My accuracy is zero for all the 15 epochs in spite of using multiple Conv2D and Max Pooling Layers. I am using ImageDataGenerator for Data Augmentation.
Complete code is given below:
# importing all the required libraries
import tensorflow as tf
from tensorflow.keras.layers import Dense, Conv2D, Flatten, MaxPool2D, Dropout
from tensorflow.keras.models import Sequential
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
# Loading the Data from the in built library
(train_images, train_labels), (test_images, test_labels) = cifar10.load_data()
# Normalize the Pixel Data
train_images = train_images/255.0
test_images = test_images/255.0
# Instantiate the Image Data Generator Class with the Data Augmentation
datagen = ImageDataGenerator(width_shift_range = 0.2, height_shift_range = 0.2,
rotation_range = 20, horizontal_flip = True,
vertical_flip = True, validation_split = 0.2)
# Apply the Data Augmentation to the Training Images
datagen.fit(train_images)
# Create the Generator for the Training Images
train_gen = datagen.flow(train_images, train_labels, batch_size = 32,
subset = 'training')
# Create the Generator for the Validation Images
val_gen = datagen.flow(train_images, train_labels, batch_size = 8,
subset = 'validation')
num_classes = 10
# One Hot Encoding of Labels using to_categorical
train_labels = to_categorical(train_labels, num_classes)
test_labels = to_categorical(test_labels, num_classes)
img_height = 32
img_width = 32
# Building the Keras Model
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPool2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPool2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
#model.add(Dropout(rate = 0.2))
model.add(Dense(units = num_classes, activation = 'softmax'))
model.summary()
model.compile(loss = 'categorical_crossentropy', optimizer = 'adam',
metrics = ['accuracy'])
steps_per_epoch = len(train_images) * 0.8//32
history = model.fit(train_gen, validation_data = val_gen,
steps_per_epoch = steps_per_epoch, epochs = 15)
Your problem is you ran this code
train_gen = datagen.flow(train_images, train_labels, batch_size = 32,
subset = 'training')
# Create the Generator for the Validation Images
val_gen = datagen.flow(train_images, train_labels, batch_size = 8,
subset = 'validation')
but only after this did you convert the labels to categorical. So take the code
num_classes = 10
# One Hot Encoding of Labels using to_categorical
train_labels = to_categorical(train_labels, num_classes)
test_labels = to_categorical(test_labels, num_classes)
and place it PRIOR to the train_gen and val_gen code. On a finer point you have the code
datagen.fit(train_images)
You only need to fit the generator if you have any of the parameters
featurewise_center, samplewise_center, featurewise_std_normalization, or
samplewise_std_normalization set to true.
Transform your label to one hot right before the .flow.
...
# One Hot Encoding of Labels using to_categorical
train_labels = to_categorical(train_labels, num_classes)
test_labels = to_categorical(test_labels, num_classes)
# Create the Generator for the Training Images
train_gen = datagen.flow(train_images, train_labels, batch_size = 32,
subset = 'training')
# Create the Generator for the Validation Images
val_gen = datagen.flow(train_images, train_labels, batch_size = 8,
subset = 'validation')
...
