2023-01-09 06:36:33 (1, 224, 224, 3) 2023-01-09 06:36:38 2023-01-09 06:36:38.430361: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
I want to recognize fruits with python and I encountered such an error. !!!
2023-01-09 12:02:24 2023-01-09 12:02:24.465445: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
2023-01-09 12:12:15 Mon Jan 9 12:12:14 2023 - *** HARAKIRI ON WORKER 2 (pid: 24, try: 1) ***
2023-01-09 12:12:15 Mon Jan 9 12:12:14 2023 - HARAKIRI !!! worker 2 status !!!
2023-01-09 12:12:15 Mon Jan 9 12:12:14 2023 - HARAKIRI [core 0] 10.0.0.75 - POST /neyedinanaliz since 1673265733
2023-01-09 12:12:15 Mon Jan 9 12:12:14 2023 - HARAKIRI !!! end of worker 2 status !!!
2023-01-09 12:12:15 DAMN ! worker 2 (pid: 24) died, killed by signal 9 :( trying respawn ...
2023-01-09 12:12:15 Respawned uWSGI worker 2 (new pid: 34)
2023-01-09 12:12:15 spawned 2 offload threads for uWSGI worker 2
from flask import Flask, request from flask_restful import Api, Resource import pandas as pd from PIL import Image import keras from keras import backend as K from keras.layers.core import Dense, Flatten from keras.preprocessing.image import ImageDataGenerator from keras.utils import img_to_array from flask import jsonify import io import numpy as np import base64 import tensorflow as tf from tensorflow.keras import applications from keras import applications from tensorflow.keras.models import Sequential
import requests
#open('model_weights.h5', 'wb').write(r.content)
app = Flask(__name__)
api = Api(app)
global image
def preprocess_image(image, target_size):
if image.mode != "RGB":
image = image.convert("RGB")
image = image.resize(target_size)
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
print(np.shape(image))
return image
def get_model():
global model
global graph
vgg16_model = applications.vgg16.VGG16()
model = tf.keras.Sequential()
for i in vgg16_model.layers:
model.add(i)
for layer in model.layers:
layer.trainable = False
model.add(Dense(4, activation='softmax'))
model.make_predict_function('model_weights.h5')
graph = tf.compat.v1.get_default_graph()
print("Model loaded!")
print(" Loading Keras model...")
get_model()
import csv
csvFile = 0;
with open('/home/iamonuryilmaz/mysite/csvornek.csv', mode ='r')as file:
csvFile = csv.reader(file)
for lines in csvFile:
fileList = lines
class NeYedim(Resource):
def get(self):
data = {
'prediction': {
'get' : 'get işlemi',
}
}
print(data)
return {'data' : data}, 200
#post işlemi
def post(self):
name = request.form['name']
encoded = request.form['image']
decoded = base64.b64decode(encoded)
decode = io.BytesIO(decoded)
image = Image.open(decode)
image.save("/home/iamonuryilmaz/mysite/picture.jpg")
image = Image.open("/home/iamonuryilmaz/mysite/picture.jpg")
processed_image = preprocess_image(image, target_size=(224, 224))
with graph.as_default():
vgg16_model = applications.vgg16.VGG16()
model = tf.keras.Sequential()
for i in vgg16_model.layers:
model.add(i)
for layer in model.layers:
layer.trainable = False
model.add(Dense(4, activation='softmax'))
model.load_weights('/home/iamonuryilmaz/mysite/model_weights.h5')
prediction = model.predict(processed_image).tolist()
prediction_max = max(prediction[0])
print(prediction_max)
id = -1
sizeOfDemoList = len(fileList)
for i in range(sizeOfDemoList):
if(prediction[0][i]==prediction_max):
id=i
print(id)
data = {
'prediction': {
'name' : name,
'post' : 'post işlemi',
'sonuc': fileList[0]
}
}
print(data)
return {'data' : data}, 200
# Add URL endpoints
api.add_resource(NeYedim, '/neyedinanaliz')
if __name__ == '__main__':
# app.run(host="0.0.0.0", port=5000)
app.run()