Revert accidental changes to dataset files

* enable variable image sizes to pi0/pi0.5

* add square image assertion

src/lerobot/optim/optimizers.py

@@ -81,10 +81,14 @@ class AdamWConfig(OptimizerConfig):
     eps: float = 1e-8
     weight_decay: float = 1e-2
     grad_clip_norm: float = 10.0
+    fused: bool = False
 
     def build(self, params: dict) -> torch.optim.Optimizer:
         kwargs = asdict(self)
         kwargs.pop("grad_clip_norm")
+        # Fused optimizer only works on CUDA
+        if kwargs.get("fused") and not torch.cuda.is_available():
+            kwargs["fused"] = False
         return torch.optim.AdamW(params, **kwargs)
 
 

src/lerobot/policies/act/configuration_act.py

@@ -136,6 +136,7 @@ class ACTConfig(PreTrainedConfig):
     optimizer_lr: float = 1e-5
     optimizer_weight_decay: float = 1e-4
     optimizer_lr_backbone: float = 1e-5
+    optimizer_fused: bool = False  # Use CUDA fused AdamW kernel
 
     def __post_init__(self):
         super().__post_init__()
@@ -164,6 +165,7 @@ class ACTConfig(PreTrainedConfig):
         return AdamWConfig(
             lr=self.optimizer_lr,
             weight_decay=self.optimizer_weight_decay,
+            fused=self.optimizer_fused,
         )
 
     def get_scheduler_preset(self) -> None:

src/lerobot/policies/groot/configuration_groot.py

@@ -94,6 +94,7 @@ class GrootConfig(PreTrainedConfig):
     optimizer_betas: tuple[float, float] = (0.95, 0.999)
     optimizer_eps: float = 1e-8
     optimizer_weight_decay: float = 1e-5
+    optimizer_fused: bool = False  # Use CUDA fused AdamW kernel
     warmup_ratio: float = 0.05
     use_bf16: bool = True
 
@@ -174,6 +175,7 @@ class GrootConfig(PreTrainedConfig):
             betas=self.optimizer_betas,
             eps=self.optimizer_eps,
             weight_decay=self.optimizer_weight_decay,
+            fused=self.optimizer_fused,
         )
 
     def get_scheduler_preset(self) -> CosineDecayWithWarmupSchedulerConfig:

src/lerobot/policies/pi0/configuration_pi0.py

@@ -23,6 +23,8 @@ from lerobot.optim.schedulers import CosineDecayWithWarmupSchedulerConfig
 from lerobot.policies.rtc.configuration_rtc import RTCConfig
 from lerobot.utils.constants import OBS_IMAGES
 
+DEFAULT_IMAGE_SIZE = 224
+
 
 @PreTrainedConfig.register_subclass("pi0")
 @dataclass
@@ -51,7 +53,10 @@ class PI0Config(PreTrainedConfig):
     # Real-Time Chunking (RTC) configuration
     rtc_config: RTCConfig | None = None
 
-    image_resolution: tuple[int, int] = (224, 224)  # see openpi `preprocessing_pytorch.py`
+    image_resolution: tuple[int, int] = (
+        DEFAULT_IMAGE_SIZE,
+        DEFAULT_IMAGE_SIZE,
+    )  # see openpi `preprocessing_pytorch.py`
 
     # Add empty images. Used to add empty cameras when no image features are present.
     empty_cameras: int = 0
@@ -69,6 +74,7 @@ class PI0Config(PreTrainedConfig):
     gradient_checkpointing: bool = False  # Enable gradient checkpointing for memory optimization
     compile_model: bool = False  # Whether to use torch.compile for model optimization
     compile_mode: str = "max-autotune"  # Torch compile mode
+    optimizer_fused: bool = False  # Use CUDA fused AdamW kernel
     device: str | None = None  # Device to use for the model (None = auto-detect)
 
     # Optimizer settings: see openpi `AdamW``
@@ -136,6 +142,7 @@ class PI0Config(PreTrainedConfig):
             eps=self.optimizer_eps,
             weight_decay=self.optimizer_weight_decay,
             grad_clip_norm=self.optimizer_grad_clip_norm,
+            fused=self.optimizer_fused,
         )
 
     def get_scheduler_preset(self):

src/lerobot/policies/pi0/modeling_pi0.py

@@ -41,7 +41,7 @@ else:
     PaliGemmaForConditionalGeneration = None
 
 from lerobot.configs.policies import PreTrainedConfig
-from lerobot.policies.pi0.configuration_pi0 import PI0Config
+from lerobot.policies.pi0.configuration_pi0 import DEFAULT_IMAGE_SIZE, PI0Config
 from lerobot.policies.pretrained import PreTrainedPolicy, T
 from lerobot.policies.rtc.modeling_rtc import RTCProcessor
 from lerobot.utils.constants import (
@@ -337,6 +337,7 @@ class PaliGemmaWithExpertModel(
         action_expert_config,
         use_adarms=None,
         precision: Literal["bfloat16", "float32"] = "bfloat16",
+        image_size: int = DEFAULT_IMAGE_SIZE,
     ):
         if use_adarms is None:
             use_adarms = [False, False]
@@ -356,6 +357,7 @@ class PaliGemmaWithExpertModel(
         vlm_config_hf.text_config.vocab_size = 257152
         vlm_config_hf.text_config.use_adarms = use_adarms[0]
         vlm_config_hf.text_config.adarms_cond_dim = vlm_config.width if use_adarms[0] else None
+        vlm_config_hf.vision_config.image_size = image_size
         vlm_config_hf.vision_config.intermediate_size = 4304
         vlm_config_hf.vision_config.projection_dim = 2048
         vlm_config_hf.vision_config.projector_hidden_act = "gelu_fast"
@@ -519,11 +521,17 @@ class PI0Pytorch(nn.Module):  # see openpi `PI0Pytorch`
         paligemma_config = get_gemma_config(config.paligemma_variant)
         action_expert_config = get_gemma_config(config.action_expert_variant)
 
