Better way to deal with downsampled MNIST images Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30 pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsRecognition human in images through HOG descriptor and SVM classifier performs poorlySGD learning gets stuck when using a max pooling layer (but it works fine with just conv + fc)What is the reason that CNN classify some images horribly wrongcounting number of parameters kerasIdentifying computer scanned digitsHow are data in tensorflow.examples.tutorials.mnist formatted?Why is my Keras model not learning image segmentation?Multi-inputs Convolutional Neural Network for images from the same classHow to combine multiple images featuresDeep Learning for high contrast images with small differences
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
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 23, 2019 at 23:30 UTC (7:30 pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsRecognition human in images through HOG descriptor and SVM classifier performs poorlySGD learning gets stuck when using a max pooling layer (but it works fine with just conv + fc)What is the reason that CNN classify some images horribly wrongcounting number of parameters kerasIdentifying computer scanned digitsHow are data in tensorflow.examples.tutorials.mnist formatted?Why is my Keras model not learning image segmentation?Multi-inputs Convolutional Neural Network for images from the same classHow to combine multiple images featuresDeep Learning for high contrast images with small differences
$begingroup$
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
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
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
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'])
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
tensorflow cnn computer-vision mnist
asked 10 mins ago
MrRobot9MrRobot9
1154
asked 10 mins ago
MrRobot9MrRobot9
1154
asked 10 mins ago
MrRobot9MrRobot9
1154
asked 10 mins ago
MrRobot9MrRobot9
1154
asked 10 mins ago
MrRobot9MrRobot9
1154
1154
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f50811%2fbetter-way-to-deal-with-downsampled-mnist-images%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f50811%2fbetter-way-to-deal-with-downsampled-mnist-images%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