Related
enter code here
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import MaxPooling2D
classifier = Sequential()
classifier.add(Convolution2D(32,(3,3),input_shape = (64,64,3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))
classifier.add(Convolution2D(32,(3,3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))
classifier.add(Flatten())
classifier.add(Dense(units=32,activation = 'relu'))
classifier.add(Dense(units=64,activation = 'relu'))
classifier.add(Dense(units=128,activation = 'relu'))
classifier.add(Dense(units=256,activation = 'relu'))
classifier.add(Dense(units=256,activation = 'relu'))
classifier.add(Dense(units=6,activation = 'softmax'))
classifier.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255, # To rescaling the image in range of [0,1]
shear_range = 0.2, # To randomly shear the images
zoom_range = 0.2, # To randomly zoom the images
horizontal_flip = True) # for randomly flipping half of the images
horizontally
test_datagen = ImageDataGenerator(rescale = 1./255)
print("\nTraining the data...\n")
training_set = train_datagen.flow_from_directory('train',
target_size=(64,64),
batch_size=12, #Total no. of batches
class_mode='categorical')
test_set = test_datagen.flow_from_directory('test',
target_size=(64,64),
batch_size=12,
class_mode='categorical')
classifier.fit_generator(training_set,
steps_per_epoch=len(training_set), # Total training images
epochs = 20, # Total no. of epochs
validation_data = test_set,
validation_steps = len(test_set)) # Total testing images
classifier.save("model.h5")
#Prediction
classes = ['Fresh Apple','Fresh Banana','Fresh Orange','Rotten Apple','Rotten Banana','Rotten
Orange']
from keras.preprocessing import image
from keras.models import load_model
import numpy as np
new_model = load_model('model.h5')
filename = 'a1.jpeg'
new_model.summary()
test_image = image.load_img('images\\a1.jpg',target_size=(64,64))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
result = new_model(test_image)
result1 = result[0]
for i in range(6):
if result1[i] == 1.:
break;
prediction = classes[i]
print(prediction)
My model is giving the same output for any input. The errors and warnings have been removed but the output still remains the same. Earlier the model was giving same value 'A'(example) before removing Warnings and after removing Warnings, the model is giving same value 'B'. I don't know where is the problem in my code whether it is in model or whether it is in #Prediction.
A couple of things. In your generators you set a batch size of 12. then in model.fit you have steps_per_epoch=len(training_set). This means you will go through your training set 12 times per epoch. I usually leave steps per epoch and validation steps as None. model.fit will determine the value internally but if you want to then set
steps_per_epoch = int(len(train_set/batch_size) + 1
validation_steps= int(len(test_set/batch_size) +1
Now in predictions. You scaled your train and test images by 1/255. You need to do the same for images you wish to predict. So right after the code to expand dimension add code
test_image=test_image/255
enter code here
from tensorflow import keras
classifier = keras.Sequential()
classifier.add(keras.layers.Convolution2D(16,kernel_size=(3,3),input_shape = (64,64,3),activation =
'relu'))
classifier.add(keras.layers.MaxPooling2D(pool_size = (2, 2)))
classifier.add(keras.layers.Convolution2D(32,kernel_size=(3, 3),activation = 'relu'))
classifier.add(keras.layers.MaxPooling2D(pool_size = (2, 2)))
#classifier.add(keras.layers.BatchNormalization())
classifier.add(keras.layers.Convolution2D(64,kernel_size=(3, 3),activation = 'relu'))
classifier.add(keras.layers.MaxPooling2D(pool_size = (2, 2)))
classifier.add(keras.layers.Dropout(0.2))
classifier.add(keras.layers.Flatten())
classifier.add(keras.layers.Dense(128, activation = 'relu'))
classifier.add(keras.layers.Dense( 1, activation = 'sigmoid'))
# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Part 2 - Fitting the CNN to the images
from keras_preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory(r'C:\Users\KIIT\Desktop\Deep Learning\dataset2\Training_set',
target_size = (64, 64),
batch_size = 8,
class_mode = 'binary')
test_set = test_datagen.flow_from_directory(r'C:\Users\KIIT\Desktop\Deep Learning\dataset2\Test_set',
target_size = (64, 64),
batch_size = 8,
class_mode = 'binary')
classifier.fit_generator(training_set,
steps_per_epoch =2140,
epochs = 30,
validation_data = test_set,
validation_steps = 90)
import numpy as np
from keras_preprocessing import image
test_image=image.load_img(r'D:\IDM DOWNLOADS\Data Set A-Z DL\Convolutional_Neural_Networks\dataset\single_prediction\shifaface6.jpg',target_size=(64,64))
test_image=image.array_to_img(test_image)
test_image=np.expand_dims(test_image,axis=0)
result=classifier.predict(test_image)
training_set.class_indices
if result[0][0]==1:
prediction='Shifa'
else:
prediction='Rishav'
After Training and Testing I get accuracy close to 100% in both test and train set ,but when I give image
of Shifa it still classifies it as Rishav,and Rishav's image is classified as Rishav.My dataset contains 1070 images for each class for training and 45 images for testing in each class.
