Skip to content

updated occurences of tree_multimap to tree_map #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shyams2 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

updated occurences of tree_multimap to tree_map #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion enn/losses/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ def loss_fn(enn: base.EpistemicNetwork[base.Input, base.Output],
# index. We choose to average the state across epistemic indices and
# then perform basic error checking to make sure the shape is unchanged.
new_state = jax.tree_map(batch_mean, new_state)
jax.tree_multimap(
jax.tree_map(
lambda x, y: chex.assert_equal_shape([x, y]), new_state, state)
mean_metrics = jax.tree_map(batch_mean, metrics)

Expand Down
2 changes: 1 addition & 1 deletion enn/metrics/calibration.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ def __call__(
state = self._get_init_stats()

# Update state
new_stats = jax.tree_multimap(jnp.add, state.extra, batch_stats)
new_stats = jax.tree_map(jnp.add, state.extra, batch_stats)
new_count = state.count + 1
new_value = _map_stats_to_ece(new_stats)
return metrics_base.MetricsState(
Expand Down
2 changes: 1 addition & 1 deletion enn/networks/ensembles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ def apply(params: hk.Params, states: hk.State, inputs: chex.Array,
sub_params = jax.tree_map(particle_selector, params)
sub_states = jax.tree_map(particle_selector, states)
out, new_sub_states = model.apply(sub_params, sub_states, inputs)
new_states = jax.tree_multimap(
new_states = jax.tree_map(
lambda s, nss: s.at[index, ...].set(nss), states, new_sub_states)
return out, new_states

Expand Down
2 changes: 1 addition & 1 deletion enn/networks/hypermodels.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ def hyper_fn(inputs: chex.Array,
flat_output = jax.tree_map(lambda layer: layer(hyper_index), final_layers)

# Reshape this flattened output to the original base shapes (unflatten)
generated_params = jax.tree_multimap(jnp.reshape, flat_output, base_shapes)
generated_params = jax.tree_map(jnp.reshape, flat_output, base_shapes)

if scale:
# Scale the generated params such that expected variance of the raw
Expand Down