Recipes
Each recipe in the SparseZoo is stored under the model created with it and has a specific stub that identifies it. The stubs are made up of the following structure:
DOMAIN/SUB_DOMAIN/ARCHITECTURE{-SUB_ARCHITECTURE}/FRAMEWORK/REPO/DATASET{-TRAINING_SCHEME}/SPARSE_NAME-SPARSE_CATEGORY-{SPARSE_TARGET}?recipe-type=RECIPE_TYPE
The properties within each model stub are defined as the following:
| Model Property | Definition | Examples |
|---|---|---|
| DOMAIN | The type of solution the model is architected and trained for | cv, nlp |
| SUB_DOMAIN | The sub type of solution the model is architected and trained for | classification, segmentation |
| ARCHITECTURE | The name of the guiding setup for the network's graph | resnet_v1, mobilenet_v1 |
| SUB_ARCHITECTURE | (optional) The scaled version of the architecture such as width or depth | 50, 101, 152 |
| FRAMEWORK | The machine learning framework the model was defined and trained in | pytorch, tensorflow_v1 |
| REPO | The model repository the model and baseline weights originated from | sparseml, torchvision |
| DATASET | The dataset the model was trained on | imagenet, cifar10 |
| TRAINING_SCHEME | (optional) A description on how the model was trained | augmented, lower_lr |
| SPARSE_NAME | An overview of what was done to sparsify the model | base, pruned, quant (quantized), pruned_quant, arch (architecture modified) |
| SPARSE_CATEGORY | Descriptor on the degree to which the model is sparsified as compared with the baseline metric | none, conservative (100% baseline), moderate (>= 99% baseline), aggressive (< 99%) |
| SPARSE_TARGET | (optional) Descriptor for the target environment the model was sparsified for | disk, edge, deepsparse, gpu |
| RECIPE_TYPE | A named descriptor for the recipe signifying what the recipe is for | original, transfer_learn |