How to know labels of generated images in WGAN using keras The 2019 Stack Overflow Developer Survey Results Are In Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) The Ask Question Wizard is Live! Data science time! April 2019 and salary with experienceHow can I safely create a nested directory in Python?How to get the current time in PythonHow can I make a time delay in Python?How to know if an object has an attribute in PythonHow do I sort a dictionary by value?How to make a chain of function decorators?How to make a flat list out of list of listsHow do I pass a variable by reference?How do I list all files of a directory?How do I install pip on Windows?
RT6224D-based step down circuit yields 0V - why?
Is a pteranodon too powerful as a beast companion for a beast master?
Why can't devices on different VLANs, but on the same subnet, communicate?
In horse breeding, what is the female equivalent of putting a horse out "to stud"?
How to copy the contents of all files with a certain name into a new file?
Semisimplicity of the category of coherent sheaves?
Take groceries in checked luggage
What information about me do stores get via my credit card?
What's the point in a preamp?
Typeface like Times New Roman but with "tied" percent sign
Windows 10: How to Lock (not sleep) laptop on lid close?
Do warforged have souls?
How can I protect witches in combat who wear limited clothing?
How do I add random spotting to the same face in cycles?
The variadic template constructor of my class cannot modify my class members, why is that so?
Road tyres vs "Street" tyres for charity ride on MTB Tandem
Do working physicists consider Newtonian mechanics to be "falsified"?
How many people can fit inside Mordenkainen's Magnificent Mansion?
The following signatures were invalid: EXPKEYSIG 1397BC53640DB551
What can I do if neighbor is blocking my solar panels intentionally?
Mortgage adviser recommends a longer term than necessary combined with overpayments
Finding degree of a finite field extension
Can undead you have reanimated wait inside a portable hole?
Does the AirPods case need to be around while listening via an iOS Device?
How to know labels of generated images in WGAN using keras
The 2019 Stack Overflow Developer Survey Results Are In
Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
The Ask Question Wizard is Live!
Data science time! April 2019 and salary with experienceHow can I safely create a nested directory in Python?How to get the current time in PythonHow can I make a time delay in Python?How to know if an object has an attribute in PythonHow do I sort a dictionary by value?How to make a chain of function decorators?How to make a flat list out of list of listsHow do I pass a variable by reference?How do I list all files of a directory?How do I install pip on Windows?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;
I am working on medical image classification problem, and suffering from low data set problem. So want to generate images using WGAN. In given code WGAN code example is taken of MNIST data set. after image generation it's easy to recognize digit which class they belongs too. But in medical image case, after generating images it's hard to decide generated images belongs to which category, because they saved in group from following code given:
def sample_images(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()
so what changes i have to perform to get labels of generated images.
python tensorflow keras
asked Mar 22 at 6:17
HiteshHitesh
391721
add a comment |
I am working on medical image classification problem, and suffering from low data set problem. So want to generate images using WGAN. In given code WGAN code example is taken of MNIST data set. after image generation it's easy to recognize digit which class they belongs too. But in medical image case, after generating images it's hard to decide generated images belongs to which category, because they saved in group from following code given:
def sample_images(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()
so what changes i have to perform to get labels of generated images.
python tensorflow keras
asked Mar 22 at 6:17
HiteshHitesh
391721
add a comment |
I am working on medical image classification problem, and suffering from low data set problem. So want to generate images using WGAN. In given code WGAN code example is taken of MNIST data set. after image generation it's easy to recognize digit which class they belongs too. But in medical image case, after generating images it's hard to decide generated images belongs to which category, because they saved in group from following code given:
def sample_images(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()
so what changes i have to perform to get labels of generated images.
python tensorflow keras
asked Mar 22 at 6:17
HiteshHitesh
391721
I am working on medical image classification problem, and suffering from low data set problem. So want to generate images using WGAN. In given code WGAN code example is taken of MNIST data set. after image generation it's easy to recognize digit which class they belongs too. But in medical image case, after generating images it's hard to decide generated images belongs to which category, because they saved in group from following code given:
def sample_images(self, epoch):
r, c = 5, 5
noise = np.random.normal(0, 1, (r * c, self.latent_dim))
gen_imgs = self.generator.predict(noise)
# Rescale images 0 - 1
gen_imgs = 0.5 * gen_imgs + 0.5
fig, axs = plt.subplots(r, c)
cnt = 0
for i in range(r):
for j in range(c):
axs[i,j].imshow(gen_imgs[cnt, :,:,0], cmap='gray')
axs[i,j].axis('off')
cnt += 1
fig.savefig("images/mnist_%d.png" % epoch)
plt.close()
so what changes i have to perform to get labels of generated images.
python tensorflow keras
python tensorflow keras
asked Mar 22 at 6:17
HiteshHitesh
391721
asked Mar 22 at 6:17
HiteshHitesh
391721
asked Mar 22 at 6:17
HiteshHitesh
391721
asked Mar 22 at 6:17
HiteshHitesh
391721
asked Mar 22 at 6:17
HiteshHitesh
391721
391721
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
WGAN in the vanilla version cannot generate images conditionally. Therefore, the WGAN you have trained can only generate images without any knowledge of which class they belong to.
To be able to generate images of a particular label, check out conditonal gans. Here's a medium article to get you started.
The alternate option is to train a discriminator from the original training data and use that discriminator to help you manually classify the images.
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f55293914%2fhow-to-know-labels-of-generated-images-in-wgan-using-keras%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
WGAN in the vanilla version cannot generate images conditionally. Therefore, the WGAN you have trained can only generate images without any knowledge of which class they belong to.
To be able to generate images of a particular label, check out conditonal gans. Here's a medium article to get you started.
The alternate option is to train a discriminator from the original training data and use that discriminator to help you manually classify the images.
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
add a comment |
WGAN in the vanilla version cannot generate images conditionally. Therefore, the WGAN you have trained can only generate images without any knowledge of which class they belong to.
To be able to generate images of a particular label, check out conditonal gans. Here's a medium article to get you started.
The alternate option is to train a discriminator from the original training data and use that discriminator to help you manually classify the images.
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
add a comment |
WGAN in the vanilla version cannot generate images conditionally. Therefore, the WGAN you have trained can only generate images without any knowledge of which class they belong to.
To be able to generate images of a particular label, check out conditonal gans. Here's a medium article to get you started.
The alternate option is to train a discriminator from the original training data and use that discriminator to help you manually classify the images.
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
WGAN in the vanilla version cannot generate images conditionally. Therefore, the WGAN you have trained can only generate images without any knowledge of which class they belong to.
To be able to generate images of a particular label, check out conditonal gans. Here's a medium article to get you started.
The alternate option is to train a discriminator from the original training data and use that discriminator to help you manually classify the images.
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
answered Mar 22 at 9:41
Haran RajkumarHaran Rajkumar
538316
538316
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
add a comment |
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
yup , i thought the same. What i did is, i run my WGAN code 2 times. each time i only give single class. Is this correct approach?
– Hitesh
Mar 25 at 7:29
1
1
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
That's an option as well. But given that you have very less training data. It would be better to maximise the gan's potential by training on the entire set.
– Haran Rajkumar
Mar 25 at 8:44
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
Yup i have very less data. and i am doing training on entire set.
– Hitesh
Mar 26 at 4:24
add a comment |
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f55293914%2fhow-to-know-labels-of-generated-images-in-wgan-using-keras%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
