Update pre-commits (huggingface#733)

Author: aliberts

.pre-commit-config.yaml

@@ -14,25 +14,25 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.19.0
+    rev: v3.19.1
     hooks:
     -   id: pyupgrade
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.2
+    rev: v0.9.6
     hooks:
       - id: ruff
         args: [--fix]
       - id: ruff-format
   - repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
+    rev: 1.8.5
     hooks:
       - id: poetry-check
       - id: poetry-lock
         args:
           - "--check"
           - "--no-update"
   - repo: https://github.com/gitleaks/gitleaks
-    rev: v8.21.2
+    rev: v8.23.3
     hooks:
       - id: gitleaks
   - repo: https://github.com/woodruffw/zizmor-pre-commit

lerobot/common/datasets/factory.py

@@ -104,7 +104,7 @@ def make_dataset(cfg: TrainPipelineConfig) -> LeRobotDataset | MultiLeRobotDatas
         )
         logging.info(
             "Multiple datasets were provided. Applied the following index mapping to the provided datasets: "
-            f"{pformat(dataset.repo_id_to_index , indent=2)}"
+            f"{pformat(dataset.repo_id_to_index, indent=2)}"
         )
 
     if cfg.dataset.use_imagenet_stats:

lerobot/common/datasets/push_dataset_to_hub/dora_parquet_format.py

@@ -72,7 +72,7 @@ def load_from_raw(raw_dir: Path, videos_dir: Path, fps: int, video: bool, episod
             # However, note that "nearest" might synchronize the reference camera with other cameras on slightly future timestamps.
             # are too far appart.
             direction="nearest",
-            tolerance=pd.Timedelta(f"{1/fps} seconds"),
+            tolerance=pd.Timedelta(f"{1 / fps} seconds"),
         )
     # Remove rows with episode_index -1 which indicates data that correspond to in-between episodes
     df = df[df["episode_index"] != -1]

lerobot/common/policies/act/modeling_act.py

@@ -409,9 +409,9 @@ def forward(self, batch: dict[str, Tensor]) -> tuple[Tensor, tuple[Tensor, Tenso
             latent dimension.
         """
         if self.config.use_vae and self.training:
-            assert (
-                "action" in batch
-            ), "actions must be provided when using the variational objective in training mode."
+            assert "action" in batch, (
+                "actions must be provided when using the variational objective in training mode."
+            )
 
         batch_size = (
             batch["observation.images"]

lerobot/common/policies/diffusion/configuration_diffusion.py

@@ -221,7 +221,7 @@ def validate_features(self) -> None:
         for key, image_ft in self.image_features.items():
             if image_ft.shape != first_image_ft.shape:
                 raise ValueError(
-                    f"`{key}` does not match `{first_image_key}`, but we " "expect all image shapes to match."
+                    f"`{key}` does not match `{first_image_key}`, but we expect all image shapes to match."
                 )
 
     @property

lerobot/common/policies/tdmpc/modeling_tdmpc.py

@@ -594,9 +594,9 @@ def _apply_fn(m):
 
         self.apply(_apply_fn)
         for m in [self._reward, *self._Qs]:
-            assert isinstance(
-                m[-1], nn.Linear
-            ), "Sanity check. The last linear layer needs 0 initialization on weights."
+            assert isinstance(m[-1], nn.Linear), (
+                "Sanity check. The last linear layer needs 0 initialization on weights."
+            )
             nn.init.zeros_(m[-1].weight)
             nn.init.zeros_(m[-1].bias)  # this has already been done, but keep this line here for good measure
 

lerobot/common/policies/vqbet/configuration_vqbet.py

@@ -184,7 +184,7 @@ def validate_features(self) -> None:
         for key, image_ft in self.image_features.items():
             if image_ft.shape != first_image_ft.shape:
                 raise ValueError(
-                    f"`{key}` does not match `{first_image_key}`, but we " "expect all image shapes to match."
+                    f"`{key}` does not match `{first_image_key}`, but we expect all image shapes to match."
                 )
 
     @property

lerobot/common/policies/vqbet/vqbet_utils.py

@@ -203,9 +203,9 @@ def __init__(self, config: VQBeTConfig):
     def forward(self, input, targets=None):
         device = input.device
         b, t, d = input.size()
-        assert (
-            t <= self.config.gpt_block_size
-        ), f"Cannot forward sequence of length {t}, block size is only {self.config.gpt_block_size}"
+        assert t <= self.config.gpt_block_size, (
+            f"Cannot forward sequence of length {t}, block size is only {self.config.gpt_block_size}"
+        )
 
