3/23/2023 0 Comments Ai meme generatorHopefully, you enjoyed reading the simplified version of all the tech stack used in Meme Generator. One of the core reasons behind doing this project was just to understand the different aspects of Deep Learning, Cloud Services, Chef, Image Augmentation, etc. The application was hence developed using a wide variety of tech stack. The full code can be found in GitHub here. To know what the above terms mean and do, please visit our GitHub repository “COVID19 Feedback Application,” where we have explained it clearly in detail. In addition to the above, we’ve also used the following in building MemeGen: 1. This ensures that all the existing models play their part appropriately and provide the most accurate results. Hence we assign weights to the models for each class (expressions) to conjure up the best possible results.įor example, for sad expression the weight of model A would be 0.8 and that of B and C would be 0.3 and 0.1 respectively. If you want to know more about CNN, click here.Ī point to notice here is that the model A gives a good precision for Sad expression and 60% of the times it is correct, whereas model C gives an inadequate precision for Sad faces and predicts it to be some other expression predicting approximately 25% of the times right. It seems simple, but in reality, involves a lot of mathematical calculations and understanding of neural networks. We have multiple feature detectors to help with things like edge detection, identifying different shapes, bends, or different colors, etc.ĬNN has several advantages over the conventional image classification methods, one of them being transational invariance which typically means that it identifies an object even if it is translated, rotated or slightly deformed. Kernel K, which is a feature detector, is equivalent to the flashlight on the image I, and we are trying to detect features and create multiple features maps to help us identify or classify the image. This is exactly what we do in the convolutional layer. If you were a detective and you come across a large image or a picture in the dark, how will you identify the image? You will use a flashlight and scan across the entire image. Here is a very satisfying metaphor we found on the Internet about how CNN works: Kernel K is a set of learnable filters and is spatially small compared to the image but extends through the full depth of the input image. The convolutional layer is the core building block of CNN, and it helps with feature detection. CNN can be understood by clearly associating it with two crucial elements: 1.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |