Scalable architecture for automatic generation of content distribution images
Methods and systems are disclosed for automatic generation of content distribution images that include receiving user input corresponding to a content-distribution operation. The user input may be parsed to identify keywords. Image data corresponding to the keywords can be identified. Image-processing operations may be executed on the image data. Executing a generative adversarial network on the processed image data, which includes: executing a first neural network on the processed-image data to generate first images that correspond to the keywords, the first images generated based on a likelihood that each image of the first images would not be detected as having been generated by the first neural network. A user interface can display the first images with second images that include images that were previously part of content-distribution operations or images that were designated by an entity as being available for content-distribution operations.
1. A method comprising:
receiving user textual input corresponding to a content-distribution operation;
parsing the user textual input to identify one or more keywords associated with the content-distribution operation;
querying one or more databases for one or more images that correspond to the one or more keywords;
executing one or more image-processing operations on the one or more images to derive processed image data that includes one or more image segments of the one or more images, wherein each of at least one of the one or more image segments corresponds to a keyword of the one or more keywords;
executing a generative adversarial network on the processed image data to generate one or more images for the content-distribution operation, wherein executing the generative adversarial network includes:
executing a first neural network on the processed image data, the first neural network generating a first set of images that correspond to the one or more keywords, wherein the first set of images were generated based at least in part on a likelihood that each image of the first set of images would not be detected as having been generated by the first neural network; and
displaying, via a first user interface, the first set of images with a second set of images, the second set of images including images that were previously part of one or more content-distribution operations or images that were designated by an entity associated with the content-distribution operation to be available for content-distribution operations.
2. The method of claim 1 , wherein the generative adversarial network is trained at runtime based on the one or more keywords.
3. The method of claim 1 , further comprising:
determining, based on the one or more keywords, that the generative adversarial network is not trained to generate new images that correspond to at least one keyword of the one or more keywords;
transmitting, to one or more databases, a request for a training dataset, the training dataset including a plurality of images, wherein a portion of each image of the plurality of images corresponds to at least one keyword of the one or more keywords; and
training the generative adversarial network using the training dataset.
4. The method of claim 1 , wherein the image data includes one or more images from previous content-distribution operations.
5. The method of claim 1 , wherein the one or more image-processing operations include labeling portions of each image of the image data that corresponds to a keyword of the one or more keywords.
6. The method of claim 1 , wherein executing a generative adversarial network further includes:
receiving input assigning a label of accepted or rejection to each image of the first set of images;
training, the first neural network, based at least in part on the label; and
removing from the first set of images, each image assigned a label of rejected.
7. A system comprising:
one or more processors; and
a non-transitory computer-readable medium including instructions that when executed by the one or more processors, cause the one or more processors to perform operations including:
receiving user textual input corresponding to a content-distribution operation;
parsing the user textual input to identify one or more keywords associated with the content-distribution operation;
querying one or more databases for one or more images that correspond to the one or more keywords;
executing one or more image-processing operations on the one or more images to derive processed image data that includes one or more image segments of the one or more images, wherein each of at least one of the one or more image segments corresponds to a keyword of the one or more keywords;
executing a generative adversarial network on the processed image data to generate one or more images for the content-distribution operation, wherein executing the generative adversarial network includes:
executing a first neural network on the processed image data, the first neural network generating a first set of images that correspond to the one or more keywords, wherein the first set of images were generated based at least in part on a likelihood that each image of the first set of images would not be detected as having been generated by the first neural network; and
displaying, via a first user interface, the first set of images with a second set of images, the second set of images including images that were previously part of one or more content-distribution operations or images that were designated by an entity associated with the content-distribution operation to be available for content-distribution operations.
8. The system of claim 7 , wherein the generative adversarial network is trained at runtime based on the one or more keywords.
9. The system of claim 7 , further comprising:
determining, based on the one or more keywords, that the generative adversarial network is not trained to generate new images that correspond to at least one keyword of the one or more keywords;
transmitting, to one or more databases, a request for a training dataset, the training dataset including a plurality of images, wherein a portion of each image of the plurality of images corresponds to at least one keyword of the one or more keywords; and
training the generative adversarial network using the training dataset.
10. The system of claim 7 , wherein the image data includes one or more images from previous content-distribution operations.
11. The system of claim 7 , wherein the one or more image-processing operations include labeling portions of each image of the image data that corresponds to a keyword of the one or more keywords.
12. The system of claim 7 , wherein executing a generative adversarial network further includes:
receiving input assigning a label of accepted or rejection to each image of the first set of images;
training, the first neural network, based at least in part on the label; and
removing from the first set of images, each image assigned a label of rejected.
13. A non-transitory computer-readable medium including instructions that when executed by one or more processors, cause the one or more processors to perform operations including:
receiving user textual input corresponding to a content-distribution operation;
parsing the user textual input to identify one or more keywords associated with the content-distribution operation;
querying one or more databases for one or more images that correspond to the one or more keywords;
executing one or more image-processing operations on the one or more images to derive processed image data that includes one or more image segments of the one or more images, wherein each of at least one of the one or more image segments corresponds to a keyword of the one or more keywords;
executing a generative adversarial network on the processed image data to generate one or more images for the content-distribution operation, wherein executing the generative adversarial network includes:
executing a first neural network on the processed image data, the first neural network generating a first set of images that correspond to the one or more keywords, wherein the first set of images were generated based at least in part on a likelihood that each image of the first set of images would not be detected as having been generated by the first neural network; and
displaying, via a first user interface, the first set of images with a second set of images, the second set of images including images that were previously part of one or more content-distribution operations or images that were designated by an entity associated with the content-distribution operation to be available for content-distribution operations.
14. The non-transitory computer-readable medium of claim 13 , wherein the generative adversarial network is trained at runtime based on the one or more keywords.
15. The non-transitory computer-readable medium of claim 13 , further comprising:
determining, based on the one or more keywords, that the generative adversarial network is not trained to generate new images that correspond to at least one keyword of the one or more keywords;
transmitting, to one or more databases, a request for a training dataset, the training dataset including a plurality of images, wherein a portion of each image of the plurality of images corresponds to at least one keyword of the one or more keywords; and
training the generative adversarial network using the training dataset.
16. The non-transitory computer-readable medium of claim 13 , wherein the one or more image-processing operations include labeling portions of each image of the image data that corresponds to a keyword of the one or more keywords.
17. The non-transitory computer-readable medium of claim 13 , wherein executing a generative adversarial network further includes:
receiving input assigning a label of accepted or rejection to each image of the first set of images;
training, the first neural network, based at least in part on the label; and removing from the first set of images, each image assigned a label of rejected.