Revert "much stricter ruff linting"

This reverts commit 310dbf1574.

modules/control/proc/canny.py

@@ -7,7 +7,7 @@ from modules.control.util import HWC3, resize_image
 class CannyDetector:
     def __call__(self, input_image=None, low_threshold=100, high_threshold=200, detect_resolution=512, image_resolution=512, output_type=None, **kwargs):
         if "img" in kwargs:
-            warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning)
             input_image = kwargs.pop("img")
         if input_image is None:
             raise ValueError("input_image must be defined.")

modules/control/proc/depth_anything/util/transform.py

@@ -1,4 +1,7 @@
+import random
+from PIL import Image, ImageOps, ImageFilter
 import torch
+from torchvision import transforms
 import torch.nn.functional as F
 
 import numpy as np

modules/control/proc/depth_pro/__init__.py

@@ -16,7 +16,7 @@ class DepthProDetector:
         self.processor = processor
 
     @classmethod
-    def from_pretrained(cls, pretrained_model_or_path: str = "apple/DepthPro-hf", cache_dir: str | None = None, local_files_only = False) -> "DepthProDetector":
+    def from_pretrained(cls, pretrained_model_or_path: str = "apple/DepthPro-hf", cache_dir: str = None, local_files_only = False) -> "DepthProDetector":
         from transformers import AutoImageProcessor, DepthProForDepthEstimation
 
         processor = AutoImageProcessor.from_pretrained(pretrained_model_or_path, cache_dir=cache_dir, local_files_only=local_files_only)

modules/control/proc/edge.py

@@ -33,7 +33,7 @@ class EdgeDetector:
         params.PFmode = pf
         ed.setParams(params)
         if "img" in kwargs:
-            warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("img is deprecated, please use `input_image=...` instead.", DeprecationWarning)
             input_image = kwargs.pop("img")
         if input_image is None:
             raise ValueError("input_image must be defined.")

modules/control/proc/leres/leres/Resnext_torch.py

@@ -5,7 +5,7 @@ import torch.nn as nn
 try:
     from urllib import urlretrieve
 except ImportError:
-    pass
+    from urllib.request import urlretrieve
 
 __all__ = ['resnext101_32x8d']
 

modules/control/proc/leres/leres/multi_depth_model_woauxi.py

@@ -1,3 +1,4 @@
+import torch
 import torch.nn as nn
 
 from . import network_auxi as network

modules/control/proc/leres/leres/network_auxi.py

@@ -384,7 +384,7 @@ class SenceUnderstand(nn.Module):
         self.initial_params()
 
     def forward(self, x):
-        n, _c, h, w = x.size()
+        n, c, h, w = x.size()
         x = self.conv1(x)
         x = self.pool(x)
         x = x.view(n, -1)

modules/control/proc/leres/pix2pix/options/base_options.py

@@ -1,8 +1,8 @@
 import argparse
 import os
-from ...pix2pix.util import util  # noqa: TID252
+from ...pix2pix.util import util
 # import torch
-from ...pix2pix import models  # noqa: TID252
+from ...pix2pix import models
 # import pix2pix.data
 import numpy as np
 

modules/control/proc/marigold/marigold_pipeline.py

@@ -113,7 +113,7 @@ class MarigoldPipeline(DiffusionPipeline):
         batch_size: int = 0,
         color_map: str = "Spectral",
         show_progress_bar: bool = True,
-        ensemble_kwargs: Dict | None = None,
+        ensemble_kwargs: Dict = None,
     ) -> MarigoldDepthOutput:
         """
         Function invoked when calling the pipeline.

modules/control/proc/marigold/util/ensemble.py

@@ -43,7 +43,7 @@ def ensemble_depths(
     max_iter: int = 2,
     tol: float = 1e-3,
     reduction: str = "median",
-    max_res: int | None = None,
+    max_res: int = None,
 ):
     """
     To ensemble multiple affine-invariant depth images (up to scale and shift),

modules/control/proc/marigold/util/seed_all.py

@@ -28,6 +28,6 @@ def seed_all(seed: int = 0):
     Set random seeds of all components.
     """
     random.seed(seed)
-    np.random.seed(seed)
+    np.random.seed(seed) # noqa
     torch.manual_seed(seed)
     torch.cuda.manual_seed_all(seed)

