"unknown node" error in Keras convolutional neural network - image-processing

I have the following (2D) convolutional neural network in Keras for image classification with binary labels:
model = keras.Sequential()
model.add(Conv2D(32, kernel_size=5, activation='relu', input_shape=(128, 128, 1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Conv2D(64, kernel_size=5, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Flatten())
model.add(Dense(1024, activation="relu"))
model.add(Dense(2, activation="softmax"))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
To train it, I have a lot of (.jpeg) image files, but too many to load all at once. Hence I use the following generator (and preprocessing):
def load_preprocess(path):
img = img_to_array(load_img(path, target_size=(128, 128)))
output = rgb_to_grayscale(img)
output = tf.reshape(output, (-1,128, 128, 1))
return output
def image_generator(paths, labels, batch_size=32):
while True:
for i in range(0, len(paths), batch_size):
images = [load_preprocess(path) for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(images, target)
I tried training the network using
model.fit_generator(image_generator(train_paths, train_labels), steps_per_epoch=int(np.ceil(len(train_paths)/32)), epochs=1)
Here train_paths is a list of paths and train_labels is a binary numpy array with two columns.
However, this gives me the following error:
InvalidArgumentError: Requested tensor connection from unknown node: "conv2d_input:0".
What causes this error and how do I solve it? I tried googling it, but I found no hits at all.

I found the error: the images are tensors and should be converted to arrays. I do this as follows:
def image_generator(paths, labels, batch_size=32):
sess = tf.Session()
while True:
for i in range(0, len(paths), batch_size):
with sess.as_default():
images = [load_preprocess(path).eval() for path in paths[i:i+batch_size]]
target = labels[i:i+batch_size]
yield(np.array(images), target)

Related

1D Convolutions CNN Keras

I'm very new to Keras and I'm tying to implement a CNN using 1D convolutions for binary classification on the raw time series data. Each training example has 160 time steps and I have 120 training examples. The training data is of shape (120,160). Here is the code:
X_input = Input((160,1))
X = Conv1D(6, 5, strides=1, name='conv1', kernel_initializer=glorot_uniform(seed=0))(X_input)
X = Activation('relu')(X)
X = MaxPooling1D(2, strides=2)(X)
X = Conv1D(16, 5, strides=1, name='conv2', kernel_initializer=glorot_uniform(seed=0))(X)
X = Activation('relu')(X)
X = MaxPooling1D(2, strides=2)(X)
X = Flatten()(X)
X = Dense(120, activation='relu', name='fc1', kernel_initializer=glorot_uniform(seed=0))(X)
X = Dense(84, activation='relu', name='fc2', kernel_initializer=glorot_uniform(seed=0))(X)
X = Dense(2, activation='sigmoid', name='fc3', kernel_initializer=glorot_uniform(seed=0))(X)
model = Model(inputs=X_input, outputs=X, name='model')
X_train = X_train.reshape(-1,160,1) # shape (120,160,1)
t_train = y_train.reshape(-1,1,1) # shape (120,1,1)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(X_train, y_train)
The error that I get is expected fc3 to have 2 dimensions, but got array with shape (120, 1, 1).
I tried removing each layer and just leaving the 'conv1' component but I get the error expected conv1 to have shape (156, 6) but got array with shape (1, 1). It seems like my input shape is wrong; however, looking at other examples it seems that this worked for other people.
I think the issue is not your inputs, but rather your targets.
The output of the model is 2 dimensions, but when it checks against the targets, it realizes that the targets are in an array with shape (120, 1, 1).
You can try changing the y_train reshape line as follows (fyi, it also seems that you accidentally typed t_train instead of y_train):
y_train = y_train.reshape(-1,1)
Also, it seems that you probably want to use 1 instead of 2 for the last Dense layer (see Difference between Dense(2) and Dense(1) as the final layer of a binary classification CNN?)

How to use custom metrics in Keras model while using Grid Search CV?

