hebbian_prune_perc=None,
weight_prune_perc=0.3,
hebbian_grow=False,
on_perc=ray.tune.grid_search([0.02, 0.04]),
),
"mlp-Sparse": dict(
model=ray.tune.grid_search(["SparseModel"]),
# sparse related
hebbian_prune_perc=None,
weight_prune_perc=0.3,
hebbian_grow=False,
on_perc=ray.tune.grid_search([0.02, 0.04]),
),
}
exp_configs = (
[(name, new_experiment(base_exp_config, c)) for name, c in experiments.items()]
if experiments
else [(experiment_name, base_exp_config)]
)
# Register serializers.
ray.init()
for t in [
torch.FloatTensor,
torch.DoubleTensor,
torch.HalfTensor,
torch.ByteTensor,
torch.CharTensor,
torch.ShortTensor,
torch.IntTensor,
torch.LongTensor,
network="gsc_sparse_dscnn",
prune_methods=["none", "dynamic"],
hebbian_prune_frac=0.99,
magnitude_prune_frac=0.0,
sparsity=0.98,
update_nsteps=50,
prune_dims=tuple(),
),
# "static-second-layer-varying-sparsity": dict(
# model="DSCNN",
# network="gsc_sparse_dscnn",
# prune_methods=["none", "static"],
# sparsity=tune.grid_search([0.98, 0.99, 0.999]),
# ),
}
exp_configs = ([(name, new_experiment(base_exp_config, c))
for name, c in experiments.items()]
if experiments else [(experiment_name, base_exp_config)])
# Download dataset.
download_dataset(base_exp_config)
# Register serializers.
ray.init()
for t in [
torch.FloatTensor,
torch.DoubleTensor,
torch.HalfTensor,
torch.ByteTensor,
torch.CharTensor,
torch.ShortTensor,
