We Keep Coding

Can CNN do better than pretrained CNN?

With all I know. pretrained CNN can do way better than CNN. I have a dataset of 855 images. I have applied CNN and got 94% accuracy.Then I applied Pretrained model (VGG16, ResNet50, Inception_V3, MobileNet)also with fine tuning but still i got highest 60% and two of them are doing very bad on classification. Can CNN really do better than pretrained model or my implementation is wrong. I've converted my image into 100 by 100 dimensions and followed the way of keras application. Then What is the issue ??
Naive CNN approach :
def cnn_model():
size = (100,100,1)
num_cnn_layers =2
NUM_FILTERS = 32
KERNEL = (3, 3)
MAX_NEURONS = 120
model = Sequential()
for i in range(1, num_cnn_layers+1):
if i == 1:
model.add(Conv2D(NUM_FILTERS*i, KERNEL, input_shape=size,
activation='relu', padding='same'))
else:
model.add(Conv2D(NUM_FILTERS*i, KERNEL, activation='relu',
padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(int(MAX_NEURONS), activation='relu'))
model.add(Dropout(0.25))
model.add(Dense(int(MAX_NEURONS/2), activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(3, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam',
metrics=['accuracy'])
return model
VGG16 approach:
def vgg():
` `vgg_model = keras.applications.vgg16.VGG16(weights='imagenet',include_top=False,input_shape = (100,100,3))
model = Sequential()
for layer in vgg_model.layers:
model.add(layer)
# Freeze the layers
for layer in model.layers:
layer.trainable = False
model.add(keras.layers.Flatten())
model.add(keras.layers.Dense(3, activation='softmax'))
model.compile(optimizer=keras.optimizers.Adam(lr=1e-5),
loss='categorical_crossentropy',
metrics=['accuracy'])
return model

What you're referring to as CNN in both cases talk about the same thing, which is a type of a neural network model. It's just that the pre-trained model has been trained on some other data instead of the dataset you're working on and trying to classify.
What is usually used here is called Transfer Learning. Instead of freezing all the layers, trying leaving the last few layers open so they can be retrained with your own data, so that the pretrained model can edit its weights and biases to match your needs as well. It could be the case that the dataset you're trying to classify is foreign to the pretrained models.
Here's an example from my own work, there are additional pieces of code but you can make it work with your own code, the logic remains the same
#You extract the layer which you want to manipulate, usually the last few.
last_layer = pre_trained_model.get_layer(name_of_layer)
# Flatten the output layer to 1 dimension
x = layers.Flatten()(last_output)
# Add a fully connected layer with 1,024 hidden units and ReLU activation
x = layers.Dense(1024,activation='relu')(x)
# Add a dropout rate of 0.2
x = layers.Dropout(0.2)(x)
# Add a final sigmoid layer for classification
x = layers.Dense(1,activation='sigmoid')(x)
#Here we combine your newly added layers and the pre-trained model.
model = Model( pre_trained_model.input, x)
model.compile(optimizer = RMSprop(lr=0.0001),
loss = 'binary_crossentropy',
metrics = ['accuracy'])

Adding to what #Ilknur Mustafa mentioned, as your dataset may be foreign to the images used for pre-training, you can try to re-train few last layers of the pre-trained model instead of adding a whole new layers. The below example code doesn't add any additional trainable layer other than the output layer. In this way, you can benefit by retraining the last few layers on the existing weights, rather than training from scratch. This may be beneficial if you don't have a large dataset to train on.
# load model without classifier layers
vgg = VGG16(include_top=False, input_shape=(100, 100, 3), weights='imagenet', pooling='avg')
# make only last 2 conv layers trainable
for layer in vgg.layers[:-4]:
layer.trainable = False
# add output layer
out_layer = Dense(3, activation='softmax')(vgg.layers[-1].output)
model_pre_vgg = Model(vgg.input, out_layer)
# compile model
opt = SGD(lr=1e-5)
model_pre_vgg.compile(optimizer=opt, loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])

#You extract the layer which you want to manipulate, usually the last few.
last_layer = pre_trained_model.get_layer(name_of_layer)
# Flatten the output layer to 1 dimension
x = layers.Flatten()(last_output)
# Add a fully connected layer with 1,024 hidden units and ReLU activation
x = layers.Dense(1024,activation='relu')(x)
# Add a dropout rate of 0.2
x = layers.Dropout(0.2)(x)
# Add a final sigmoid layer for classification
x = layers.Dense(1,activation='sigmoid')(x)
#Here we combine your newly added layers and the pre-trained model.
model = Model( pre_trained_model.input, x)
model.compile(optimizer = RMSprop(lr=0.0001),
loss = 'binary_crossentropy',
metrics = ['accuracy'])

How to apply sigmoid function for each outputs in Keras?