+        if config.image_resolution[0] != config.image_resolution[1]:
+            raise ValueError(
+                f"PaliGemma expects square image resolution, invalid resolution: {config.image_resolution}"
+            )
+
         self.paligemma_with_expert = PaliGemmaWithExpertModel(
             paligemma_config,
             action_expert_config,
             use_adarms=[False, False],
             precision=config.dtype,
+            image_size=config.image_resolution[0],
         )
 
         self.action_in_proj = nn.Linear(config.max_action_dim, action_expert_config.width)

src/lerobot/policies/pi05/configuration_pi05.py

@@ -22,6 +22,8 @@ from lerobot.optim.optimizers import AdamWConfig
 from lerobot.optim.schedulers import CosineDecayWithWarmupSchedulerConfig
 from lerobot.policies.rtc.configuration_rtc import RTCConfig
 
+DEFAULT_IMAGE_SIZE = 224
+
 
 @PreTrainedConfig.register_subclass("pi05")
 @dataclass
@@ -50,7 +52,10 @@ class PI05Config(PreTrainedConfig):
     # Real-Time Chunking (RTC) configuration
     rtc_config: RTCConfig | None = None
 
-    image_resolution: tuple[int, int] = (224, 224)  # see openpi `preprocessing_pytorch.py`
+    image_resolution: tuple[int, int] = (
+        DEFAULT_IMAGE_SIZE,
+        DEFAULT_IMAGE_SIZE,
+    )  # see openpi `preprocessing_pytorch.py`
 
     # Add empty images. Used to add empty cameras when no image features are present.
     empty_cameras: int = 0
@@ -69,6 +74,7 @@ class PI05Config(PreTrainedConfig):
     gradient_checkpointing: bool = False  # Enable gradient checkpointing for memory optimization
     compile_model: bool = False  # Whether to use torch.compile for model optimization
     compile_mode: str = "max-autotune"  # Torch compile mode
+    optimizer_fused: bool = False  # Use CUDA fused AdamW kernel
     device: str | None = None  # Device to use for the model (None = auto-detect)
 
     # Optimizer settings: see openpi `AdamW`
@@ -136,6 +142,7 @@ class PI05Config(PreTrainedConfig):
             eps=self.optimizer_eps,
             weight_decay=self.optimizer_weight_decay,
             grad_clip_norm=self.optimizer_grad_clip_norm,
+            fused=self.optimizer_fused,
         )
 
     def get_scheduler_preset(self):

src/lerobot/policies/pi05/modeling_pi05.py

@@ -41,7 +41,7 @@ else:
     PaliGemmaForConditionalGeneration = None
 
 from lerobot.configs.policies import PreTrainedConfig
-from lerobot.policies.pi05.configuration_pi05 import PI05Config
+from lerobot.policies.pi05.configuration_pi05 import DEFAULT_IMAGE_SIZE, PI05Config
 from lerobot.policies.pretrained import PreTrainedPolicy, T
 from lerobot.policies.rtc.modeling_rtc import RTCProcessor
 from lerobot.utils.constants import (
@@ -336,6 +336,7 @@ class PaliGemmaWithExpertModel(
         action_expert_config,
         use_adarms=None,
         precision: Literal["bfloat16", "float32"] = "bfloat16",
+        image_size: int = DEFAULT_IMAGE_SIZE,
     ):
         if use_adarms is None:
             use_adarms = [False, False]
@@ -355,6 +356,7 @@ class PaliGemmaWithExpertModel(
         vlm_config_hf.text_config.vocab_size = 257152
         vlm_config_hf.text_config.use_adarms = use_adarms[0]
         vlm_config_hf.text_config.adarms_cond_dim = vlm_config.width if use_adarms[0] else None
+        vlm_config_hf.vision_config.image_size = image_size
         vlm_config_hf.vision_config.intermediate_size = 4304
         vlm_config_hf.vision_config.projection_dim = 2048
         vlm_config_hf.vision_config.projector_hidden_act = "gelu_fast"
@@ -518,11 +520,17 @@ class PI05Pytorch(nn.Module):  # see openpi `PI0Pytorch`
         paligemma_config = get_gemma_config(config.paligemma_variant)
         action_expert_config = get_gemma_config(config.action_expert_variant)
 
+        if config.image_resolution[0] != config.image_resolution[1]:
+            raise ValueError(
+                f"PaliGemma expects square image resolution, invalid resolution: {config.image_resolution}"
+            )
+
         self.paligemma_with_expert = PaliGemmaWithExpertModel(
             paligemma_config,
             action_expert_config,
             use_adarms=[False, True],
             precision=config.dtype,
+            image_size=config.image_resolution[0],
         )
 
         self.action_in_proj = nn.Linear(config.max_action_dim, action_expert_config.width)

src/lerobot/policies/smolvla/configuration_smolvla.py

@@ -79,6 +79,7 @@ class SmolVLAConfig(PreTrainedConfig):
     optimizer_eps: float = 1e-8
     optimizer_weight_decay: float = 1e-10
     optimizer_grad_clip_norm: float = 10
+    optimizer_fused: bool = False
 
     scheduler_warmup_steps: int = 1_000
     scheduler_decay_steps: int = 30_000
@@ -136,6 +137,7 @@ class SmolVLAConfig(PreTrainedConfig):
             eps=self.optimizer_eps,
             weight_decay=self.optimizer_weight_decay,
             grad_clip_norm=self.optimizer_grad_clip_norm,
+            fused=self.optimizer_fused,
         )
 
     def get_scheduler_preset(self):