I have been developing a program for my school project which recognizes numbers. For that I have used Python, Keras and the MNIST Dataset. This is the code I used to train it:
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Convolution2D, MaxPooling2D, Activation, AveragePooling2D
from keras import backend as K
import matplotlib.pyplot as plt
import matplotlib
batch_size = 32
num_classes = 10
epochs = 10
img_rows, img_cols = 28, 28
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Convolution2D(6, (5, 5), input_shape=input_shape))
model.add(Activation('sigmoid'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(12, (5, 5)))
model.add(Activation('sigmoid'))
model.add(AveragePooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(192))
model.add(Dense(10))
model.add(Activation('sigmoid'))
model.add(Dense(10))
model.add(Activation('softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
hist = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
model.save('model3.h5')
train_loss = hist.history['loss']
val_loss = hist.history['val_loss']
train_acc = hist.history['acc']
val_acc = hist.history['val_acc']
xc = range(epochs)
plt.figure(1,figsize=(7,5))
plt.plot(xc,train_loss)
plt.plot(xc,val_loss)
plt.xlabel('num of Epochs')
plt.ylabel('loss')
plt.title('train_loss vs val_loss')
plt.grid(True)
plt.legend(['train','val'])
print(plt.style.available) # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])
plt.figure(2,figsize=(7,5))
plt.plot(xc,train_acc)
plt.plot(xc,val_acc)
plt.xlabel('num of Epochs')
plt.ylabel('accuracy')
plt.title('train_acc vs val_acc')
plt.grid(True)
plt.legend(['train','val'],loc=4)
#print plt.style.available # use bmh, classic,ggplot for big pictures
plt.style.use(['classic'])
plt.show()
I saved the model under the name model3.h5. However, in another program I wrote, I was trying to predict with the model I saved the numbers I entered in Paint. I had 10 pictures (0-9) and while predicting the model predicted that all numbers are number 8, which is of course wrong.
However, during training, accuracy was close to 98.5% and the loss was less than 0.1. Am I doing something wrong?
Here is the code that I run for predicting it on unseen data. It resizes the picture to 28 columns and 28 rows so it can run on my CNN.
This is my first project on Convolutional Neural Networks and I don't know "some extra techniques" that could help me do better on the unseen data.
I tried some different architectures as well (doing convolutional layers with max pooling and relu activation functions, then adding full connected layers) but the result was still the same. I also tried to set it to 100 or 200 epochs, still no use...
import os, cv2
import numpy as np
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split
from keras import backend as K
from keras.models import load_model
K.set_image_dim_ordering('tf')
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam
PATH = os.getcwd()
data_path = PATH + '\myNumbers'
data_dir_list = os.listdir(data_path) #direktoriji unutra
img_data = []
for file in data_dir_list:
test_image = cv2.imread(data_path + "\\" + file)
test_image = cv2.cvtColor(test_image, cv2.COLOR_RGB2GRAY)
test_image = cv2.resize(test_image,(28,28))
test_image = np.array(test_image)
test_image = test_image.astype('float32')
test_image /= 255
print (test_image.shape)
test_image= np.expand_dims(test_image, axis=3)
test_image= np.expand_dims(test_image, axis=0)
print (test_image.shape)
img_data.append(test_image)
model = load_model("model3.h5")
for img in img_data:
print(model.predict(img))
print(model.predict_classes(img))
Related
I am new to machine learning and I am currently working on Prediction problem. I have provided the link for an excel spreadsheet that has few columns of data.
