Skip to main content

CNN(Convolutional Neural Network) - Machine Learning - part 2

We have understood basics of CNN in detail in my previous post post now this is time to write our own code and start create our own CNN model. Please have a look on below images to understand high level CNN architecture.


We shown in picture we need multiple layers in CNN so we will create multiple layers for different purpose. So let's start writing code -
First layer - Convolution layer
Second layer - pooling layer (For minimize the size)
Third layer - Flatten layer (To convert data from 2D to 1D)
Fourth layer - Dense layer (For neural network)
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
model = Sequential()

model.add(Convolution2D(filters=32, kernel_size=(3,3), activation='relu', input_shape=(64,64,3) ) )

model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
=================================================================
Total params: 896
Trainable params: 896
Non-trainable params: 0

model.add(MaxPooling2D(pool_size=(2, 2)))
model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 31, 31, 32)        0         
=================================================================
Total params: 896
Trainable params: 896
Non-trainable params: 0

model.add(Flatten())
model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 31, 31, 32)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 30752)             0         
=================================================================
Total params: 896
Trainable params: 896
Non-trainable params: 0

model.add(Dense(units=128, activation='relu'))
model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 31, 31, 32)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 30752)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               3936384   
=================================================================
Total params: 3,937,280
Trainable params: 3,937,280
Non-trainable params: 0

model.add(Dense(units=1,activation='sigmoid'))
model.summary()
Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 31, 31, 32)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 30752)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               3936384   
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 129       
=================================================================
Total params: 3,937,409
Trainable params: 3,937,409
Non-trainable params: 0

So finally we have created convolutional layer and fully connected model. here initial 3 layers are convolution and next two are for fully connected. Complete layers or network is known as ConNet(Convolution Network).
Convolution -
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_3 (Conv2D)            (None, 62, 62, 32)        896       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 31, 31, 32)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 30752)             0         
_________________________________________________________________

Fully connected -
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 128)               3936384   
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 129       

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

Soon I'll add remaining code......cont......

Comments

Popular posts from this blog

error: db5 error(11) from dbenv->open: Resource temporarily unavailable

If rpm command is not working in your system and it is giving an error message( error: db5 error(11) from dbenv->open: Resource temporarily unavailable ). What is the root cause of this issue? How to fix this issue?   just a single command- [root@localhost rpm]# rpm --rebuilddb Detailed error message- [root@localhost rpm]# rpm -q firefox ^Cerror: db5 error(11) from dbenv->open: Resource temporarily unavailable error: cannot open Packages index using db5 - Resource temporarily unavailable (11) error: cannot open Packages database in /var/lib/rpm ^Cerror: db5 error(11) from dbenv->open: Resource temporarily unavailable error: cannot open Packages database in /var/lib/rpm package firefox is not installed [root@localhost rpm]# RPM manage a database in which it store all information related to packages installed in our system. /var/lib/rpm, this is directory where this information is available. [root@localhost rpm]# cd /var/lib/rpm [root@

Failed to get D-Bus connection: Operation not permitted

" Failed to get D-Bus connection: Operation not permitted " - systemctl command is not working in Docker container. If systemctl command is not working in your container and giving subjected error message then simple solution of this error is, create container with -- privileged option and also provide init file full path  /usr/sbin/init [root@server109 ~]# docker container run -dit --privileged --name systemctl_not_working_centos1 centos:7 /usr/sbin/init For detailed explanation and understanding I am writing more about it, please have look below. If we have a daemon based program(httpd, sshd, jenkins, docker etc.) running inside a container and we would like to start/stop or check status of daemon inside docker then it becomes difficult for us to perform such operations , because by default systemctl and service  commands don't work inside docker. Normally we run below commands to check services status in Linux systems. [root@server109 ~]# systemctl status

AWS cloud automation using Terraform

In this post I'll create multiple resources in AWS cloud using Terraform . Terraform is an infrastructure as code( IAC ) software which can do lots of things but it is superb in cloud automation. To use Terraform we have write code in a high-level configuration language known as Hashicorp Configuration Language , optionally we can write code in JSON as well. I'll create below service using Terraform- 1. Create the key-pair and security group which allow inbound traffic on port 80 and 22 2. Launch EC2 instance. 3. To create EC2 instance use same key and security group which created in step 1 4. Launch Volume(EBS) and mount this volume into /var/www/html directory 5. Upload index.php file and an image on GitHub repository 6. Clone GitHub repository into /var/www/html 7. Create S3 bucket, copy images from GitHub repo into it and set permission to public readable 8 Create a CloudFront use S3 bucket(which contains images) and use the CloudFront URL to update code in /var/w