We Keep Coding

How to extract the image names and labels in the training set after completing the active learning loop and write them to a CSV file?

I am using the Keras script at https://modal-python.readthedocs.io/en/latest/content/examples/Keras_integration.html to perform active learning for a binary classification task. After completing the active learning loop, how do we extract the image names and labels in the training set that gives the optimal test performance and write them to a CSV file?
from tensorflow import keras
import numpy as np
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
from modAL.models import ActiveLearner
from modAL.uncertainty import entropy_sampling
# build function for the Keras' scikit-learn API
def create_keras_model():
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))
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(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy'])
return model
# create the classifier
classifier = KerasClassifier(create_keras_model)
# read training data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 28, 28, 1).astype('float32') / 255
X_test = X_test.reshape(10000, 28, 28, 1).astype('float32') / 255
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)
# assemble initial data
n_initial = 1000
initial_idx = np.random.choice(range(len(X_train)), size=n_initial, replace=False)
X_initial = X_train[initial_idx]
y_initial = y_train[initial_idx]
# generate the pool
# remove the initial data from the training dataset
X_pool = np.delete(X_train, initial_idx, axis=0)
y_pool = np.delete(y_train, initial_idx, axis=0)
"""
Training the ActiveLearner
"""
# initialize ActiveLearner
learner = ActiveLearner(
estimator=classifier,
X_training=X_initial, y_training=y_initial,
verbose=1
)
# the active learning loop
n_queries = 100
for idx in range(n_queries):
query_idx, query_instance = learner.query(X_pool, n_instances=100, verbose=0)
print(query_idx)
learner.teach(
X=X_pool[query_idx], y=y_pool[query_idx], only_new=True,
verbose=1
)
# remove queried instance from pool
X_pool = np.delete(X_pool, query_idx, axis=0)
y_pool = np.delete(y_pool, query_idx, axis=0)
# the final accuracy score
print(learner.score(X_test, y_test, verbose=1))

Issue with Shape in Python Neural Network

I have the following dataframe: https://raw.githubusercontent.com/markamcgown/Projects/master/df_model.csv
At "---> 11 history = model.fit" in the last block of code below, I get the error "ValueError: Input 0 of layer sequential_8 is incompatible with the layer: : expected min_ndim=3, found ndim=2. Full shape received: [None, 26]"
Why is it expecting a minimum of 3 dimensions and how can I automate my code below to always have the right shape?
import keras
import pandas as pd
from tensorflow.keras.models import Sequential
from sklearn.model_selection import train_test_split
from keras.layers import Conv2D, MaxPooling2D, Conv1D, MaxPooling1D
from tensorflow.keras.layers import LSTM, Dense, Dropout, Bidirectional
from keras.layers import Dense, Dropout, Flatten, Reshape, GlobalAveragePooling1D
path = r'C:\Users\<your_local_directory>\df_model.csv'
#Import raw data file with accelerometer data
df_model = pd.read_csv(path)
df_model
y_column = 'Y_COLUMN'
x = df_model.drop(y_column, inplace=False, axis=1).values
y = df_model[y_column].values
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.1, random_state=42)
def create_model(num_features, num_classes, dropout=0.3,
loss="mean_absolute_error", optimizer="rmsprop"):
model = Sequential()
model.add(Conv1D(100, 10, activation='relu', input_shape=(None,num_features)))
model.add(Conv1D(100, 10, activation='relu'))
model.add(MaxPooling1D(2))
model.add(Conv1D(160, 10, activation='relu'))
model.add(Conv1D(160, 10, activation='relu'))
model.add(LSTM(160, return_sequences=True))
model.add(LSTM(160, return_sequences=True))
model.add(GlobalAveragePooling1D())
model.add(Dropout(dropout))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss=loss, metrics=["mean_absolute_error"], optimizer=optimizer)
return model
DROPOUT = 0.4
LOSS = "huber_loss"
OPTIMIZER = "adam"
num_time_periods, num_features = x_train.shape[0], x_train.shape[1]
model = create_model(num_features, num_classes=len(set(df_model[y_column])), loss=LOSS,
dropout=DROPOUT, optimizer=OPTIMIZER)
callbacks_list = [keras.callbacks.ModelCheckpoint(filepath='best_model.{epoch:02d}-{val_loss:.2f}.h5',monitor='val_loss', save_best_only=True),keras.callbacks.EarlyStopping(monitor='accuracy', patience=1)]
model.compile(loss='categorical_crossentropy',optimizer='adam', metrics=['accuracy'])
# Hyper-parameters
BATCH_SIZE = 400
EPOCHS = 1
# Enable validation to use ModelCheckpoint and EarlyStopping callbacks.
history = model.fit(x_train,y_train,batch_size=BATCH_SIZE,epochs=EPOCHS,callbacks=callbacks_list,validation_split=0.2,verbose=1)
plt.figure(figsize=(15, 4))
plt.plot(history.history['accuracy'], "g-", label="Training Accuracy")
#plt.plot(history.history['val_accuracy'], "g", label="Accuracy of validation data")
plt.plot(history.history['loss'], "r-", label="Training Loss")
#plt.plot(history.history['val_loss'], "r", label="Loss of validation data")
plt.title('Model Performance')
plt.ylabel('Accuracy & Loss')
plt.xlabel('Epoch')
plt.ylim(0)
plt.legend()
plt.show()