modules/control/proc/mediapipe_face.py

@@ -16,6 +16,7 @@ def check_dependencies():
         if not installed(pkg[1], quiet=True):
             install(pkg[0], pkg[1], ignore=False)
     try:
+        import mediapipe as mp # pylint: disable=unused-import
         checked_ok = True
         return True
     except Exception as e:

modules/control/proc/midas/api.py

@@ -2,6 +2,7 @@
 
 import cv2
 import os
+import torch
 import torch.nn as nn
 from torchvision.transforms import Compose
 

modules/control/proc/midas/midas/blocks.py

@@ -5,6 +5,7 @@ from .vit import (
     _make_pretrained_vitb_rn50_384,
     _make_pretrained_vitl16_384,
     _make_pretrained_vitb16_384,
+    forward_vit,
 )
 
 def _make_encoder(backbone, features, use_pretrained, groups=1, expand=False, exportable=True, hooks=None, use_vit_only=False, use_readout="ignore",):

modules/control/proc/midas/midas/dpt_depth.py

@@ -1,8 +1,10 @@
 import torch
 import torch.nn as nn
+import torch.nn.functional as F
 
 from .base_model import BaseModel
 from .blocks import (
+    FeatureFusionBlock,
     FeatureFusionBlock_custom,
     Interpolate,
     _make_encoder,

modules/control/proc/midas/midas/midas_net_custom.py

@@ -6,7 +6,7 @@ import torch
 import torch.nn as nn
 
 from .base_model import BaseModel
-from .blocks import FeatureFusionBlock_custom, Interpolate, _make_encoder
+from .blocks import FeatureFusionBlock, FeatureFusionBlock_custom, Interpolate, _make_encoder
 
 
 class MidasNet_small(BaseModel):

modules/control/proc/midas/midas/vit.py

@@ -54,7 +54,7 @@ class Transpose(nn.Module):
 
 
 def forward_vit(pretrained, x):
-    _b, _c, h, w = x.shape
+    b, c, h, w = x.shape
 
     pretrained.model.forward_flex(x)
 
@@ -115,7 +115,7 @@ def _resize_pos_embed(self, posemb, gs_h, gs_w):
 
 
 def forward_flex(self, x):
-    _b, _c, h, w = x.shape
+    b, c, h, w = x.shape
 
     pos_embed = self._resize_pos_embed(
         self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]

modules/control/proc/midas/utils.py

@@ -75,7 +75,7 @@ def write_pfm(path, image, scale=1):
         if len(image.shape) == 3 and image.shape[2] == 3:  # color image
             color = True
         elif (
-            len(image.shape) == 2 or (len(image.shape) == 3 and image.shape[2] == 1)
+            len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1
         ):  # greyscale
             color = False
         else:
@@ -86,7 +86,7 @@ def write_pfm(path, image, scale=1):
 
         endian = image.dtype.byteorder
 
-        if endian == "<" or (endian == "=" and sys.byteorder == "little"):
+        if endian == "<" or endian == "=" and sys.byteorder == "little":
             scale = -scale
 
         file.write("%f\n".encode() % scale)

modules/control/proc/mlsd/models/mbv2_mlsd_large.py

@@ -1,3 +1,5 @@
+import os
+import sys
 import torch
 import torch.nn as nn
 import torch.utils.model_zoo as model_zoo

modules/control/proc/mlsd/models/mbv2_mlsd_tiny.py

@@ -1,3 +1,5 @@
+import os
+import sys
 import torch
 import torch.nn as nn
 import torch.utils.model_zoo as model_zoo

modules/control/proc/mlsd/utils.py

@@ -9,6 +9,7 @@ Copyright 2021-present NAVER Corp.
 Apache License v2.0
 '''
 
+import os
 import numpy as np
 import cv2
 import torch
@@ -21,7 +22,7 @@ def deccode_output_score_and_ptss(tpMap, topk_n = 200, ksize = 5):
     center: tpMap[1, 0, :, :]
     displacement: tpMap[1, 1:5, :, :]
     '''
-    b, _c, _h, w = tpMap.shape
+    b, c, h, w = tpMap.shape
     assert  b==1, 'only support bsize==1'
     displacement = tpMap[:, 1:5, :, :][0]
     center = tpMap[:, 0, :, :]
@@ -470,9 +471,9 @@ def pred_squares(image,
                 square[end_idx]
 