         # positional encodings that are added to the input embeddings
         pos = torch.arange(0, t, dtype=torch.long, device=device).unsqueeze(0)  # shape (1, t)
@@ -273,10 +273,10 @@ def configure_parameters(self):
         assert len(inter_params) == 0, "parameters {} made it into both decay/no_decay sets!".format(
             str(inter_params)
         )
-        assert (
-            len(param_dict.keys() - union_params) == 0
-        ), "parameters {} were not separated into either decay/no_decay set!".format(
-            str(param_dict.keys() - union_params),
+        assert len(param_dict.keys() - union_params) == 0, (
+            "parameters {} were not separated into either decay/no_decay set!".format(
+                str(param_dict.keys() - union_params),
+            )
         )
 
         decay = [param_dict[pn] for pn in sorted(decay)]
@@ -419,9 +419,9 @@ def get_codebook_vector_from_indices(self, indices):
         # and the network should be able to reconstruct
 
         if quantize_dim < self.num_quantizers:
-            assert (
-                self.quantize_dropout > 0.0
-            ), "quantize dropout must be greater than 0 if you wish to reconstruct from a signal with less fine quantizations"
+            assert self.quantize_dropout > 0.0, (
+                "quantize dropout must be greater than 0 if you wish to reconstruct from a signal with less fine quantizations"
+            )
             indices = F.pad(indices, (0, self.num_quantizers - quantize_dim), value=-1)
 
         # get ready for gathering
@@ -472,9 +472,9 @@ def forward(self, x, indices=None, return_all_codes=False, sample_codebook_temp=
         all_indices = []
 
         if return_loss:
-            assert not torch.any(
-                indices == -1
-            ), "some of the residual vq indices were dropped out. please use indices derived when the module is in eval mode to derive cross entropy loss"
+            assert not torch.any(indices == -1), (
+                "some of the residual vq indices were dropped out. please use indices derived when the module is in eval mode to derive cross entropy loss"
+            )
             ce_losses = []
 
         should_quantize_dropout = self.training and self.quantize_dropout and not return_loss
@@ -887,9 +887,9 @@ def calculate_ce_loss(codes):
                 # only calculate orthogonal loss for the activated codes for this batch
 
                 if self.orthogonal_reg_active_codes_only:
-                    assert not (
-                        is_multiheaded and self.separate_codebook_per_head
-                    ), "orthogonal regularization for only active codes not compatible with multi-headed with separate codebooks yet"
+                    assert not (is_multiheaded and self.separate_codebook_per_head), (
+                        "orthogonal regularization for only active codes not compatible with multi-headed with separate codebooks yet"
+                    )
                     unique_code_ids = torch.unique(embed_ind)
                     codebook = codebook[:, unique_code_ids]
 
@@ -999,9 +999,9 @@ def gumbel_sample(
     ind = sampling_logits.argmax(dim=dim)
     one_hot = F.one_hot(ind, size).type(dtype)
 
-    assert not (
-        reinmax and not straight_through
-    ), "reinmax can only be turned on if using straight through gumbel softmax"
+    assert not (reinmax and not straight_through), (
+        "reinmax can only be turned on if using straight through gumbel softmax"
+    )
 
     if not straight_through or temperature <= 0.0 or not training:
         return ind, one_hot
@@ -1209,9 +1209,9 @@ def __init__(
         self.gumbel_sample = gumbel_sample
         self.sample_codebook_temp = sample_codebook_temp
 
-        assert not (
-            use_ddp and num_codebooks > 1 and kmeans_init
-        ), "kmeans init is not compatible with multiple codebooks in distributed environment for now"
+        assert not (use_ddp and num_codebooks > 1 and kmeans_init), (
+            "kmeans init is not compatible with multiple codebooks in distributed environment for now"
+        )
 
         self.sample_fn = sample_vectors_distributed if use_ddp and sync_kmeans else batched_sample_vectors
         self.kmeans_all_reduce_fn = distributed.all_reduce if use_ddp and sync_kmeans else noop

lerobot/common/robot_devices/control_utils.py

@@ -33,7 +33,7 @@ def log_control_info(robot: Robot, dt_s, episode_index=None, frame_index=None, f
 
     def log_dt(shortname, dt_val_s):
         nonlocal log_items, fps
-        info_str = f"{shortname}:{dt_val_s * 1000:5.2f} ({1/ dt_val_s:3.1f}hz)"
+        info_str = f"{shortname}:{dt_val_s * 1000:5.2f} ({1 / dt_val_s:3.1f}hz)"
         if fps is not None:
             actual_fps = 1 / dt_val_s
             if actual_fps < fps - 1:

lerobot/common/utils/io_utils.py

@@ -58,7 +58,7 @@ def _deserialize(target, source):
             # Check that they have exactly the same set of keys.
             if target.keys() != source.keys():
                 raise ValueError(
-                    f"Dictionary keys do not match.\n" f"Expected: {target.keys()}, got: {source.keys()}"
+                    f"Dictionary keys do not match.\nExpected: {target.keys()}, got: {source.keys()}"
                 )
 
             # Recursively update each key.