manual ruff fixes

happypose/pose_estimators/cosypose/cosypose/evaluation/evaluation.py

@@ -44,10 +44,12 @@
 )
 from happypose.pose_estimators.megapose.evaluation.runner_utils import format_results
 from happypose.pose_estimators.megapose.inference.icp_refiner import ICPRefiner
-from happypose.toolbox.datasets.datasets_cfg import make_object_dataset
 
 # Pose estimator
-# from happypose.pose_estimators.megapose.inference.teaserpp_refiner import TeaserppRefiner
+from happypose.pose_estimators.megapose.inference.teaserpp_refiner import (
+    TeaserppRefiner,
+)
+from happypose.toolbox.datasets.datasets_cfg import make_object_dataset
 from happypose.toolbox.lib3d.rigid_mesh_database import MeshDataBase
 from happypose.toolbox.renderer.panda3d_batch_renderer import Panda3dBatchRenderer
 from happypose.toolbox.utils.distributed import get_rank, get_tmp_dir
@@ -86,7 +88,9 @@ def load_pose_models(coarse_run_id, refiner_run_id, n_workers):
     # object_ds = BOPObjectDataset(BOP_DS_DIR / 'tless/models_cad')
     # object_ds = make_object_dataset(cfg.object_ds_name)
     # mesh_db = MeshDataBase.from_object_ds(object_ds)
-    # renderer = BulletBatchRenderer(object_set=cfg.urdf_ds_name, n_workers=n_workers, gpu_renderer=gpu_renderer)
+    # renderer = BulletBatchRenderer(
+    # object_set=cfg.urdf_ds_name, n_workers=n_workers, gpu_renderer=gpu_renderer
+    # )
     #
 
     object_dataset = make_object_dataset("ycbv")
@@ -210,9 +214,14 @@ def run_eval(
     # See https://stackoverflow.com/a/53287330
     assert cfg.coarse_run_id is not None
     assert cfg.refiner_run_id is not None
-    # TODO (emaitre): This fuction seems to take the wrong parameters. Trying to fix this
+    # TODO (emaitre): This fuction seems to take the wrong parameters. Trying to fix
+    # this.
     """
-    coarse_model, refiner_model, mesh_db = happypose.toolbox.inference.utils.load_pose_models(
+    (
+        coarse_model,
+        refiner_model,
+        mesh_db,
+    ) = happypose.toolbox.inference.utils.load_pose_models(
         coarse_run_id=cfg.coarse_run_id,
         refiner_run_id=cfg.refiner_run_id,
         n_workers=cfg.n_rendering_workers,

happypose/pose_estimators/cosypose/cosypose/evaluation/pred_runner/bop_predictions.py

@@ -152,7 +152,8 @@ def get_preds():
                 n_dets = len(this_batch_detections)
 
                 logger.debug(
-                    f"Full predictions: {n_dets} detections + pose estimation in {duration:.3f} s",
+                    f"Full predictions: {n_dets} detections + pose estimation "
+                    f"in {duration:.3f} s",
                 )
                 logger.debug(f"{'-'*80}")
                 return this_batch_detections, all_preds, duration

happypose/pose_estimators/cosypose/cosypose/evaluation/prediction_runner.py

@@ -89,7 +89,8 @@ def run_inference_pipeline(
 
         Returns: A dict with keys
             - 'final': final preds
-            - 'refiner/final': preds at final refiner iteration (before depth refinement)
+            - 'refiner/final': preds at final refiner iteration (before depth
+              refinement)
             - 'depth_refinement': preds after depth refinement.
 