Don't forget to rescale the pixel range of your new image by dividing it by 255
I've already asked similar question here, but now I have slightly different problem, therefore asking new question.
I decided to use slightly different approach instead of proposed among answers in the referenced question to train, and then fine-tune model.
Update: I've replaced old question provided here with more suitable version
Here is my sequence of actions:
Build VGG16 model and drop top layer (call it no-top model)
Generate bottleneck features using no-top model
Train a separate fully-connected model using bottleneck features
Build new VGG16 model, drop top layers, and attach pretrained top-model
Train concatenated model on dogs/cats data
And here is a code I use to implement aforementioned sequence of actions:
import warnings
warnings.simplefilter('ignore', UserWarning)
warnings.simplefilter('ignore', DeprecationWarning)
from __future__ import print_function
from itertools import izip_longest as zip_longest
from pprint import pformat as pf
from pprint import pprint as pp
import os
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
from keras.layers import Conv2D, MaxPooling2D, MaxPooling2D, ZeroPadding2D
from keras.layers import Dropout, Flatten, Dense, InputLayer, Lambda
from keras.models import Sequential, Model, load_model
from keras.utils.data_utils import get_file
from keras.optimizers import SGD
import keras.backend as K
import numpy as np
RANDOM_STATE = 1
IMAGE_WIDTH = 224
IMAGE_HEIGHT = 224
BATCH_SIZE = 4
VGG_MEAN = np.array([123.68, 116.779, 103.939]).reshape((3, 1, 1))
VGG16_WEIGHTS_PATH = 'http://www.platform.ai/models/vgg16.h5'
DATA_ROOT = os.path.join(os.path.expanduser('~'), 'data', 'dogscats')
TRAIN_DIR = os.path.join(DATA_ROOT, 'train')
VALID_DIR = os.path.join(DATA_ROOT, 'valid')
SAMPLES_DIR = os.path.expanduser('~/dogscats_samples')
np.random.seed(RANDOM_STATE)
K.set_image_dim_ordering('th')
def get_batches(dirname, gen=ImageDataGenerator(), shuffle=True,
batch_size=BATCH_SIZE, class_mode='categorical'):
return gen.flow_from_directory(
os.path.join(SAMPLES_DIR, dirname),
target_size=(IMAGE_WIDTH, IMAGE_HEIGHT),
class_mode=class_mode,
shuffle=shuffle,
batch_size=batch_size)
def vgg_preprocess(x):
x = x - VGG_MEAN
return x[:, ::-1]
def conv_block(model, n_layers, n_filters, name='block'):
for i in range(n_layers):
model.add(ZeroPadding2D((1, 1), name='%s_padding_%s' % (name, i)))
model.add(Conv2D(n_filters, (3, 3), activation='relu', name='%s_conv2d_%s' % (name, i)))
model.add(MaxPooling2D((2, 2), strides=(2, 2), name='%s_maxpool' % name))
def fc_block(model, name='block'):
model.add(Dense(4096, activation='relu', name=name + '_dense'))
model.add(Dropout(0.5))
def build_vgg_16():
model = Sequential()
input_shape = (3, IMAGE_WIDTH, IMAGE_HEIGHT)
model.add(InputLayer(input_shape=input_shape))
model.add(Lambda(vgg_preprocess))
conv_block(model, n_layers=2, n_filters=64, name='block1')
conv_block(model, n_layers=2, n_filters=128, name='block2')
conv_block(model, n_layers=3, n_filters=256, name='block3')
conv_block(model, n_layers=3, n_filters=512, name='block4')
conv_block(model, n_layers=3, n_filters=512, name='block5')
model.add(Flatten())
