Hfrxdjt

What's called a person who works as someone who puts products on shelves in stores?

My admission is revoked after accepting the admission offer

Will I be more secure with my own router behind my ISP's router?

What was Apollo 13's "Little Jolt" after MECO?

How was Lagrange appointed professor of mathematics so early?

SQL Server placement of master database files vs resource database files

`FindRoot [ ]`::jsing: Encountered a singular Jacobian at a point...WHY

Did war bonds have better investment alternatives during WWII?

What is a 'Key' in computer science?

France's Public Holidays' Puzzle

Why doesn't the university give past final exams' answers?

Is it appropriate to mention a relatable company blog post when you're asked about the company?

Why would the Overseers waste their stock of slaves on the Game?

Will temporary Dex penalties prevent you from getting the benefits of the "Two Weapon Fighting" feat if your Dex score falls below the prerequisite?

How to keep bees out of canned beverages?

Was there ever a LEGO store in Miami International Airport?

What is the ongoing value of the Kanban board to the developers as opposed to management

How can I wire a 9-position switch so that each position turns on one more LED than the one before?

Arriving in Atlanta (after US Preclearance in Dublin). Will I go through TSA security in Atlanta to transfer to a connecting flight?

"Working on a knee"

Like totally amazing interchangeable sister outfit accessory swapping or whatever

Why aren't road bicycle wheels tiny?

Co-worker works way more than he should

Are these square matrices always diagonalisable?

Better way to deal with downsampled MNIST images

0

$begingroup$

model = tf.keras.models.Sequential([
 tf.keras.layers.MaxPool2D(4, 4, input_shape=(28,28,1)),
 tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),

 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),
 tf.keras.layers.Flatten(),
 tf.keras.layers.Dense(512, activation=tf.nn.relu),
 tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

optimizer = tf.keras.optimizers.RMSprop(lr=0.00020, rho=0.99, epsilon=1e-8, decay=0.0)

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

So, the MNIST images are downsampled from 28*28 to 7*7 from the first line. Using that,I want to get a good accuracy and the maximum I'm getting is 89% with 40 epoch and 6000 test images. How can I improve this without removing the first line?

tensorflow cnn computer-vision mnist

share|improve this question

asked 10 mins ago

MrRobot9MrRobot9

1154

$endgroup$

add a comment | 

0

$begingroup$

model = tf.keras.models.Sequential([
 tf.keras.layers.MaxPool2D(4, 4, input_shape=(28,28,1)),
 tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),

 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),
 tf.keras.layers.Flatten(),
 tf.keras.layers.Dense(512, activation=tf.nn.relu),
 tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

optimizer = tf.keras.optimizers.RMSprop(lr=0.00020, rho=0.99, epsilon=1e-8, decay=0.0)

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

So, the MNIST images are downsampled from 28*28 to 7*7 from the first line. Using that,I want to get a good accuracy and the maximum I'm getting is 89% with 40 epoch and 6000 test images. How can I improve this without removing the first line?

tensorflow cnn computer-vision mnist

share|improve this question

asked 10 mins ago

MrRobot9MrRobot9

1154

$endgroup$

add a comment | 

$begingroup$

model = tf.keras.models.Sequential([
 tf.keras.layers.MaxPool2D(4, 4, input_shape=(28,28,1)),
 tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),

 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),
 tf.keras.layers.Flatten(),
 tf.keras.layers.Dense(512, activation=tf.nn.relu),
 tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

optimizer = tf.keras.optimizers.RMSprop(lr=0.00020, rho=0.99, epsilon=1e-8, decay=0.0)

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

So, the MNIST images are downsampled from 28*28 to 7*7 from the first line. Using that,I want to get a good accuracy and the maximum I'm getting is 89% with 40 epoch and 6000 test images. How can I improve this without removing the first line?

tensorflow cnn computer-vision mnist

share|improve this question

asked 10 mins ago

MrRobot9MrRobot9

1154

$endgroup$

model = tf.keras.models.Sequential([
 tf.keras.layers.MaxPool2D(4, 4, input_shape=(28,28,1)),
 tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),

 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.Conv2D(128, (3, 3), padding='same', activation=tf.nn.relu),
 tf.keras.layers.MaxPool2D(2, 2),
 tf.keras.layers.Dropout(0.25),
 tf.keras.layers.Flatten(),
 tf.keras.layers.Dense(512, activation=tf.nn.relu),
 tf.keras.layers.Dense(10, activation=tf.nn.softmax)
])

optimizer = tf.keras.optimizers.RMSprop(lr=0.00020, rho=0.99, epsilon=1e-8, decay=0.0)

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

share|improve this question

asked 10 mins ago

MrRobot9MrRobot9

1154

share|improve this question

asked 10 mins ago

MrRobot9MrRobot9

1154

asked 10 mins ago

MrRobot9MrRobot9

1154

asked 10 mins ago

MrRobot9MrRobot9

1154