 
@@ -130,14 +131,16 @@ def run_inference_pipeline(
         # - 'refiner/iteration=5`
         # - `depth_refiner`
         # Note: Since we support multi-hypotheses we need to potentially
-        # go back and extract out the 'refiner/iteration=1`, `refiner/iteration=5` things for the ones that were actually the highest scoring at the end.
+        # go back and extract out the 'refiner/iteration=1`, `refiner/iteration=5`
+        # things for the ones that were actually the highest scoring at the end.
 
         all_preds = {}
         data_TCO_refiner = extra_data["refiner"]["preds"]
 
+        k_0 = f"refiner/iteration={self.inference_cfg.n_refiner_iterations}"
         all_preds = {
             "final": preds,
-            f"refiner/iteration={self.inference_cfg.n_refiner_iterations}": data_TCO_refiner,
+            k_0: data_TCO_refiner,
             "refiner/final": data_TCO_refiner,
             "coarse": extra_data["coarse"]["preds"],
         }

happypose/pose_estimators/cosypose/cosypose/integrated/detector.py

@@ -4,8 +4,6 @@
 import pandas as pd
 import torch
 
-import happypose.pose_estimators.cosypose.cosypose.utils.tensor_collection as tc
-
 # MegaPose
 import happypose.toolbox.utils.tensor_collection as tc
 from happypose.toolbox.inference.detector import DetectorModule

happypose/pose_estimators/cosypose/cosypose/integrated/icp_refiner.py

@@ -173,8 +173,12 @@ def icp_refinement(
 
     # import trimesh
     # print(points_src.shape, points_tgt.shape)
-    # trimesh.Trimesh(vertices=points_src[:, :3], normals=points_src[:, 3:]).export(DEBUG_DATA_DIR / 'src.ply')
-    # trimesh.Trimesh(vertices=points_tgt[:, :3], normals=points_tgt[:, 3:]).export(DEBUG_DATA_DIR / 'tgt.ply')
+    # trimesh.Trimesh(vertices=points_src[:, :3], normals=points_src[:, 3:]).export(
+    # DEBUG_DATA_DIR / "src.ply"
+    # )
+    # trimesh.Trimesh(vertices=points_tgt[:, :3], normals=points_tgt[:, 3:]).export(
+    # DEBUG_DATA_DIR / "tgt.ply"
+    # )
     # raise ValueError
 
     tolerence = 0.05

happypose/pose_estimators/cosypose/cosypose/integrated/pose_estimator.py

@@ -113,7 +113,8 @@ def batched_model_predictions(self, model, images, K, obj_data, n_iterations=1):
                 preds[f"iteration={n}"].append(batch_preds)
 
         logger.debug(
-            f"Pose prediction on {len(obj_data)} detections (n_iterations={n_iterations}): {timer.stop()}",
+            f"Pose prediction on {len(obj_data)} detections "
+            f"(n_iterations={n_iterations}): {timer.stop()}",
         )
         preds = dict(preds)
         for k, v in preds.items():

happypose/pose_estimators/cosypose/cosypose/integrated/pose_predictor.py

@@ -66,7 +66,8 @@ def batched_model_predictions(self, model, images, K, obj_data, n_iterations=1):
                 preds[f"iteration={n}"].append(batch_preds)
 
         logger.debug(
-            f"Pose prediction on {len(obj_data)} detections (n_iterations={n_iterations}): {timer.stop()}",
+            f"Pose prediction on {len(obj_data)} detections "
+            f"(n_iterations={n_iterations}): {timer.stop()}",
         )
         preds = dict(preds)
         for k, v in preds.items():

happypose/pose_estimators/cosypose/cosypose/lib3d/rigid_mesh_database.py

@@ -16,7 +16,7 @@ class MeshDataBase:
     def __init__(self, obj_list):
         self.infos = {obj["label"]: obj for obj in obj_list}
         self.meshes = {
-            l: trimesh.load(obj["mesh_path"]) for l, obj in self.infos.items()
+            m: trimesh.load(obj["mesh_path"]) for m, obj in self.infos.items()
         }
 
