].display_name
measure = response.payload[0].classification.score
context = {
"done": True,
"guess_mal": class_ == "Malignant",
"class_": class_,
"measure": '{:.2%}'.format(measure)
}
return render_template('site.html', **context)
def produce_automl_results(dir_img_path: str = "",
dir_destination_path: str = ""):
from google.cloud import automl
project_id = "hidden"
model_id = "hidden"
imgs = os.listdir(dir_img_path)
relevant_images = [
os.path.join(dir_img_path, i) for i in imgs if "png" in i
]
prediction_client = automl.PredictionServiceClient()
project_id = "hidden"
model_id = "hidden"
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
file_path = "../../data/005.png"
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
params = {}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
print("Prediction results:")
for result in response.payload:
print("Predicted class name: {}".format(result.display_name))
print("Predicted class score: {}".format(result.classification.score))
def automl_vision(file_path):
"""Predict."""
# [START automl_vision_classification_predict]
#print(file_path)
# autoML JSon 키 설정
#credential_path = r"키.json"
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = credential_path
project_id = "수정"
model_id = "수정"
# 원본 이미지
img = cv2.imread(file_path)
# 원본 이미지 크기
img_height = img.shape[0]
img_width = img.shape[1]
# RGB 색상으로 변환
orig = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# 파일 읽어들이기
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
# params is additional domain-specific parameters.
# score_threshold is used to filter the result
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#predictrequest
params = {"score_threshold": "0.8"}
request = automl.PredictRequest(name=model_full_id,
payload=payload,
params=params)
response = prediction_client.predict(request=request)
tags = []
for result in response.payload:
# 태그로 잡힌 박스 몇 개인지
bounding_box = result.image_object_detection.bounding_box
# normalized vertices로 되어있는 좌표를 실사이즈로 변환 및 직사각형의 네 꼭짓점 좌표를 구함
lu = bounding_box.normalized_vertices[0] # left/up x, y 좌표
rd = bounding_box.normalized_vertices[1] # right/down x, y 좌표
w = rd.x - lu.x
h = rd.y - lu.y
# cropping
cropped_img = orig[int(lu.y * img_height):int((lu.y + h) * img_height),
int(lu.x * img_width):int((lu.x + w) * img_width)]
texts = my_detect_text_mat(
cropped_img) #잘린 이미지들 속 글자 추출하기 위해 my_detect_text_mat() 호출
tags.append(texts[0].description)
return tags
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(
project_id, "us-central1", model_id
)
# Read the file.
with open(file_path, "rb") as content_file:
content = content_file.read()
image = automl.Image(image_bytes=content)
payload = automl.ExamplePayload(image=image)
request = automl.PredictRequest(
name=model_full_id,
payload=payload
)
response = prediction_client.predict(request=request)
print("Prediction results:")
for result in response.payload:
print("Predicted class name: {}".format(result.display_name))
print("Predicted class score: {}".format(result.classification.score))
def request_prediction(file):
# model path
project_id = "241661365506"
model_id = "IOD6459342741137522688"
name = "projects/{}/locations/us-central1/models/{}".format(
project_id, model_id)
prediction_client = automl.PredictionServiceClient.from_service_account_json(
"GCPkeys.json")
# open image file and convert to base64
image = automl.Image(image_bytes=file.read())
payload = automl.ExamplePayload(image=image)
params = {}
request = automl.PredictRequest(name=name, payload=payload, params=params)
# request a prediction
try:
response = prediction_client.predict(request=request)
except:
card = "The Eye is shut. Please try again later."
score = 0
# now translate the prediction to nicer looking text
try:
score = round(response.payload[0].image_object_detection.score, 4)
if response.payload[0].display_name == "chariot":
card = "The Chariot"
elif response.payload[0].display_name == "death":
card = "Death"
elif response.payload[0].display_name == "devil":
card = "The Devil"
elif response.payload[0].display_name == "emperor":
card = "The Emperor"
elif response.payload[0].display_name == "empress":
card = "The Empress"
elif response.payload[0].display_name == "fool":
card = "The Fool"
elif response.payload[0].display_name == "Fortune":
card = "Fortune"
elif response.payload[0].display_name == "hanged":
card = "The Hanged Man"
elif response.payload[0].display_name == "hermit":
card = "The Hermit"
elif response.payload[0].display_name == "hierophant":
card = "The Hierophant"
elif response.payload[0].display_name == "judgment":
card = "Judgment"
elif response.payload[0].display_name == "justice":
card = "Justice"
elif response.payload[0].display_name == "lovers":
card = "The Lovers"
elif response.payload[0].display_name == "magician":
card = "The Magician"
elif response.payload[0].display_name == "moon":
card = "The Moon"
elif response.payload[0].display_name == "priestess":
card = "The Priestess"
elif response.payload[0].display_name == "star":
card = "The Star"
elif response.payload[0].display_name == "strength":
card = "Strength"
elif response.payload[0].display_name == "sun":
card = "The Sun"
elif response.payload[0].display_name == "temperance":
card = "Temperance"
elif response.payload[0].display_name == "tower":
card = "The Tower"
elif response.payload[0].display_name == "world":
card = "The World"
else:
card = "Your future is murky. Try another card."
score = 666
except:
card = "Your future is murky. Try another card."
score = 666
return card, score
