diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2024-02-13 14:26:32 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-13 14:26:32 +0100 |
| commit | ad73e93da2cf7311cb5c5bc39250aa335c5f9b76 (patch) | |
| tree | 5b5ea591d0fda870f4499869e3a8feb9718cfebf /candle-examples/examples/reinforcement-learning/ddpg.rs | |
| parent | 13c67226e68de216b731707067f7e68af0438821 (diff) | |
| download | candle-ad73e93da2cf7311cb5c5bc39250aa335c5f9b76.tar.gz candle-ad73e93da2cf7311cb5c5bc39250aa335c5f9b76.tar.bz2 candle-ad73e93da2cf7311cb5c5bc39250aa335c5f9b76.zip | |
Detach the tensors on batch-norm eval. (#1702)
* Detach the tensors on batch-norm eval.
* Fix pyo3 bindings.
* Black tweak.
* Formatting.
* Also update the pyo3-onnx formatting.
* Apply black.
Diffstat (limited to 'candle-examples/examples/reinforcement-learning/ddpg.rs')
| -rw-r--r-- | candle-examples/examples/reinforcement-learning/ddpg.rs | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/candle-examples/examples/reinforcement-learning/ddpg.rs b/candle-examples/examples/reinforcement-learning/ddpg.rs index 1ce4889e..5309eaf6 100644 --- a/candle-examples/examples/reinforcement-learning/ddpg.rs +++ b/candle-examples/examples/reinforcement-learning/ddpg.rs @@ -411,7 +411,7 @@ impl DDPG<'_> { pub fn actions(&mut self, state: &Tensor) -> Result<f32> { let actions = self .actor - .forward(&state.detach()?.unsqueeze(0)?)? + .forward(&state.detach().unsqueeze(0)?)? .squeeze(0)?; let actions = if self.train { (actions + self.ou_noise.sample()?)? |