     @staticmethod
@@ -92,9 +92,9 @@ def n_sym_mapping(self):
         return {label: obj["n_sym"] for label, obj in self.infos.items()}
 
     def select(self, labels):
-        ids = [self.label_to_id[l] for l in labels]
+        ids = [self.label_to_id[label] for label in labels]
         return Meshes(
-            infos=[self.infos[l] for l in labels],
+            infos=[self.infos[label] for label in labels],
             labels=self.labels[ids],
             points=self.points[ids],
             symmetries=self.symmetries[ids],

happypose/pose_estimators/cosypose/cosypose/models/efficientnet.py

@@ -144,12 +144,16 @@ def forward(self, inputs, drop_connect_rate=None):
         return x
 
     def set_swish(self, memory_efficient=True):
-        """Sets swish function as memory efficient (for training) or standard (for export)."""
+        """
+        Sets swish function as memory efficient (for training) or standard (for export).
+        """
         self._swish = MemoryEfficientSwish() if memory_efficient else Swish()
 
 
 class EfficientNet(nn.Module):
-    """An EfficientNet model. Most easily loaded with the .from_name or .from_pretrained methods.
+    """
+    An EfficientNet model. Most easily loaded with the .from_name or .from_pretrained
+    methods.
 
     Args:
     ----
@@ -238,7 +242,9 @@ def __init__(self, blocks_args=None, global_params=None, in_channels=3):
         self._swish = MemoryEfficientSwish()
 
     def set_swish(self, memory_efficient=True):
-        """Sets swish function as memory efficient (for training) or standard (for export)."""
+        """
+        Sets swish function as memory efficient (for training) or standard (for export).
+        """
         self._swish = MemoryEfficientSwish() if memory_efficient else Swish()
         for block in self._blocks:
             block.set_swish(memory_efficient)
@@ -261,7 +267,10 @@ def extract_features(self, inputs):
         return x
 
     def forward(self, inputs):
-        """Calls extract_features to extract features, applies final linear layer, and returns logits."""
+        """
+        Calls extract_features to extract features, applies final linear layer, and
+        returns logits.
+        """
         inputs.size(0)
         # Convolution layers
         x = self.extract_features(inputs)

happypose/pose_estimators/cosypose/cosypose/models/efficientnet_utils.py

@@ -1,6 +1,8 @@
 """Copied from https://github.com/lukemelas/EfficientNet-PyTorch
-This file contains helper functions for building the model and for loading model parameters.
-These helper functions are built to mirror those in the official TensorFlow implementation.
+This file contains helper functions for building the model and for loading model
+parameters.
+These helper functions are built to mirror those in the official TensorFlow
+implementation.
 """
 
 import collections
@@ -120,7 +122,8 @@ def drop_connect(inputs, p, training):
 
 
 def get_same_padding_conv2d(image_size=None):
-    """Chooses static padding if you have specified an image size, and dynamic padding otherwise.
+    """Chooses static padding if you have specified an image size, and dynamic padding
+    otherwise.
     Static padding is necessary for ONNX exporting of models.
     """
     if image_size is None:
@@ -193,7 +196,9 @@ def __init__(
 
         # Calculate padding based on image size and save it
         assert image_size is not None
-        ih, iw = image_size if type(image_size) == list else [image_size, image_size]
+        ih, iw = (
+            image_size if isinstance(image_size, list) else [image_size, image_size]
+        )
         kh, kw = self.weight.size()[-2:]
         sh, sw = self.stride
         oh, ow = math.ceil(ih / sh), math.ceil(iw / sw)
@@ -252,7 +257,9 @@ def efficientnet_params(model_name):
 
 
 class BlockDecoder:
-    """Block Decoder for readability, straight from the official TensorFlow repository."""
+    """
+    Block Decoder for readability, straight from the official TensorFlow repository.
+    """
 