                 # check whether outside or inside
-                _start_position, start_min, start_cover_param, start_peri_param = check_outside_inside(start_segments,
+                start_position, start_min, start_cover_param, start_peri_param = check_outside_inside(start_segments,
                                                                                                       connect_idx)
-                _end_position, end_min, end_cover_param, end_peri_param = check_outside_inside(end_segments, connect_idx)
+                end_position, end_min, end_cover_param, end_peri_param = check_outside_inside(end_segments, connect_idx)
 
                 cover += dist_segments[connect_idx] + start_cover_param * start_min + end_cover_param * end_min
                 perimeter += dist_segments[connect_idx] + start_peri_param * start_min + end_peri_param * end_min

modules/control/proc/openpose/__init__.py

@@ -194,14 +194,14 @@ class OpenposeDetector:
     def __call__(self, input_image, detect_resolution=512, image_resolution=512, include_body=True, include_hand=False, include_face=False, hand_and_face=None, output_type="pil", **kwargs):
         self.to(devices.device)
         if hand_and_face is not None:
-            warnings.warn("hand_and_face is deprecated. Use include_hand and include_face instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("hand_and_face is deprecated. Use include_hand and include_face instead.", DeprecationWarning)
             include_hand = hand_and_face
             include_face = hand_and_face
         if "return_pil" in kwargs:
-            warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning)
             output_type = "pil" if kwargs["return_pil"] else "np"
         if type(output_type) is bool:
-            warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions", stacklevel=2)
+            warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions")
             if output_type:
                 output_type = "pil"
         if not isinstance(input_image, np.ndarray):

modules/control/proc/openpose/face.py

@@ -328,7 +328,7 @@ class Face(object):
 
     def __call__(self, face_img):
         device = next(iter(self.model.parameters())).device
-        H, W, _C = face_img.shape
+        H, W, C = face_img.shape
 
         w_size = 384
         x_data = torch.from_numpy(util.smart_resize(face_img, (w_size, w_size))).permute([2, 0, 1]) / 256.0 - 0.5

modules/control/proc/openpose/hand.py

@@ -32,7 +32,7 @@ class Hand(object):
         wsize = 128
         heatmap_avg = np.zeros((wsize, wsize, 22))
 
-        Hr, Wr, _Cr = oriImgRaw.shape
+        Hr, Wr, Cr = oriImgRaw.shape
 
         oriImg = cv2.GaussianBlur(oriImgRaw, (0, 0), 0.8)
 

modules/control/proc/segment_anything/__init__.py

@@ -53,7 +53,7 @@ class SamDetector:
 
     def __call__(self, input_image: Union[np.ndarray, Image.Image]=None, detect_resolution=512, image_resolution=512, output_type="pil", **kwargs) -> Image.Image:
         if "image" in kwargs:
-            warnings.warn("image is deprecated, please use `input_image=...` instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("image is deprecated, please use `input_image=...` instead.", DeprecationWarning)
             input_image = kwargs.pop("image")
         if input_image is None:
             raise ValueError("input_image must be defined.")

modules/control/proc/segment_anything/modeling/sam.py

@@ -25,8 +25,8 @@ class Sam(nn.Module):
         image_encoder: Union[ImageEncoderViT, TinyViT],
         prompt_encoder: PromptEncoder,
         mask_decoder: MaskDecoder,
-      pixel_mean: List[float] | None = None,
-      pixel_std: List[float] | None = None,
+        pixel_mean: List[float] = None,
+        pixel_std: List[float] = None,
     ) -> None:
         """
         SAM predicts object masks from an image and input prompts.

modules/control/proc/segment_anything/modeling/transformer.py

@@ -79,7 +79,7 @@ class TwoWayTransformer(nn.Module):
           torch.Tensor: the processed image_embedding
         """
         # BxCxHxW -> BxHWxC == B x N_image_tokens x C
-        _bs, _c, _h, _w = image_embedding.shape
+        bs, c, h, w = image_embedding.shape
         image_embedding = image_embedding.flatten(2).permute(0, 2, 1)
         image_pe = image_pe.flatten(2).permute(0, 2, 1)
 

modules/control/proc/segment_anything/utils/onnx.py

@@ -10,7 +10,7 @@ from torch.nn import functional as F
 
 from typing import Tuple
 
-from ..modeling import Sam  # noqa: TID252
+from ..modeling import Sam
 from .amg import calculate_stability_score
 
