Search Results for "wrapper"

Implementation of Imagen, Google's Text-to-Image Neural Network that beats DALL-E2, in Pytorch. It is the new SOTA for text-to-image synthesis. Architecturally, it is actually much simpler than DALL-E2. It consists of a cascading DDPM conditioned on text embeddings from a large pre-trained T5 model (attention network). It also contains dynamic clipping for improved classifier-free guidance, noise level conditioning, and a memory-efficient unit design. It appears neither CLIP nor prior...

...Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the new FullyShardedDataParallel (FSDP) wrapper provided by fairscale. Fairseq can be extended through user-supplied plug-ins. Models define the neural network architecture and encapsulate all of the learnable parameters. Criterions compute the loss function given the model outputs and targets. Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss.