{"url":"/dataset/deepnets-1m","name":"DeepNets-1M","full_name":null,"description_markdown":"The DeepNets-1M dataset is composed of neural network architectures represented as graphs where nodes are operations (convolution, pooling, etc.) and edges correspond to the forward pass flow of data through the network.\r\nDeepNets-1M has 1 million training architectures and 1402 in-distribution (ID) and out-of-distribution (OOD) evaluation architectures: \r\n500 validation and 500 testing ID architectures, \r\n100 wide OOD architectures, \r\n100 deep OOD architectures, \r\n100 dense OOD architectures, \r\n100 OOD archtectures without batch normalization, and \r\n2 predefined architectures (ResNet-50 and 12 layer Visual Transformer).\r\n\r\nFor 1402 evaluation architectures, DeepNets-1M includes accuracies of the networks on CIFAR-10 and ImageNet after training them with stochastic gradient descent (SGD).\r\nBesides accuracy, other properties of evaluation architectures are included: accuracy on noisy images, inference and convergence time. These properties of architectures can enable training neural architecture search models.\r\n\r\nThe DeepNets-1M is used to train and evaluate parameter prediction models such as Graph HyperNetworks. These models can predict all parameters for a given network (graph) in a single forward pass and the results can be compared to optimizing parameters with SGD.","description_withheld":null,"homepage":"https://github.com/facebookresearch/ppuda","introduced_date":"2021-10-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/parameter-prediction-for-unseen-deep","title":"Parameter Prediction for Unseen Deep Architectures","first_author":"Boris Knyazev","url":null},"license":{"name":"MIT","url":"https://github.com/facebookresearch/ppuda/blob/main/LICENSE"},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Parameter Prediction","url":"/task/parameter-prediction","datasets_with_task":"/datasets/task/parameter-prediction"}],"languages":[],"variants":["DeepNets-1M"],"data_loaders":[{"repo":"https://github.com/facebookresearch/ppuda","url":"https://github.com/facebookresearch/ppuda#deepnets-1m","frameworks":["pytorch"]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}