I want to use R2 (Coefficient of determination) as metrics in my Keras model. For that, I have already defined a function (coeff_determination). This function as a metric works well without Grid Search CV but with grid search cv it gives an error like "The model is not configured to compute the accuracy. You should pass metrics=["accuracy"] to the model.compile() method". The code is given below.
def create_model():
#CNN Architecture - Model 7
model = Sequential()
model.add(Convolution1D(filters=10, kernel_size=12, activation="relu", kernel_initializer="glorot_uniform", input_shape=(X_train.shape[1],1)))
model.add(MaxPooling1D(pool_size=4, strides=2))
model.add(BatchNormalization())
model.add(Convolution1D(filters=16, kernel_size=12, activation='relu', kernel_initializer="glorot_uniform"))
model.add(MaxPooling1D(pool_size=3, strides=2))
model.add(BatchNormalization())
model.add(Convolution1D(filters=22, kernel_size=12, activation='relu', kernel_initializer="glorot_uniform"))
model.add(MaxPooling1D(pool_size=3, strides=2))
model.add(BatchNormalization())
model.add(Convolution1D(filters=28, kernel_size=12, activation='relu', kernel_initializer="glorot_uniform"))
model.add(MaxPooling1D(pool_size=4, strides=2))
model.add(BatchNormalization())
model.add(Convolution1D(filters=34, kernel_size=12, activation='relu', kernel_initializer="glorot_uniform"))
model.add(MaxPooling1D(pool_size=3, strides=2))
model.add(BatchNormalization())
model.add(Convolution1D(filters=40, kernel_size=12, activation='relu', kernel_initializer="glorot_uniform"))
model.add(MaxPooling1D(pool_size=3, strides=2))
model.add(BatchNormalization())
model.add(Flatten())
#model.add(Dropout(0.35))
model.add(Dense(130, activation='relu'))
#model.add(Dropout(0.35))
model.add(Dense(130, activation='relu'))
model.add(Dense(1, activation='linear'))
history = History()
model.compile(loss='mean_squared_error',optimizer= Adam(lr=0.0001), metrics=[coeff_determination])
#model.fit(X_train,y_train, validation_data=(X_test,y_test), epochs=400, batch_size=30, callbacks=[history])
return model
def coeff_determination(y_true, y_pred):
SS_res = K.sum(K.square(y_true - y_pred))
SS_tot = K.sum(K.square(y_true - K.mean(y_true)))
return (1 - SS_res / (SS_tot + K.epsilon()))
# to reprduce the same results next time
seed = 7
np.random.seed(seed)
# Creating Keras model with Scikit learn wrap-up
model = KerasClassifier(build_fn=create_model, verbose=0)
# define the grid search parameters
batch_size = [20,30,40,80]
epochs = [100,200,300,400]
# Using make scorer to convert metric r_2 to a scorer
my_scorer = make_scorer(r2_score, greater_is_better=True)
# passing dictionaries of parameters to the GridSearchCV
param_grid = dict(batch_size=batch_size, epochs=epochs)
grid = GridSearchCV(estimator=model, scoring=my_scorer, param_grid=param_grid, n_jobs=1, cv=3)
grid_result = grid.fit(X_train, y_train)
# summarizing the results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
I think you need to feed your custom scoring function as the input for scoring param to GridSearchCV otherwise it will look out for the default estimator's scoring method which is accuracy.
From Documentation:
scoring: str, callable, list/tuple or dict, default=None
A single str (see The scoring parameter: defining model evaluation rules) or a callable (see Defining your scoring strategy from metric functions) to evaluate the predictions on the test set.
For evaluating multiple metrics, either give a list of (unique) strings or a dict with names as keys and callables as values.
NOTE that when using custom scorers, each scorer should return a single value. Metric functions returning a list/array of values can be wrapped into multiple scorers that return one value each.
See Specifying multiple metrics for evaluation for an example.
If None, the estimator’s score method is used.

I have this error "input 0 is incompatible with layer lstm expected ndim=3 found ndim=5"

I am very new in this field. I searched on the internet but I could not find a solution. I am waiting for the help of people who are interested in this field.
My model
def load_VGG16_model():
base_model = VGG16(weights='imagenet', include_top=False, input_shape=(256,256,3))
print("Model loaded..!")
return base_model
Summary of the model
load_VGG16_model().summary()
Adding Layers
def action_model(shape=(30, 256, 256, 3), nbout=len(classes)):
convnet = load_VGG16_model()
model = Sequential()
model.add(TimeDistributed(convnet, input_shape=shape))
model.add(LSTM(30,return_sequences=True,input_shape=(30,512))) # the error shows this line.
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
model.add(Dense(nbout, activation='softmax'))
return model
model.add(LSTM(30,return_sequences=True,input_shape=(30,512))) ==> the error shows this line.
Your problem is similar to this one Building CNN + LSTM in Keras for a regression problem. What are proper shapes?
Using reshape layer before the LSTM should work fine for you
def action_model(shape=(256, 256, 3), nbout=len(classes)):
convnet = load_VGG16_model()
model = Sequential()
model.add(convnet)
model.add(tf.keras.layers.Reshape((8*8, 512))) # Shape comes from the last output of covnet
model.add(LSTM(30,return_sequences=True,input_shape=(8*8,512))) # the error shows this line.
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
top_model.add(Dense(4096, activation='relu', W_regularizer=l2(0.1)))
top_model.add(Dropout(0.5))
model.add(Dense(nbout, activation='softmax'))
return model