https://drive.google.com/file/d/1fWf6dX8kOCRB3GpX42AF6UvTmd0g9zXp/view?usp=sharing
I was trying to predict the column F values based column A to E values. The code for which is given below
import numpy as np
import pandas as pn
from keras.layers import Dense, Activation
from keras.models import Sequential
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import linear_model
import matplotlib.pyplot as plt
dataset = pn.read_excel(r"G:\Machine learning\data\database.xlsx", "Sheet5")
dataset.columns = ['A','B','C','D','E','F']
print (dataset)
#check= dataset.iloc[0:,3 :13]
X = dataset.iloc[0:,0 :5]
print(X)
Y = dataset.iloc[0:, 5 :6]
print(Y)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.15, random_state = 0)
print(X_test)
print(Y_test)
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
#
model = Sequential()
##
### Adding the input layer and the first hidden layer
model.add(Dense(32, activation = 'relu', input_dim = 5, kernel_initializer='normal'))
##
### Adding the second hidden layer
model.add(Dense(units = 16, activation = 'relu'))
model.add(Dense(units = 64, activation = 'relu'))
model.add(Dense(units = 8, activation = 'relu'))
model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 8, activation = 'linear'))
###
#### Adding the third hidden layer
#model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 16, activation = 'relu'))
#model.add(Dense(units = 16, activation = 'relu'))
##
### Adding the output layer
model.add(Dense(units = 1))
##
model.add(Dense(units = 1))
##
model.add(Dense(1))
### Compiling the ANN
model.compile(optimizer = 'nadam', loss = 'mean_squared_error',metrics= ['accuracy'])
##
### Fitting the ANN to the Training set
history = model.fit(X_train, Y_train, epochs=125, batch_size=5, verbose=1, validation_split=0.1)
##
y_pred = model.predict(X_test)
##
y_pred1 = model.predict(X_train)
print (y_pred1)
Y_test.reset_index(drop= True, inplace= True)
print (Y_train)
Y_train.reset_index(drop= True, inplace= True)
plt.plot(y_pred1)
plt.plot(Y_train)
plt.show()
plt.plot(y_pred)
plt.plot(Y_test)
plt.show()
print (y_pred)
print (Y_test)
plt.plot((Y_test-y_pred)*100/Y_test)
plt.show()
The fit I get from this code is shown below.
Fit
Now when I predict, the error is huge in some cases as shown below
Prediction
Can anyone guide me on improvising the code so as to get a better prediction?

For a small dataset you have provided, it might be the case that your neural network model is too complicated (4 hidden layers and maximum 64 neurons).
What you can try is manually decreasing the amount of layers to see if the accuracy raises. But in the future, if you would like to more practically tune the hyperparameters or optimize your model parameters, you should consider using methods such as random/grid search, cross validation, and regularization.
Random Search: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html
I'm trying to train my model with Keras and I'm taking this online course from udemy. Now everything works fine but when I try to fit the ANN to the training set it gives the following error. everything works fine but when I EXECUTE this last line it gives the error.
It should work fine without this error or is there any other way to fit the ANN to the training set?
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
dataset = pd.read_csv('Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
labelencoder_X_2 = LabelEncoder()
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categorical_features = [1])
X = onehotencoder.fit_transform(X).toarray()
X = X[:, 1:]
from sklearn.model_selection import train_test_split
X_train , y_train , X_test, y_test = train_test_split(X,y, test_size = 0.2 , random_state = 0)
#convert X_test into a 'numpy' array to acoid valur error for 1D array
X_test = np.reshape(y, (-1,1))
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.fit_transform(X_test)
import keras
from keras.models import Sequential
from keras.layers import Dense
#initializing the ANN
classifier = Sequential()
#adding the input layer and the first hidden layer
classifier.add(Dense(units =6, kernel_initializer = 'uniform' , activation = 'relu', input_dim =11 ))
#adding the second layer
classifier.add(Dense(units = 6 , kernel_initializer = 'uniform' , activation = 'relu'))
#adding the output layer
classifier.add(Dense(units = 1 , kernel_initializer = 'uniform' , activation = 'sigmoid'))
#compiling the ANN
classifier.compile(optimizer = 'adam' , loss = 'binary_crossentropy', metrics = ['accuracy'])
# 'optimizer' is the algorithm that u wanna use for the wights adjustments
#fitting the ann to the trainging set
classifier.fit(X_train , y_train , batch_size =10 , epochs = 100 )
It seems that input_shape is not set correctly.
from docs:
Input shape
nD tensor with shape: (batch_size, ..., input_dim). The most common
situation would be a 2D input with shape (batch_size, input_dim).
In your case input_shape=(X_train.shape[1],)
Try this:
#initializing the ANN
classifier = Sequential()
#adding the input layer and the first hidden layer
classifier.add(Dense(units=6,
kernel_initializer='uniform',
activation='relu',
input_shape=(X_train.shape[1],))
...
