def predict_host(host_csv="./hostHW/host_hwrecord.csv",
predict_type="both",
cpu_weight=0.5,
memory_weight=0.5):
predict(previous_csv=host_csv,
predict_type=predict_type,
cpu_weight=cpu_weight,
memory_weight=memory_weight)
def predict_container(predict_type="both", cpu_weight=0.5, memory_weight=0.5):
if cpu_weight + memory_weight != 1:
raise RuntimeError("Weight Error")
# get all container id
result_conid = get_id()
for id in result_conid:
id = id[:-1]
container_csv = "./containerHW/" + id + "_hwrecord.csv"
predict(previous_csv=container_csv,
predict_type=predict_type,
cpu_weight=cpu_weight,
memory_weight=memory_weight)
return
def predictor():
p = predict()
if request.method == 'POST':
message = request.form['mail']
data = [message]
result = p.prediction(data)
#result = str(result)
#print(result)
#print(type(result))
return render_template('sample.html',
tables=[result.to_html(classes='data')],
titles=result.columns.values)
#return result
return render_template('predict.html')
def predict_attend(request):
"""HTTP Cloud Function.
Args:
request (flask.Request): The request object.
<http://flask.pocoo.org/docs/1.0/api/#flask.Request>
Returns:
The response text, or any set of values that can be turned into a
Response object using `make_response`
<http://flask.pocoo.org/docs/1.0/api/#flask.Flask.make_response>.
"""
request_json = request.get_json(silent=True)
result = pm.predict(request_json)
print('you will be absent at {}!'.format(result))
return (json.dumps(result), 200, {})
def main():
# Parse input arguments
args = parse_inputs()
# We get the image as a FloatTensor
img = process_image(args.image)
# We now have to load the checkpoint and build the model
model = loadcheckpoint(args)
# We will performe the calculation in the select device
device = "cuda:0" if torch.cuda.is_available() and args.gpu else "cpu"
print(f'These computations are performed in {device}')
model.to(device)
# We set the model to evaluation mode (so that we are not using dropout)
model.eval()
with torch.no_grad():
probs,classes = predict(img, model, args.top_k, device)
# Now, if we indicated a category_name:
if args.category_names:
try:
with open(args.category_names, 'r') as f:
cat_to_name = json.load(f)
except FileNotFoundError:
print("The category names file has not been found.")
print("Please introduce a valid file.")
sys.exit("Program terminating.")
classes = [cat_to_name[item] for item in classes]
# Printing out the results
print(f'The {args.top_k} most likely classes of flowers are:')
for key, value in zip(classes, probs):
print(f'Flower: {key}; '
f'Probability: {value}')
# Label mapping
with open(category_names, 'r') as f:
cat_to_name = json.load(f)
# Load the checkpoint
filepath = checkpoint + '/checkpoint.pth'
checkpoint = torch.load(filepath, map_location='cpu')
model = checkpoint["model"]
model.load_state_dict(checkpoint['state_dict'])
# Image preprocessing
np_image = process_image(image_path)
# imshow(np_image)
# Predict class and probabilities
print(
f"Predicting top {top_k} most likely flower names from image {image_path}."
)
probs, classes = predict(np_image, model, top_k, gpu)
classes_name = [cat_to_name[class_i] for class_i in classes]
# print("Flower names: ", classes_name)
# print("Probabilities: ", [round(prob, 3) for prob in probs])
print("\nFlower name (probability): ")
print("---")
for i in range(len(probs)):
print(f"{classes_name[i]} ({round(probs[i], 3)})")
print("")
image_path = result.image_path
saved_model = result.saved_model
top_k = result.top_k
category_names = result.category_names
if top_k == None:
top_k = 5
# load model
reloaded_keras_model = tf.keras.models.load_model(
saved_model, custom_objects={'KerasLayer': hub.KerasLayer})
# predict image
image = np.asarray(Image.open(image_path))
probs, classes = predict(image_path, reloaded_keras_model, top_k)
if category_names != None:
with open(category_names, 'r') as f:
class_names = json.load(f)
names = [str(x + 1) for x in classes]
classes = [class_names.get(name) for name in names]
# print results
print(
'\n********************************************************************************************'
)
print('\nthe {} top classes:'.format(top_k))
for i in range(top_k):
print('\n\u2022 Class: {}'.format(classes[i]),
'\n\u2022 Probability: {:.3%}'.format(probs[i]))
def predict_tweet(json_tweet):
text = json_tweet["text"]
prediction = predict([text])
return prediction