fc_block(model)
fc_block(model)
model.add(Dense(1000, activation='softmax'))
return model
def train_finetuned_model():
file_path = get_file('vgg16.h5', VGG16_WEIGHTS_PATH, cache_subdir='models')
print('Building VGG16 (no-top) model to generate bottleneck features')
vgg16_notop = build_vgg_16()
vgg16_notop.load_weights(file_path)
for _ in range(6):
vgg16_notop.pop()
vgg16_notop.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
train_batches = get_batches('train', shuffle=False, class_mode=None)
train_labels = np.array([0]*1000 + [1]*1000)
bottleneck_train = vgg16_notop.predict_generator(train_batches, steps=2000 // BATCH_SIZE)
valid_batches = get_batches('valid', shuffle=False, class_mode=None)
valid_labels = np.array([0]*400 + [1]*400)
bottleneck_valid = vgg16_notop.predict_generator(valid_batches, steps=800 // BATCH_SIZE)
print('Training top model on bottleneck features')
top_model = Sequential()
top_model.add(Flatten(input_shape=bottleneck_train.shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(1, activation='sigmoid'))
top_model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy'])
top_model.fit(bottleneck_train, train_labels,
batch_size=32, epochs=50,
validation_data=(bottleneck_valid, valid_labels))
print('Concatenate new VGG16 (without top layer) with pretrained top model')
vgg16_fine = build_vgg_16()
vgg16_fine.load_weights(file_path)
for _ in range(6):
vgg16_fine.pop()
vgg16_fine.add(Flatten(name='top_flatten'))
vgg16_fine.add(Dense(256, activation='relu', name='top_dense'))
vgg16_fine.add(Dropout(0.5, name='top_dropout'))
vgg16_fine.add(Dense(1, activation='sigmoid', name='top_sigmoid'))
for i, layer in enumerate(reversed(top_model.layers), 1):
pretrained_weights = layer.get_weights()
vgg16_fine.layers[-i].set_weights(pretrained_weights)
for layer in vgg16_fine.layers[:26]:
layer.trainable = False
vgg16_fine.compile(optimizer=SGD(lr=1e-4, momentum=0.9),
loss='binary_crossentropy',
metrics=['accuracy'])
print('Train concatenated model on dogs/cats dataset sample')
train_datagen = ImageDataGenerator(rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_batches = get_batches('train', gen=train_datagen, class_mode='binary')
valid_batches = get_batches('valid', gen=test_datagen, class_mode='binary')
vgg16_fine.fit_generator(train_batches,
steps_per_epoch=2000 // BATCH_SIZE,
epochs=50,
validation_data=valid_batches,
validation_steps=800 // BATCH_SIZE)
return vgg16_fine
final_model = train_finetuned_model()
But the problem is that model's accuracy drastically dropped. After 50 epochs, its accuracy is around 50%. Therefore, probably I've done something wrong.
Maybe something wrong with parameters, i.e. learning rate, batch size, etc.?
Your fully connected layers look totally different from the original VGG architecture.
# yours
Flatten()
Dense(256, activation='relu')
Dense(1, activation='sigmoid')
# original
Flatten()
Dense(4096, activation='relu')
Dense(4096, activation='relu')
Dense(2, activation='softmax')
Two points.
The last layer should be 2-class-softmax instead of sigmoid. The
accuracy is not computed as you expect if you use sigmoid, I guess.
Complexity (number of neurons and layers) seems to be too low.