How to implement CAM without visualize_cam in this code?

I want to make Class activation map, so I have write the code
from keras.datasets import mnist
from keras.layers import Conv2D, Dense, GlobalAveragePooling2D
from keras.models import Model, Input
from keras.utils import to_categorical
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train_resized = x_train.reshape((60000, 28, 28, 1))
x_test_resized = x_test.reshape((10000, 28, 28, 1))
y_train_hot_encoded = to_categorical(y_train)
y_test_hot_encoded = to_categorical(y_test)
inputs = Input(shape=(28,28, 1))
x = Conv2D(64, (3,3), activation='relu')(inputs)
x = Conv2D(64, (3,3), activation='relu')(x)
x = GlobalAveragePooling2D()(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train_resized, y_train_hot_encoded, epochs=30, batch_size=256, shuffle=True, validation_split=0.3)
works fine, so I have imported visualize_cam module
from vis.visualization import visualize_cam
import matplotlib.pyplot as plt
import numpy as np
for i in range(10):
ind = np.where(y_test == i)[0][0]
plt.subplot(141)
plt.imshow(x_test_resized[ind].reshape((28,28)))
for j,modifier in enumerate([None, 'guided', 'relu']):
heat_map = visualize_cam(model, 4, y_test[ind], x_test_resized[ind], backprop_modifier=modifier)
plt.subplot(1,4,j+2)
plt.imshow(heat_map)
plt.show()
but the visualize_cam didn`t work well
I tried many times to fix the module but it doesn`t go well
(it depends on scipy which version is below 1.3. but )
so I have to implement cam without that module
Is there any solution to replace visualize_cam into other option to implement CAM?

Here is a scipy library independent implementation.
from keras.datasets import mnist
from keras.layers import Conv2D, Dense, GlobalAveragePooling2D
from keras.models import Model, Input
from keras.utils import to_categorical
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train_resized = x_train.reshape((60000, 28, 28, 1))
x_test_resized = x_test.reshape((10000, 28, 28, 1))
y_train_hot_encoded = to_categorical(y_train)
y_test_hot_encoded = to_categorical(y_test)
inputs = Input(shape=(28,28, 1))
x = Conv2D(64, (3,3), activation='relu')(inputs)
x = Conv2D(64, (3,3), activation='relu', name='final_conv')(x)
x = GlobalAveragePooling2D()(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(x_train_resized, y_train_hot_encoded, epochs=1, batch_size=256, shuffle=True, validation_split=0.3)
import numpy as np
import cv2
import io
import requests
from PIL import Image
import matplotlib.pyplot as plt
# Using Keras implementation from tensorflow
from tensorflow.python.keras import applications
from tensorflow.python.keras.preprocessing.image import load_img, img_to_array
from tensorflow.python.keras import backend as K
# Get the layer of the last conv layer
fianlconv = model.get_layer('final_conv')
# Get the weights matrix of the last layer
weight_softmax = model.layers[-1].get_weights()[0]
# Function to generate Class Activation Mapping
HEIGHT = 28
WIDTH = 28
def returnCAM(feature_conv, weight_softmax, class_idx):
size_upsample = (WIDTH, HEIGHT)
# Keras default is channels last, hence nc is in last
bz, h, w, nc = feature_conv.shape
output_cam = []
for idx in class_idx:
cam = np.dot(weight_softmax[:, idx], np.transpose(feature_conv.reshape(h*w, nc)))
cam = cam.reshape(h, w)
cam = cam - np.min(cam)
cam_img = cam / np.max(cam)
cam_img = np.uint8(255 * cam_img)
output_cam.append(cv2.resize(cam_img, size_upsample))
return output_cam
x = x_test_resized[0,:,:,0]
plt.imshow(x)
plt.show()
classes = {1:'1', 2: '2', 3: '3', 4:'4', 5:'5', 6:'6', 7:'7', 8:'8', 9:'9', 0:'0'}
probs_extractor = K.function([model.input], [model.output])
features_conv_extractor = K.function([model.input], [fianlconv.output])
probs = probs_extractor([np.expand_dims(x, 0).reshape(1,28,28,1)])[0]
features_blob = features_conv_extractor([np.expand_dims(x, 0).reshape(1,28,28,1)])[0]
features_blobs = []
features_blobs.append(features_blob)
idx = np.argsort(probs)
probs = np.sort(probs)
for i in range(-1, -6, -1):
print('{:.3f} -> {}'.format(probs[0, i], classes[idx[0, i]]))
CAMs = returnCAM(features_blobs[0], weight_softmax, [idx[0, -1]])
heatmap = cv2.applyColorMap(cv2.resize(CAMs[0], (28, 28)), cv2.COLORMAP_JET)
result = heatmap[:,:,0] * 0.3 + x * 0.5
print(result.shape)
plt.imshow(result)
plt.show()
N.B: I'm plotting normalized images so the result isn't great, I also trained only for 1 epoch. For better results, you may try training more, change to appropriate color space.