     @staticmethod
     def _decode_block_string(block_string):
@@ -377,7 +384,8 @@ def get_model_params(model_name, override_params):
     else:
         raise NotImplementedError("model name is not pre-defined: %s" % model_name)
     if override_params:
-        # ValueError will be raised here if override_params has fields not included in global_params.
+        # ValueError will be raised here if override_params has fields not included in
+        # global_params.
         global_params = global_params._replace(**override_params)
     return blocks_args, global_params
 

happypose/pose_estimators/cosypose/cosypose/models/wide_resnet.py

@@ -17,7 +17,8 @@ def conv3x3(in_planes, out_planes, stride=1):
 
 class BasicBlockV2(nn.Module):
     r"""BasicBlock V2 from
-    `"Identity Mappings in Deep Residual Networks"<https://arxiv.org/abs/1603.05027>`_ paper.
+    `"Identity Mappings in Deep Residual Networks"
+    <https://arxiv.org/abs/1603.05027>`_ paper.
     This is used for ResNet V2 for 18, 34 layers.
 
     Args:

happypose/pose_estimators/cosypose/cosypose/multiview/bundle_adjustment.py

@@ -221,7 +221,8 @@ def align_TCO_cand(self, TWO_9d, TCW_9d):
     def forward_jacobian(self, TWO_9d, TCW_9d, residuals_threshold):
         _, TCO_cand_aligned = self.align_TCO_cand(TWO_9d, TCW_9d)
 
-        # NOTE: This could be *much* faster by computing gradients manually, reducing number of operations.
+        # NOTE: This could be *much* faster by computing gradients manually, reducing
+        # number of operations.
         cand_ids, view_ids, obj_ids, point_ids, xy_ids = (
             self.residuals_ids[k]
             for k in ("cand_id", "view_id", "obj_id", "point_id", "xy_id")

happypose/pose_estimators/cosypose/cosypose/scripts/make_ycbv_compat_models.py

@@ -13,7 +13,8 @@
 
     orig_names = (ds_dir / "ycbv_friendly_names.txt").read_text()
     orig_names = {
-        str(int(l.split(" ")[0])): l.split(" ")[1] for l in orig_names.split("\n")[:-1]
+        str(int(line.split(" ")[0])): line.split(" ")[1]
+        for line in orig_names.split("\n")[:-1]
     }
 
     infos = json.loads((models_dir / "models_info.json").read_text())

happypose/pose_estimators/cosypose/cosypose/scripts/run_bop_inference.py

@@ -22,10 +22,10 @@
     make_object_dataset,
     make_scene_dataset,
 )
-from happypose.pose_estimators.cosypose.cosypose.datasets.wrappers.multiview_wrapper import (
+from happypose.pose_estimators.cosypose.cosypose.datasets.wrappers.multiview_wrapper import (  # noqa: E501
     MultiViewWrapper,
 )
-from happypose.pose_estimators.cosypose.cosypose.evaluation.pred_runner.bop_predictions import (
+from happypose.pose_estimators.cosypose.cosypose.evaluation.pred_runner.bop_predictions import (  # noqa: E501
     BopPredictionRunner,
 )
 from happypose.pose_estimators.cosypose.cosypose.evaluation.runner_utils import (
@@ -46,7 +46,7 @@
 from happypose.pose_estimators.cosypose.cosypose.lib3d.rigid_mesh_database import (
     MeshDataBase,
 )
-from happypose.pose_estimators.cosypose.cosypose.rendering.bullet_batch_renderer import (
+from happypose.pose_estimators.cosypose.cosypose.rendering.bullet_batch_renderer import (  # noqa: E501
     BulletBatchRenderer,
 )
 

happypose/pose_estimators/cosypose/cosypose/scripts/run_colmap_reconstruction.py

@@ -9,7 +9,7 @@
 from happypose.pose_estimators.cosypose.cosypose.datasets.datasets_cfg import (
     make_scene_dataset,
 )
-from happypose.pose_estimators.cosypose.cosypose.datasets.wrappers.multiview_wrapper import (
+from happypose.pose_estimators.cosypose.cosypose.datasets.wrappers.multiview_wrapper import (  # noqa: E501
     MultiViewWrapper,
 )