In this blogpost, we examined the architecture and capabilities of the Versatile Diffusion framework. We then demonstrated this model within a Gradient Notebook to perform txt2img, img2txt, image variation, text variation, dual-guided, and Latent Image to Text to Image synthesis.
This tutorial provides step-by-step instructions on how to handle class imbalances in image datasets for training computer vision models.
This tutorial shows in detail how to train Textual Inversion for Stable Diffusion in a Gradient Notebook, and use it to generate samples that accurately represent the features of the training images using control over the prompt.
In this article, we took a look at data augmentation as an upsampling technique for handing class imbalance by looking at 5 sample methods. Thereafter, we augment a dataset and train it on a convnet using said dataset show how it improved accuracy and recall scores.
In this article, we walked through each of the steps for creating a Dreambooth concept from scratch within a Gradient Notebook, generated novel images from inputted prompts, and showed how to export the concept as a model checkpoint.
Follow these step-by-step instructions to learn how to train YOLOv7 on custom datasets, and then test it with our sample demo on detecting objects with the Road Sign Detection dataset with Gradient's Free GPU Notebooks
Batch normalization is a term commonly mentioned in the context of convolutional neural networks. In this article, we are going to explore what it actually entails and its effects, if any, on the performance or overall behavior of convolutional neural networks.
In our newest article, we discuss autoencoders and convolutional autoencoders in the context of image data. We then show how to write custom autoencoders of our own with PyTorch, train them, and view our results in a Gradient Notebook.
In this article, we explore the whys and the hows behind the fundamental process of pooling in CNN architectures, and then compare two common techniques: max and average pooling.