I am trying to predict a digit by using a keras example, when i trained my model everything is fine and the accuracy of test data is very good, but when i want to predict a digit i have some problem with the match of dimensions , i tryed to change the dimension of the digit but it still the same error .
here is my code :
main.py:
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.optimizers import Adam
from keras.layers.convolutional import MaxPooling2D
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
from keras import backend as K
# Read training and test data files
train = pd.read_csv("C:/Users/GOT/Desktop/Arabic Handwritten Digits Dataset CSV/csvTrainImages 60k x 784.csv").values
test = pd.read_csv("C:/Users/GOT/Desktop/Arabic Handwritten Digits Dataset CSV/csvTestImages 10k x 784.csv").values
train_label = pd.read_csv("C:/Users/GOT/Desktop/Arabic Handwritten Digits Dataset CSV/csvTrainLabel 60k x 1.csv").values
test_label = pd.read_csv("C:/Users/GOT/Desktop/Arabic Handwritten Digits Dataset CSV/csvTestLabel 10k x 1.csv").values
print(train.shape)
#Reshape and normalize training data
trainX = train[:, 0:].reshape(train.shape[0],1,28, 28).astype( 'float32' )
X_train = trainX / 255.0
y_train = train_label[:, 0]
# print(y_train.shape)
#Reshape and normalize test data
testX = test[:,0:].reshape(test.shape[0],1, 28, 28).astype( 'float32' )
X_test = testX / 255.0
y_test = test_label[:,0]
# print(y_test.shape)
#one hot encode
from keras.utils import np_utils
number_of_classes = 10
y_train = np_utils.to_categorical(y_train, number_of_classes)
y_test = np_utils.to_categorical(y_test, number_of_classes)
model = Sequential()
K.set_image_dim_ordering('th')
model.add(Conv2D(30, 5, 5, border_mode= 'valid' , input_shape=(1, 28, 28),activation= 'relu' ))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(15, 3, 3, activation= 'relu' ))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation= 'relu' ))
model.add(Dense(50, activation= 'relu' ))
model.add(Dense(10, activation= 'softmax' ))
# # Compile model
model.compile(loss= 'categorical_crossentropy' , optimizer= 'adam' , metrics=[ 'accuracy' ])
model.fit(X_train, y_train,
epochs=20,
batch_size= 160)
model.summary()
model.save('modelRasool.h5')
score = model.evaluate(X_test, y_test, batch_size=128)
print("The Accuracy and the Loss :")
print(score)
teset_predict.py
from keras.models import load_model
from PIL import Image
import numpy as np
model = load_model('C:/Users/GOT/PycharmProjects/test/modelRasool.h5')
for index in range(2):
img = Image.open('data/' + str(index) + '.png').convert("L")
img = img.resize((28,28))
im2arr = np.array(img)
im2arr = im2arr.reshape(1,28,28,1)
# Predicting the Test set results
y_pred = model.predict(im2arr)
print(y_pred)
the Error :
ValueError: Error when checking input: expected conv2d_1_input to have shape (1, 28, 28) but got array with shape (28, 28, 1)
please help me
it's easy your shape input need be (1 ,1 28,28)
im2arr = np.array(img)
im2arr = im2arr.reshape(1,1,28,28)
I am beginner in machine learning. I am making a CNN model using keras to detect pest from leaf image. During training the data, memory exceed and I was unable to train. I have used kaggle/Google Collab but in both I have memory probelm.
I was suggested to use Data Generator, but while trying to do, I was unable to do. Is there any other way to efficiently train or any example whether data generator is used(Have seen many examples but have problem while adding.
import numpy as np
import pickle
import cv2
from os import listdir
from sklearn.preprocessing import LabelBinarizer
from keras.models import Sequential
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.layers.core import Activation, Flatten, Dropout, Dense
from keras import backend as K
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
from keras.preprocessing import image
from keras.preprocessing.image import img_to_array
from sklearn.preprocessing import MultiLabelBinarizer
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
EPOCHS = 25
INIT_LR = 1e-3
BS = 32
default_image_size = tuple((256, 256))
image_size = 0
directory_root = 'PlantVillage/'
width=256
height=256
depth=3
#Function to convert images to array
def convert_image_to_array(image_dir):
try:
image = cv2.imread(image_dir)
if image is not None:
image = cv2.resize(image,default_image_size)
return img_to_array(image)
else:
return np.array([])
except Exception as e:
print(f"Error : {e}")
return None
image_list, label_list = [], []
try:
print("[INFO] Loading images ...")
root_dir = listdir(directory_root)
#Looping inside root_directory
for directory in root_dir :
# remove .DS_Store from list
if directory == ".DS_Store" :
root_dir.remove(directory)
for plant_folder in root_dir :
plant_disease_folder_list = listdir(f"{directory_root}/{plant_folder}")
print(f"[INFO] Processing {plant_folder} ...")
#looping in images
for disease_folder in plant_disease_folder_list :
# remove .DS_Store from list
if disease_folder == ".DS_Store" :
plant_disease_folder_list.remove(plant_folder)
#If all data taken not able to train
for images in plant_disease_folder_list:
image_directory = f"{directory_root}/{plant_folder}/{images}"
if image_directory.endswith(".jpg") == True or image_directory.endswith(".JPG") == True:
image_list.append(convert_image_to_array(image_directory))
label_list.append(plant_folder)
print("[INFO] Image loading completed")
except Exception as e:
print(f"Error : {e}")
#Get Size of Processed Image
image_size = len(image_list)
#Converting multi-class labels to binary labels(belong or doesnot belong in the class)
label_binarizer = LabelBinarizer()
image_labels = label_binarizer.fit_transform(label_list)
#Saving label binarizer instance using pickle
pickle.dump(label_binarizer,open('label_transform.pkl','wb'))
n_classes = len(label_binarizer.classes_)
print(label_binarizer.classes_)
#Normalizing image from [0,255] to [0,1]
np_image_list = np.array(image_list, dtype = np.float)/255.0
#Splitting data into training and test set 80:20
print('Splitting data to train,test')
x_train, x_test, y_train, y_test = train_test_split(np_image_list, image_labels, test_size=0.2, random_state = 42)
#Creating image generator object which performs random rotations, shifs,flips,crops,sheers
aug = ImageDataGenerator(
rotation_range = 25, width_shift_range=0.1,
height_shift_range=0.1, shear_range=0.2,
zoom_range=0.2, horizontal_flip = True,
fill_mode="nearest")
model = Sequential()
inputShape = (height, width, depth)
chanDim = -1
if K.image_data_format() == "channels_first":
inputShape = (depth, height, width)
chanDim = 1
model.add(Conv2D(32, (3, 3), padding="same",input_shape=inputShape))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(3, 3)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(64, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(128, (3, 3), padding="same"))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(32))
model.add(Activation("relu"))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(n_classes))
model.add(Activation("softmax"))
#model.summary()
#Compiling the CNN
opt = Adam(lr= INIT_LR, decay= INIT_LR/EPOCHS)
#distribution
model.compile(loss="binary_crossentropy", optimizer = opt, metrics=["accuracy"])
#training the Model
print("Training Model.....")
history = model.fit_generator(
aug.flow(x_train, y_train, batch_size= BS),
validation_data = (x_test, y_test),
steps_per_epoch = len(x_train) // BS,
epochs = EPOCHS, verbose = 1
)
You find code in this link too.
The problem here is that you have loaded the complete data in the workspace, which fills lots of memory and create lots of extra load on the processes.
One thing you can used is data-generator with flow_from_directory, which allows you to define the augmentation and pre-processing pipeline along with data on the fly. The advantage here is that workspace doesn't have extra load of data. You can find an example here.
Feel free to ask question.
You can convert images into binary format which is understandable by tensorflow called "tfrecord" format.
Please refer to the below links
https://www.tensorflow.org/guide/datasets http://www.machinelearninguru.com/deep_learning/tensorflow/basics/tfrecord/tfrecord.html
I'm trying to do deployment from Keras to opencv c++.
I trained a simple CNN with the mnist dataset (my example is a modified Keras example). After training I exposed tensorflow graph from Keras backend and saved the model and the graph.
tensorFlowSession = K.get_session()
tf.saved_model.simple_save(tensorFlowSession, newpath + "/TensorFlow", inputs={"x": x}, outputs={"y": y})
tf.train.write_graph(tensorFlowSession.graph_def,newpath + "/TensorFlow", "trainGraph_def.pbtxt")
Then I tried to load the saved model using opencv in python, I started with opencv in python, however I experience a similar error using opencv in c++.
net = cv.dnn.readNet(newpath + '/TensorFlow/' + 'saved_model.pb', newpath + '/TensorFlow/' + 'trainGraph.pbtxt')
The problem is the opencv failed to load tensorflow graph, I get an error-
[libprotobuf ERROR /io/opencv/3rdparty/protobuf/src/google/protobuf/wire_format_lite.cc:629] String field 'tensorflow.FunctionDef.Node.ret' contains invalid UTF-8 data when parsing a protocol buffer. Use the 'bytes' type if you intend to send raw bytes.
