From 103beb518fc01535d1a5edb9a8d754816e53ec2c Mon Sep 17 00:00:00 2001 From: Navan Chauhan Date: Tue, 15 Sep 2020 15:53:28 +0530 Subject: Publish deploy 2020-09-15 15:53 --- posts/2019-12-08-Image-Classifier-Tensorflow/index.html | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'posts/2019-12-08-Image-Classifier-Tensorflow/index.html') diff --git a/posts/2019-12-08-Image-Classifier-Tensorflow/index.html b/posts/2019-12-08-Image-Classifier-Tensorflow/index.html index 9b4db41..300fc2e 100644 --- a/posts/2019-12-08-Image-Classifier-Tensorflow/index.html +++ b/posts/2019-12-08-Image-Classifier-Tensorflow/index.html @@ -1,4 +1,4 @@ -Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria | Navan Chauhan
Navan Chauhan
4 minute readCreated on December 8, 2019Last modified on June 1, 2020

Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria

Done during Google Code-In. Org: Tensorflow.

Imports

%tensorflow_version 2.x #This is for telling Colab that you want to use TF 2.0, ignore if running on local machine
+Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria | Navan Chauhan
Navan Chauhan
4 minute readCreated on December 8, 2019Last modified on September 15, 2020
Creating a Custom Image Classifier using Tensorflow 2.x and Keras for Detecting Malaria
Done during Google Code-In. Org: Tensorflow.
Imports
%tensorflow_version 2.x #This is for telling Colab that you want to use TF 2.0, ignore if running on local machine
 
 from PIL import Image # We use the PIL Library to resize images
 import numpy as np
@@ -58,7 +58,7 @@ np.random.shuffle(s)
 model.add(layers.Dropout(0.2))
 model.add(layers.Dense(2,activation="softmax"))#2 represent output layer neurons 
 model.summary()
-
Compiling Model
We use the adam optimiser as it is an adaptive learning rate optimization algorithm that's been designed specifically for training deep neural networks, which means it changes its learning rate automaticaly to get the best results
model.compile(optimizer="adam",
+
Compiling Model
We use the Adam optimiser as it is an adaptive learning rate optimisation algorithm that's been designed specifically for training deep neural networks, which means it changes its learning rate automatically to get the best results
model.compile(optimizer="adam",
               loss="sparse_categorical_crossentropy", 
              metrics=["accuracy"])
 
Training Model
We train the model for 10 epochs on the training data and then validate it using the testing data
history = model.fit(X_train,y_train, epochs=10, validation_data=(X_test,y_test))
-- 
cgit v1.2.3