 

modules/control/proc/shuffle.py

@@ -10,10 +10,10 @@ from modules.control.util import HWC3, img2mask, make_noise_disk, resize_image
 class ContentShuffleDetector:
     def __call__(self, input_image, h=None, w=None, f=None, detect_resolution=512, image_resolution=512, output_type="pil", **kwargs):
         if "return_pil" in kwargs:
-            warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning, stacklevel=2)
+            warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning)
             output_type = "pil" if kwargs["return_pil"] else "np"
         if type(output_type) is bool:
-            warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions", stacklevel=2)
+            warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions")
             if output_type:
                 output_type = "pil"
 
@@ -49,7 +49,7 @@ class ContentShuffleDetector:
 class ColorShuffleDetector:
     def __call__(self, img):
         H, W, C = img.shape
-        F = np.random.randint(64, 384)
+        F = np.random.randint(64, 384) # noqa
         A = make_noise_disk(H, W, 3, F)
         B = make_noise_disk(H, W, 3, F)
         C = (A + B) / 2.0
@@ -82,11 +82,11 @@ class DownSampleDetector:
     def __call__(self, img, level=3, k=16.0):
         h = img.astype(np.float32)
         for _ in range(level):
-            h += np.random.normal(loc=0.0, scale=k, size=h.shape)
+            h += np.random.normal(loc=0.0, scale=k, size=h.shape) # noqa
             h = cv2.pyrDown(h)
         for _ in range(level):
             h = cv2.pyrUp(h)
-            h += np.random.normal(loc=0.0, scale=k, size=h.shape)
+            h += np.random.normal(loc=0.0, scale=k, size=h.shape) # noqa
         return h.clip(0, 255).astype(np.uint8)
 
 

modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/beit.py

@@ -66,7 +66,7 @@ def attention_forward(self, x, resolution, shared_rel_pos_bias: Optional[torch.T
     """
     Modification of timm.models.beit.py: Attention.forward to support arbitrary window sizes.
     """
-    B, N, _C = x.shape
+    B, N, C = x.shape
 
     qkv_bias = torch.cat((self.q_bias, self.k_bias, self.v_bias)) if self.q_bias is not None else None
     qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)

modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/utils.py

@@ -81,7 +81,7 @@ def forward_default(pretrained, x, function_name="forward_features"):
 
 
 def forward_adapted_unflatten(pretrained, x, function_name="forward_features"):
-    _b, _c, h, w = x.shape
+    b, c, h, w = x.shape
 
     exec(f"glob = pretrained.model.{function_name}(x)")
 

modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/backbones/vit.py

@@ -31,7 +31,7 @@ def _resize_pos_embed(self, posemb, gs_h, gs_w):
 
 
 def forward_flex(self, x):
-    _b, _c, h, w = x.shape
+    b, c, h, w = x.shape
 
     pos_embed = self._resize_pos_embed(
         self.pos_embed, h // self.patch_size[1], w // self.patch_size[0]

modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/blocks.py

@@ -5,6 +5,10 @@ from .backbones.beit import (
     _make_pretrained_beitl16_512,
     _make_pretrained_beitl16_384,
     _make_pretrained_beitb16_384,
+    forward_beit,
+)
+from .backbones.swin_common import (
+    forward_swin,
 )
 from .backbones.swin2 import (
     _make_pretrained_swin2l24_384,
@@ -16,11 +20,13 @@ from .backbones.swin import (
 )
 from .backbones.levit import (
     _make_pretrained_levit_384,
+    forward_levit,
 )
 from .backbones.vit import (
     _make_pretrained_vitb_rn50_384,
     _make_pretrained_vitl16_384,
     _make_pretrained_vitb16_384,
+    forward_vit,
 )
 
 def _make_encoder(backbone, features, use_pretrained, groups=1, expand=False, exportable=True, hooks=None,

modules/control/proc/zoe/zoedepth/models/base_models/midas_repo/midas/midas_net_custom.py

@@ -6,7 +6,7 @@ import torch
 import torch.nn as nn
 
 from .base_model import BaseModel
-from .blocks import FeatureFusionBlock_custom, Interpolate, _make_encoder
+from .blocks import FeatureFusionBlock, FeatureFusionBlock_custom, Interpolate, _make_encoder
 
 
 class MidasNet_small(BaseModel):

modules/control/proc/zoe/zoedepth/models/layers/attractor.py

@@ -100,7 +100,7 @@ class AttractorLayer(nn.Module):
         A = self._net(x)
         eps = 1e-3
         A = A + eps
-        n, _c, h, w = A.shape
+        n, c, h, w = A.shape
         A = A.view(n, self.n_attractors, 2, h, w)
         A_normed = A / A.sum(dim=2, keepdim=True)  # n, a, 2, h, w
         A_normed = A[:, :, 0, ...]  # n, na, h, w
@@ -177,7 +177,7 @@ class AttractorLayerUnnormed(nn.Module):
             x = x + prev_b_embedding
 