Well, not sure if it is a right solution, but I was able to increase accuracy at least up to 70% with this code (probably the main reason is decreased learning rate and more epochs):
def train_finetuned_model(lr=1e-5, verbose=True):
file_path = get_file('vgg16.h5', VGG16_WEIGHTS_PATH, cache_subdir='models')
if verbose:
print('Building VGG16 (no-top) model to generate bottleneck features.')
vgg16_notop = build_vgg_16()
vgg16_notop.load_weights(file_path)
for _ in range(6):
vgg16_notop.pop()
vgg16_notop.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])
if verbose:
print('Bottleneck features generation.')
train_batches = get_batches('train', shuffle=False, class_mode=None, batch_size=BATCH_SIZE)
train_labels = np.array([0]*1000 + [1]*1000)
train_bottleneck = vgg16_notop.predict_generator(train_batches, steps=2000 // BATCH_SIZE)
valid_batches = get_batches('valid', shuffle=False, class_mode=None, batch_size=BATCH_SIZE)
valid_labels = np.array([0]*400 + [1]*400)
valid_bottleneck = vgg16_notop.predict_generator(valid_batches, steps=800 // BATCH_SIZE)
if verbose:
print('Training top model on bottleneck features.')
top_model = Sequential()
top_model.add(Flatten(input_shape=train_bottleneck.shape[1:]))
top_model.add(Dense(4096, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(4096, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(2, activation='softmax'))
top_model.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])
top_model.fit(train_bottleneck, to_categorical(train_labels),
batch_size=32, epochs=10,
validation_data=(valid_bottleneck, to_categorical(valid_labels)))
if verbose:
print('Concatenate new VGG16 (without top layer) with pretrained top model.')
vgg16_fine = build_vgg_16()
vgg16_fine.load_weights(file_path)
for _ in range(6):
vgg16_fine.pop()
vgg16_fine.add(Flatten(name='top_flatten'))
vgg16_fine.add(Dense(4096, activation='relu'))
vgg16_fine.add(Dropout(0.5))
vgg16_fine.add(Dense(4096, activation='relu'))
vgg16_fine.add(Dropout(0.5))
vgg16_fine.add(Dense(2, activation='softmax'))
vgg16_fine.compile(optimizer=RMSprop(lr=lr), loss='categorical_crossentropy', metrics=['accuracy'])
if verbose:
print('Loading pre-trained weights into concatenated model')
for i, layer in enumerate(reversed(top_model.layers), 1):
pretrained_weights = layer.get_weights()
vgg16_fine.layers[-i].set_weights(pretrained_weights)
for layer in vgg16_fine.layers[:26]:
layer.trainable = False
if verbose:
print('Layers training status:')
for layer in vgg16_fine.layers:
print('[%6s] %s' % ('' if layer.trainable else 'FROZEN', layer.name))
vgg16_fine.compile(optimizer=RMSprop(lr=1e-6), loss='binary_crossentropy', metrics=['accuracy'])
if verbose:
print('Train concatenated model on dogs/cats dataset sample.')
train_datagen = ImageDataGenerator(rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
train_batches = get_batches('train', gen=train_datagen, class_mode='categorical', batch_size=BATCH_SIZE)
valid_batches = get_batches('valid', gen=test_datagen, class_mode='categorical', batch_size=BATCH_SIZE)
vgg16_fine.fit_generator(train_batches, epochs=100,
steps_per_epoch=2000 // BATCH_SIZE,
validation_data=valid_batches,
validation_steps=800 // BATCH_SIZE)
return vgg16_fine
I guess there is a way to achieve much better results with fine-tuning (up to 98%), but I wasn't able to achieve it with provided code.
I am following this guide as a start to train a model using some cats and dogs images:
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
This is the code:
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
# dimensions of our images.
img_width, img_height = 150, 150
train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 1
batch_size = 16
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)
# this is a generator that will read pictures found in
# subfolers of 'data/train', and indefinitely generate
# batches of augmented image data
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
# this is a similar generator, for validation data
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='binary')
model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size)
model.save_weights('first_try.h5')
with open('model.json', 'w') as f:
f.write(model.to_json())
So I get two files: first_try.h5 and model.json.