This is part of my codes.
model = Sequential()
model.add(Dense(3, input_shape=(4,), activation='softmax'))
model.compile(Adam(lr=0.1),
loss='categorical_crossentropy',
metrics=['accuracy'])
with this code, it will apply softmax to all the outputs at once. So the output indicates probability among all. However, I am working on non-exclusive classifire, which means I want the outputs to have independent probability.
Sorry my English is bad...
But what I want to do is to apply sigmoid function to each outputs so that they will have independent probabilities.

There is no need to create 3 separate outputs like suggested by the accepted answer.
The same result can be achieved with just one line:
model.add(Dense(3, input_shape=(4,), activation='sigmoid'))
You can just use 'sigmoid' activation for the last layer:
from tensorflow.keras.layers import GRU
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation
import numpy as np
from tensorflow.keras.optimizers import Adam
model = Sequential()
model.add(Dense(3, input_shape=(4,), activation='sigmoid'))
model.compile(Adam(lr=0.1),
loss='categorical_crossentropy',
metrics=['accuracy'])
pred = model.predict(np.random.rand(5, 4))
print(pred)
Output of independent probabilities:
[[0.58463055 0.53531045 0.51800555]
[0.56402034 0.51676977 0.506389 ]
[0.665879 0.58982867 0.5555959 ]
[0.66690147 0.57951677 0.5439698 ]
[0.56204814 0.54893976 0.5488999 ]]
As you can see the classes probabilities are independent from each other. The sigmoid is applied to every class separately.

You can try using Functional API to create a model with n outputs where each output is activated with sigmoid.
You can do it like this
in = Input(shape=(4, ))
dense_1 = Dense(units=4, activation='relu')(in)
out_1 = Dense(units=1, activation='sigmoid')(dense_1)
out_2 = Dense(units=1, activation='sigmoid')(dense_1)
out_3 = Dense(units=1, activation='sigmoid')(dense_1)
model = Model(inputs=[in], outputs=[out_1, out_2, out_3])

how to make a complicated output of a neural network keras

I would like to combine 2 neural networks which are showing probabilities of classes.
One says that it is a cat on the image.
The second says that the cat has a collar.
How to use softmax activation function on the output of the neural network?
Please, see the picture to understand the main idea:

You can use the functional API to create a multi-output network. Essentially every output will be a separate prediction. Something along the lines of:
in = Input(shape=(w,h,c)) # image input
latent = Conv...(...)(in) # some convolutional layers to extract features
# How share the underlying features to predict
animal = Dense(2, activation='softmax')(latent)
collar = Dense(2, activation='softmax')(latent)
model = Model(in, [animal, coller])
model.compile(loss='categorical_crossentropy', optimiser='adam')
You can have as many separate outputs you like. If you have only binary features you can have a single vector output as well, Dense(2, activation='sigmoid') and first entry could predict cat or not, while second whether it has a collar. This would be multi-class multi-label setup.

Juste create two separate dense layers (with sofmax activation) at the end of your model, e.g.:
from keras.layers import Input, Dense, Conv2D
from keras.models import Model
# Input example:
inputs = Input(shape=(64, 64, 3))
# Example of model:
x = Conv2D(16, (3, 3), padding='same')(inputs)
x = Dense(512, activation='relu')(x)
x = Dense(64, activation='relu')(x)
# ... (replace with your actual layers)
# Then add two separate layers taking the previous output and generating two estimations:
cat_predictions = Dense(2, activation='softmax')(x)
collar_predictions = Dense(2, activation='softmax')(x)
model = Model(inputs=inputs, outputs=[cat_predictions, collar_predictions])

How to use additional features along with word embeddings in Keras ?

I am training a LSTM model with Keras on the dataset which looks like following. The variable "Description" is a text field and "Age" and "Gender" are categorical and continuous fields.
Age, Gender, Description
22, M, "purchased a phone"
35, F, "shopping for kids"
I am using word-embedding to convert the text fields to word vectors and then input it in the keras model. The code is given below:
model = Sequential()
model.add(Embedding(word_index, 300, weights=[embedding_matrix], input_length=70, trainable=False))
model.add(LSTM(300, dropout=0.3, recurrent_dropout=0.3))
model.add(Dropout(0.6))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics['accuracy'])
This model is running successfully but I want to input "age" and "gender" variables as features as well. What changes are required in the code to use these features as well ?