         A = self._net(x)
-        _n, _c, h, w = A.shape
+        n, c, h, w = A.shape
 
         b_prev = nn.functional.interpolate(
             b_prev, (h, w), mode='bilinear', align_corners=True)

modules/control/proc/zoe/zoedepth/models/layers/localbins_layers.py

@@ -146,7 +146,7 @@ class LinearSplitter(nn.Module):
         S = self._net(x)
         eps = 1e-3
         S = S + eps
-        n, _c, h, w = S.shape
+        n, c, h, w = S.shape
         S = S.view(n, self.prev_nbins, self.split_factor, h, w)
         S_normed = S / S.sum(dim=2, keepdim=True)  # fractional splits
 

modules/control/proc/zoe/zoedepth/models/zoedepth/zoedepth_v1.py

@@ -26,13 +26,13 @@ import itertools
 
 import torch
 import torch.nn as nn
-from ..depth_model import DepthModel  # noqa: TID252
-from ..base_models.midas import MidasCore  # noqa: TID252
-from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed  # noqa: TID252
-from ..layers.dist_layers import ConditionalLogBinomial  # noqa: TID252
-from ..layers.localbins_layers import (Projector, SeedBinRegressor,  # noqa: TID252
+from ..depth_model import DepthModel
+from ..base_models.midas import MidasCore
+from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed
+from ..layers.dist_layers import ConditionalLogBinomial
+from ..layers.localbins_layers import (Projector, SeedBinRegressor,
                                             SeedBinRegressorUnnormed)
-from ..model_io import load_state_from_resource  # noqa: TID252
+from ..model_io import load_state_from_resource
 
 
 class ZoeDepth(DepthModel):
@@ -139,7 +139,7 @@ class ZoeDepth(DepthModel):
                 - probs (torch.Tensor): Output probability distribution of shape (B, n_bins, H, W). Present only if return_probs is True
 
         """
-        b, _c, h, w = x.shape
+        b, c, h, w = x.shape
         # print("input shape ", x.shape)
         self.orig_input_width = w
         self.orig_input_height = h

modules/control/proc/zoe/zoedepth/models/zoedepth_nk/zoedepth_nk_v1.py

@@ -27,14 +27,14 @@ import itertools
 import torch
 import torch.nn as nn
 
-from ..depth_model import DepthModel  # noqa: TID252
-from ..base_models.midas import MidasCore  # noqa: TID252
-from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed  # noqa: TID252
-from ..layers.dist_layers import ConditionalLogBinomial  # noqa: TID252
-from ..layers.localbins_layers import (Projector, SeedBinRegressor,  # noqa: TID252
+from ..depth_model import DepthModel
+from ..base_models.midas import MidasCore
+from ..layers.attractor import AttractorLayer, AttractorLayerUnnormed
+from ..layers.dist_layers import ConditionalLogBinomial
+from ..layers.localbins_layers import (Projector, SeedBinRegressor,
                                             SeedBinRegressorUnnormed)
-from ..layers.patch_transformer import PatchTransformerEncoder  # noqa: TID252
-from ..model_io import load_state_from_resource  # noqa: TID252
+from ..layers.patch_transformer import PatchTransformerEncoder
+from ..model_io import load_state_from_resource
 
 class ZoeDepthNK(DepthModel):
     def __init__(self, core,  bin_conf, bin_centers_type="softplus", bin_embedding_dim=128,
@@ -173,10 +173,10 @@ class ZoeDepthNK(DepthModel):
                 - "bin_centers": Bin centers of shape (B, N, H, W). Present only if return_final_centers is True
                 - "probs": Bin probabilities of shape (B, N, H, W). Present only if return_probs is True
         """
-        b, _c, h, w = x.shape
+        b, c, h, w = x.shape
         self.orig_input_width = w
         self.orig_input_height = h
-        _rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
+        rel_depth, out = self.core(x, denorm=denorm, return_rel_depth=True)
 
         outconv_activation = out[0]
         btlnck = out[1]