Now I want to try to do a simple image prediction using a sample dog.jpg and a cat.jpg. This is what I tried:
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
from PIL import Image
import cv2, numpy as np
# load json and create model
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("first_try.h5")
print("Loaded model from disk")
#attempt 1
img = cv2.resize(cv2.imread('cat.jpg'), (150, 150))
mean_pixel = [103.939, 116.779, 123.68]
img = img.astype(np.float32, copy=False)
for c in range(3):
img[:, :, c] = img[:, :, c] - mean_pixel[c]
img = img.transpose((2,0,1))
img = np.expand_dims(img, axis=0)
out1 = loaded_model.predict(img)
print(np.argmax(out1))
#attempt 2
loaded_model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
img = Image.open('dog.jpg')
img = img.convert('RGB')
x = np.asarray(img, dtype='float32')
x = x.transpose(2, 0, 1)
x = np.expand_dims(x, axis=0)
out1 = loaded_model.predict(x)
print(np.argmax(out1))
I get this output:
Using Theano backend.
Loaded model from disk
0
0
Can someone guide me? How to do a model.predict correctly?
I would suggest you use (https://keras.io/getting-started/faq/#how-can-i-save-a-keras-model):
from keras.models import load_model
model.save('model.hdf5')
model = load_model('model.hdf5')
Anyways, what makes you think that this is not the correct output? You do the argmax on 1 value. This is naturally the index 0. If you want the final output of the last layer remove the argmax and then you get a probability.
I'm trying to make a basic MLP example in keras. My input data has the shape train_data.shape = (2000,75,75) and my testing data has the shape test_data.shape = (500,75,75). 2000 and 500 are the numbers of samples of training and test data (in other words, the shape of the data is (75,75), but there are 2000 and 500 pieces of training and testing data). The output should have two classes.
I'm unsure what value to use for the input_shape parameter on the first layer of the network. Using the code from the mnist example in the keras repository, I have (updated):
from six.moves import cPickle
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.utils import np_utils
from keras.optimizers import RMSprop
# Globals
NUM_CLASSES = 2
NUM_EPOCHS = 10
BATCH_SIZE = 250
def loadData():
fData = open('data.pkl','rb')
fLabels = open('labels.pkl','rb')
data = cPickle.load(fData)
labels = cPickle.load(fLabels)
train_data = data[0:2000]
train_labels = labels[0:2000]
test_data = data[2000:]
test_labels = labels[2000:]
return (train_data, train_labels, test_data, test_labels)
# Load data and corresponding labels for model
train_data, train_labels, test_data, test_labels = loadData()
train_labels = np_utils.to_categorical(train_labels, NUM_CLASSES)
test_labels = np_utils.to_categorical(test_labels, NUM_CLASSES)
print(train_data.shape)
print(test_data.shape)
model = Sequential()
model.add(Dense(512, input_shape=(5625,)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(2))
model.add(Activation('softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer=RMSprop(),
metrics=['accuracy'])
history = model.fit(train_data, train_labels, validation_data=(test_data, test_labels),
batch_size=BATCH_SIZE, nb_epoch=NUM_EPOCHS,
verbose=1)
score = model.evaluate(test_data, test_labels, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])
where 5625 is 75 * 75 (emulating the MNIST example). The error I get is:
Error when checking model input: expected dense_input_1 to have 2 dimensions, but got array with shape (2000, 75, 75)
Any ideas?
From keras MLP example, https://github.com/fchollet/keras/blob/master/examples/mnist_mlp.py
# the data, shuffled and split between train and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
And the model input
model = Sequential()
model.add(Dense(512, input_shape=(784,)))
So you should reshape your train and test to (2000,75*75) and (500,75*75) with
train_data = train_data.reshape(2000, 75*75)
test_data = test_data.reshape(500, 75*75)
and then set the model input shape as you did
model.add(Dense(512, input_shape=(75*75,)))