View y_true of batch in Keras Callback during training

I am attempting to implement a custom loss functoin in Keras. It requires that I compute the sum of the inverse class frequencies for each y in B
It is the 1/epsilon(...) portion of the below function
The functoin is from this paper - Page 7
Note: I most definitely could be misinterpreting what the paper is describing to do. Please let me know if I am
I am currently trying to use a Keras Callback and the on_batch_start/end methods to try and determine the class frequency of the input batch (which means accessing y_true of the batch input), but am having little luck.
Thank you in advance for any help you can offer.
Edit: By "little luck" I mean I cannot find a way to access the y_true of an individual batch during training. Example: batch_size = 64, train_features.shape == (50000, 120, 20), I cannot find a way to access the y_true of an individual batch during training. I can access the keras model from on_batch_start/end (self.model), but I cannot find a way to access the actual y_true of the batch, size 64.
from tensorflow.python.keras.callbacks import Callback
class FreqReWeight(Callback):
"""
Update learning rate by batch label frequency distribution -- for use with LDAM loss
"""
def __init__(self, C):
self.C = C
def on_train_begin(self, logs={}):
self.model.custom_val = 0
def on_batch_end(self, batch, logs=None):
print('batch index', batch)
print('Model being trained', self.model)
# how can one access the y_true of the batch?
LDAM Loss Function
zj = "the j-th output of the model for the j-th class"
EDIT2
Loss Function - for testing when loss is called
def LDAM(C):
def loss(y_true, y_pred):
print('shape', y_true.shape) # only prints each epoch, not each batch
return K.mean(y_pred) + C # NOT LDAM, just dummy for testing purposes
return loss
Preparing Data, Compiling Model & Training
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.cifar10.load_data()
y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)
m = 64 # batch_size
model = keras.Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(10))
model.add(Activation('softmax'))
model.compile(loss=LDAM(1), optimizer='sgd', metrics=['accuracy'])
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
model.fit(x_train, y_train,
batch_size=m,
validation_data=(x_test, y_test),
callbacks=[FreqReWeight(1)])
Solution
Ended up asking a more specific question regarding this.
Answer to both can be found here

What is the best Neural Network architecture for mapping one input image to two outputs?

I have generated a data set using EMNIST that has one character per image or two characters per image.The image is sized at 28x56(hxw)
I basically want to predict the one or two characters in a given image. I am not sure on which architecture to follow to implement this. There are 62 character classes.
ex:-single character two characters
For single character y= [23]
For two characters y= [35,11]
I tried the following.
I tried implementing this thorough a CTC but I got stuck in a infinite loss that I couldn't fix.
Padded the single character ground truths with 62 to note a blank character and trained a CNN with following layers.
print()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
y_train = sequence.pad_sequences(y_train, padding='post', value = 62)
y_test = sequence.pad_sequences(y_test,padding='post', value = 62)
X_train = X_train/255.0
X_test = X_test/255.0
input_shape = (28, 56, 1)
model = Sequential()
model.add(Conv2D(filters=72, kernel_size=(11,11), padding = 'same', activation='relu',input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2,2),strides=2))
model.add(Conv2D(filters=144, kernel_size=(7,7) , padding = 'same', activation='relu'))
model.add(Conv2D(filters=144, kernel_size=(3,3) , padding = 'same', activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(units=1024, activation='relu'))
model.add(Dropout(.5))
model.add(Dense(512, activation='relu'))
model.add(Dense(units=2, activation='relu'))
model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
model.summary()
batch_size = 128
steps = math.ceil(X_train.shape[0]/batch_size)
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=0, # randomly rotate images in the range (degrees, 0 to 180)
zoom_range = 0.2, # Randomly zoom image
width_shift_range=0.2, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=False, # randomly flip images
vertical_flip=False)
history = model.fit_generator(datagen.flow(X_train,y_train, batch_size=batch_size),
epochs = 6, validation_data = (X_test, y_test),
verbose = 1,steps_per_epoch=steps)
I was able to reach an accuracy of around 90% for validation set. However when I feed a generated image to see it's prediction it's a few characters off from the correct classification. Is there something wrong in the way I have created the model or pre-processed the data?
I have recognized my error. I have tried to tackle the problem using regression method wheres the problem is a classification problem.

Resources