the prediction function gives the same output everytime

from keras.datasets import mnist
from keras.models import Sequential, load_model
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras.preprocessing import image
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import cv2
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape((X_train.shape[0], 28, 28, 1)).astype('float32')
X_test = X_test.reshape((X_test.shape[0], 28, 28, 1)).astype('float32')
X_train = X_train / 255
X_test = X_test / 255
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
def larger_model():
model = Sequential()
model.add(Conv2D(30, (5, 5), input_shape=(28, 28, 1), activation='relu'))
model.add(MaxPooling2D())
model.add(Conv2D(15, (3, 3), activation='relu'))
model.add(MaxPooling2D())
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(50, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model
model = larger_model()
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=200)
scores = model.evaluate(X_test, y_test, verbose=0)
print("Large CNN Error: %.2f%%" % (100-scores[1]*100))
model.save('good_model.h5')
print("Model saved")
After running this code, we get a '.h5' model, then to predict this image
i added this code:
import cv2
model = load_model('good_model.h5')
file = cv2.imread('screenshot.png')
file = cv2.resize(file, (28, 28))
file = cv2.cvtColor(file, cv2.COLOR_BGR2GRAY)
file = file.reshape((-1, 28, 28,1))
result = model.predict(file)
print(result[0])
t = (np.argmax(result[0]))
print("I predict this number is a:", t)
But I always get the same answer which is 4. above I tried to load the image with cv and convert it to gray and then reshape to the size of the input. It takes the input correctly but the answer is always the same no matter what image I give it as input

You need to invert the image before prediction. Once you invert the image, it will predict correctly. The given example is predicting as "2" but I checked with other images such as "7" and it is correctly predicting.
file = cv2.bitwise_not(file)
Other than the above, I made one change. I imported modules from Tensorflow 2.x. Please check the full code here.

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (454, 512, 512)