You want to add more input layers which is not possible with Sequential Model, you have to go for functional model
from keras.models import Model
which allows you to have multiple inputs and indirect connections.
embed = Embedding(word_index, 300, weights=[embedding_matrix], input_length=70, trainable=False)
lstm = LSTM(300, dropout=0.3, recurrent_dropout=0.3)(embed)
agei = Input(shape=(1,))
conc = Concatenate()(lstm, agei)
drop = Dropout(0.6)(conc)
dens = Dense(1)(drop)
acti = Activation('sigmoid')(dens)
model = Model([embed, agei], acti)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics['accuracy'])
You cannot concatenate before LSTM layer as it doesn't make sense and also you will have 3D Tensor after embedding layer and input is a 2D Tensor.

I wrote about how to do this in keras. It's basically a functional multiple input model, which concatenates both feature vectors like this:
nlp_input = Input(shape=(seq_length,), name='nlp_input')
meta_input = Input(shape=(10,), name='meta_input')
emb = Embedding(output_dim=embedding_size, input_dim=100, input_length=seq_length)(nlp_input)
nlp_out = Bidirectional(LSTM(128))(emb)
x = concatenate([nlp_out, meta_input])
x = Dense(classifier_neurons, activation='relu')(x)
x = Dense(1, activation='sigmoid')(x)
model = Model(inputs=[nlp_input , meta_input], outputs=[x])

Consider having a separate feedforward network that takes in those features and outputs some n dimensional vector.
time_independent = Input(shape=(num_features,))
dense_1 = Dense(200, activation='tanh')(time_independent)
dense_2 = Dense(300, activation='tanh')(dense_1)
Firstly, please use keras' functional API to do something like this.
You would then either pass this in as the hidden state of the LSTM, or you can concatenate it with every word embedding so that the lstm sees it at every timestep. In the latter case, you would want to drastically reduce the dimensionality of the network.
If you need an example, let me know.

Grid Search the number of hidden layers with keras

I am trying to optimize the hyperparameters of my NN using Keras and sklearn.
I am wrapping up with KerasClassifier (it´s a classification problem).
I am trying to optimize the number of hidden layers.
I can´t figure it out how to do it with keras (actually I am wondering how to set up the function create_model in order to maximize the number of hidden layers)
Could anyone please help me?
My code (just the important part):
## Import `Sequential` from `keras.models`
from keras.models import Sequential
# Import `Dense` from `keras.layers`
from keras.layers import Dense
def create_model(optimizer='adam', activation = 'sigmoid'):
# Initialize the constructor
model = Sequential()
# Add an input layer
model.add(Dense(5, activation=activation, input_shape=(5,)))
# Add one hidden layer
model.add(Dense(8, activation=activation))
# Add an output layer
model.add(Dense(1, activation=activation))
#compile model
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=
['accuracy'])
return model
my_classifier = KerasClassifier(build_fn=create_model, verbose=0)# Create
hyperparameter space
epochs = [5, 10]
batches = [5, 10, 100]
optimizers = ['rmsprop', 'adam']
activation1 = ['relu','sigmoid']
# Create grid search
grid = RandomizedSearchCV(estimator=my_classifier,
param_distributions=hyperparameters) #inserir param_distributions
# Fit grid search
grid_result = grid.fit(X_train, y_train)
# Create hyperparameter options
hyperparameters = dict(optimizer=optimizers, epochs=epochs,
batch_size=batches, activation=activation1)
# View hyperparameters of best neural network
grid_result.best_params_

If you want to make the number of hidden layers a hyperparameter you have to add it as parameter to your KerasClassifier build_fn like:
def create_model(optimizer='adam', activation = 'sigmoid', hidden_layers=1):
# Initialize the constructor
model = Sequential()
# Add an input layer
model.add(Dense(5, activation=activation, input_shape=(5,)))
for i in range(hidden_layers):
# Add one hidden layer
model.add(Dense(8, activation=activation))
# Add an output layer
model.add(Dense(1, activation=activation))
#compile model
model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=
['accuracy'])
return model
Then you will be able to optimize the number of hidden layers by adding it to the dictionary, which is passed to RandomizedSearchCV's param_distributions.
One more thing, you probably should separate the activation you use for the output layer from the other layers.
Different classes of activation functions are suitable for hidden layers and for output layers used in binary classification.