Saving and loading a tensorflow graph using opencv should be rather straightforward, what am I missing here? See attached my code.
'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
import tensorflow as tf
import datetime
import cv2 as cv
from pathlib import Path
import numpy as np
from os import listdir
from os.path import isfile, join
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
batch_size = 128
num_classes = 10
epochs = 1
# input image dimensions
img_rows, img_cols = 28, 28
# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
# Save as tensor flow graph
# Save the model to pd file
exportModelDir = '/home/iaiai/Documents/Shahar/DataSets/TrainedNetworks/MnistKeras/'
newpath = exportModelDir + str(datetime.datetime.now())
print ("output dir", newpath)
if not os.path.exists(newpath):
os.makedirs(newpath)
x = tf.placeholder(dtype=tf.float32, shape=input_shape)
y = tf.placeholder(dtype=tf.float32, shape=num_classes)
tensorFlowSession = K.get_session()
tf.saved_model.simple_save(tensorFlowSession, newpath + "/TensorFlow", inputs={"x": x}, outputs={"y": y})
# with tf.Session() as sess:
# tf.train.Saver(tf.trainable_variables()).save(sess, newpath + "/TensorFlow/" + 'saveTrainableVariables')
if not os.path.exists(newpath + "/TensorFlow/" + 'saveTrainableVariables/'):
os.makedirs(newpath + "/TensorFlow/" + 'saveTrainableVariables/')
tf.train.Saver(tf.trainable_variables()).save(tensorFlowSession, newpath + "/TensorFlow/saveTrainableVariables/" + 'saveTrainableVariables')
# Write graph in tensorflow format
tf.train.write_graph(tensorFlowSession.graph_def,newpath + "/TensorFlow", "trainGraph_def.pbtxt")
tf.train.write_graph(tensorFlowSession.graph,newpath + "/TensorFlow", "trainGraph.pbtxt")
tf.train.write_graph(tensorFlowSession.graph_def,newpath + "/TensorFlow", "trainGraph_def_notAsText.pbtxt", False)
# now try to load the tensorflow graph from opencv python module
net = cv.dnn.readNet(newpath + '/TensorFlow/' + 'saved_model.pb', newpath + '/TensorFlow/' + 'trainGraph.pbtxt')
here is the full error message
[libprotobuf ERROR /io/opencv/3rdparty/protobuf/src/google/protobuf/wire_format_lite.cc:629] String field 'tensorflow.FunctionDef.Node.ret' contains invalid UTF-8 data when parsing a protocol buffer. Use the 'bytes' type if you intend to send raw bytes.
Traceback (most recent call last):
File "/snap/pycharm-community/79/helpers/pydev/pydevd.py", line 1664, in <module>
main()
File "/snap/pycharm-community/79/helpers/pydev/pydevd.py", line 1658, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "/snap/pycharm-community/79/helpers/pydev/pydevd.py", line 1068, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/snap/pycharm-community/79/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/iaiai/Documents/Shahar/Project2/MnistKerasExport/mnist_cnn.py", line 106, in <module>
net = cv.dnn.readNet(newpath + '/TensorFlow/' + 'saved_model.pb', newpath + '/TensorFlow/' + 'trainGraph.pbtxt')
cv2.error: OpenCV(3.4.2) /io/opencv/modules/dnn/src/tensorflow/tf_io.cpp:44: error: (-2:Unspecified error) FAILED: ReadProtoFromBinaryFile(param_file, param). Failed to parse GraphDef file: /home/iaiai/Documents/Shahar/DataSets/TrainedNetworks/MnistKeras/2018-09-06 08:35:34.025216/TensorFlow/saved_model.pb in function 'ReadTFNetParamsFromBinaryFileOrDie'
The same with my net but with *.pbtxt file.
FAILED: ReadProtoFromTextFile(param_file, param). Failed to parse GraphDef file: ./output_graph.pbtxt" char *
It seems OK with *.pb and here the code to generate it:
output_nodes = [n.name for n in tf.get_default_graph().as_graph_def().node]
# Freeze the graph
frozen_gdef = tf.graph_util.convert_variables_to_constants(
sess,
sess.graph_def,
output_nodes)
# Save the frozen graph
with open('./model/output_graph.pb', 'wb') as f:
f.write(frozen_gdef.SerializeToString())
Hope that help!
Let me known if it is ok with your *.pbtxt