I used this code to produce my dataset in keras. but when I implement my code it produces this error:
ValueError: Error when checking input: expected conv2d_1_input to
have 4 dimensions, but got array with shape (454, 512, 512)
and I can not solve it. could you please tell me what is the problem? I expand the dimension before using in network but it does not work! could you please answer me fast, due to I search for several days but I could not find the solution and I do not have enough time:
import os,cv2
import numpy as np
import matplotlib.pyplot as plt
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras import backend as K
#K.set_image_dim_ordering('th')
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()
# Define data path
data_path = r"E:\PhD\thesis\deepwatermark\databasetest\train"
data_dir_list = os.listdir(data_path)
img_rows=512
img_cols=512
num_channel=1
num_epoch=20
# Define the number of classes
num_classes = 7
labels_name={'CRP':0,'GF':1,'GN':2,'JPG':3,'MED':4,'ROT':5,'SP':6}
img_data_list=[]
labels_list = []
for dataset in data_dir_list:
img_list=os.listdir(data_path+'/'+ dataset)
print ('Loading the images of dataset-'+'{}\n'.format(dataset))
label = labels_name[dataset]
for img in img_list:
input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
input_img_resize=cv2.resize(input_img,(512,512))
img_data_list.append(input_img_resize)
labels_list.append(label)
img_data = np.array(img_data_list)
img_data = img_data.astype('float32')
img_data /= 255
print (img_data.shape)
labels = np.array(labels_list)
# print the count of number of samples for different classes
print(np.unique(labels,return_counts=True))
# convert class labels to on-hot encoding
Y = np_utils.to_categorical(labels, num_classes)
#Shuffle the dataset
x,y = shuffle(img_data,Y, random_state=2)
# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)
img_data= np.expand_dims(img_data, axis=4)**
print (img_data.shape)
# Defining the model
input_shape=img_data[0].shape
model = Sequential()
model.add(Convolution2D(32, 3,3,border_mode='same',input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
#sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
#model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=["accuracy"])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop',metrics=["accuracy"])
# Viewing model_configuration
model.summary()
model.get_config()
model.layers[0].get_config()
model.layers[0].input_shape
model.layers[0].output_shape
model.layers[0].get_weights()
np.shape(model.layers[0].get_weights()[0])
model.layers[0].trainable
#%%
# Training
hist = model.fit(X_train, y_train, batch_size=16, nb_epoch=num_epoch, verbose=1, validation_data=(X_test, y_test))
my new code with generator is here, did you see any problem? my dataset is the same as before.
import numpy as np
import matplotlib.pyplot as plt
from keras.preprocessing.image import ImageDataGenerator
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras import backend as K
#K.set_image_dim_ordering('th')
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 Conv2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
#
valid_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
#
test_datagen = ImageDataGenerator(rescale=1./255)
#
train_generator = train_datagen.flow_from_directory(
directory=r"E:\databasetest\train",
target_size=(512, 512),
color_mode="grayscale",
batch_size=32,
class_mode="categorical",
shuffle=True,
seed=42
)
#
valid_generator = valid_datagen.flow_from_directory(
directory=r"E:\databasetest\validation",
target_size=(512, 512),
color_mode="grayscale",
batch_size=32,
class_mode="categorical",
shuffle=True,
seed=42
)
#
test_generator = test_datagen.flow_from_directory(
directory=r"E:\databasetest\test",
target_size=(512, 512),
color_mode="grayscale",
batch_size=16,
class_mode=None,
shuffle=False,
seed=42
)
#
## neural network model
model = Sequential()
model.add(Conv2D(32, (3,3),border_mode='same', input_shape = (512, 512, 1), activation = 'relu'))
model.add(Activation('relu'))
model.add(Conv2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Conv2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(7))
model.add(Activation('softmax'))
model.summary()
model.compile(loss = 'categorical_crossentropy',
optimizer = 'rmsprop',
metrics = ['accuracy'])
STEP_SIZE_TRAIN=train_generator.n//train_generator.batch_size
STEP_SIZE_VALID=valid_generator.n//valid_generator.batch_size
model.fit_generator(generator=train_generator,
steps_per_epoch=STEP_SIZE_TRAIN,
validation_data=valid_generator,
validation_steps=STEP_SIZE_VALID,
epochs=10
)
but when I implement it I received this error again:
ResourceExhaustedError: OOM when allocating tensor with shape[32,32,512,512] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: conv2d_1/convolution = Conv2D[T=DT_FLOAT, data_format="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv2d_1/convolution-0-TransposeNHWCToNCHW-LayoutOptimizer, conv2d_1/kernel/read)]]

for img in img_list:
input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
input_img_resize=cv2.resize(input_img,(512,512))
--->input_img_resize = np.expand_dims(input_img_resize, axis=-1)
img_data_list.append(input_img_resize)
labels_list.append(label)
this will make all your arrays 512x512x1, which should do the trick and ends up zith an array of shape (454, 512, 512, 1). You sure you want to use grayscaled images though?
Another thing is this snippet of code
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, `random_state=2)`
img_data= np.expand_dims(img_data, axis=4)**
print (img_data.shape)
You apply another dimension to your img_data, after you've already declared x_train, etc. And in the end you feed x_train, which is not extended, hence the error. If you do it in the beginning, and remove the expanding in the end, then your code should work.
EDIT OOM
I recommend creating a separate question for the OOM problem, so more people see it. Possible problems are the size of the images and the batch size. Reduce the image size to 64 x 64 and change the batch size to 5. If that still raises the error, try also kicking out this dense layer.
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
If these reductions still cause the error then I have the following questions: are you running on GPU/CPU, and which one?
Just to repeat myself: the code is fine, just needs a few changes perhaps.