Use pre-commit to reformat code

Use pre-commit to reformat code

autonomous_driving/openlane-v2/tools/data_converter/nuscenes_converter.py

@@ -6,14 +6,13 @@ from typing import List, Tuple, Union
 
 import mmcv
 import numpy as np
+from mmdet3d.core.bbox import points_cam2img
+from mmdet3d.datasets import NuScenesDataset
 from nuscenes.nuscenes import NuScenes
 from nuscenes.utils.geometry_utils import view_points
 from pyquaternion import Quaternion
 from shapely.geometry import MultiPoint, box
 
-from mmdet3d.core.bbox import points_cam2img
-from mmdet3d.datasets import NuScenesDataset
-
 nus_categories = ('car', 'truck', 'trailer', 'bus', 'construction_vehicle',
                   'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
                   'barrier')

autonomous_driving/openlane-v2/tools/data_converter/s3dis_data_utils.py

@@ -221,7 +221,7 @@ class S3DISSegData(object):
         """
         num_classes = len(self.cat_ids)
         num_point_all = []
-        label_weight = np.zeros((num_classes + 1, ))  # ignore_index
+        label_weight = np.zeros((num_classes + 1,))  # ignore_index
         for data_info in self.data_infos:
             label = self._convert_to_label(
                 osp.join(self.data_root, data_info['pts_semantic_mask_path']))

autonomous_driving/openlane-v2/tools/data_converter/scannet_data_utils.py

@@ -273,7 +273,7 @@ class ScanNetSegData(object):
         """
         num_classes = len(self.cat_ids)
         num_point_all = []
-        label_weight = np.zeros((num_classes + 1, ))  # ignore_index
+        label_weight = np.zeros((num_classes + 1,))  # ignore_index
         for data_info in self.data_infos:
             label = self._convert_to_label(
                 osp.join(self.data_root, data_info['pts_semantic_mask_path']))

autonomous_driving/openlane-v2/tools/data_converter/sunrgbd_data_utils.py

@@ -47,7 +47,7 @@ class SUNRGBDInstance(object):
         # z_size (height) in our depth coordinate system,
         # l corresponds to the size along the x axis
         self.size = np.array([data[9], data[8], data[10]]) * 2
-        self.orientation = np.zeros((3, ))
+        self.orientation = np.zeros((3,))
         self.orientation[0] = data[11]
         self.orientation[1] = data[12]
         self.heading_angle = np.arctan2(self.orientation[1],

autonomous_driving/openlane-v2/tools/data_converter/waymo_converter.py

@@ -171,7 +171,7 @@ class Waymo2KITTI(object):
                 self.cart_to_homo(T_front_cam_to_ref) @ T_vehicle_to_cam
             if camera.name == 1:  # FRONT = 1, see dataset.proto for details
                 self.T_velo_to_front_cam = Tr_velo_to_cam.copy()
-            Tr_velo_to_cam = Tr_velo_to_cam[:3, :].reshape((12, ))
+            Tr_velo_to_cam = Tr_velo_to_cam[:3, :].reshape((12,))
             Tr_velo_to_cams.append([f'{i:e}' for i in Tr_velo_to_cam])
 
             # intrinsic parameters

autonomous_driving/openlane-v2/tools/deployment/mmdet3d_handler.py

@@ -4,10 +4,9 @@ import os
 
 import numpy as np
 import torch
-from ts.torch_handler.base_handler import BaseHandler
-
 from mmdet3d.apis import inference_detector, init_model
 from mmdet3d.core.points import get_points_type
+from ts.torch_handler.base_handler import BaseHandler
 
 
 class MMdet3dHandler(BaseHandler):

autonomous_driving/openlane-v2/tools/deployment/test_torchserver.py

@@ -2,7 +2,6 @@ from argparse import ArgumentParser
 
 import numpy as np
 import requests
-
 from mmdet3d.apis import inference_detector, init_model
 
 

autonomous_driving/openlane-v2/tools/misc/browse_dataset.py

@@ -7,7 +7,6 @@ from pathlib import Path
 import mmcv
 import numpy as np
 from mmcv import Config, DictAction, mkdir_or_exist
-
 from mmdet3d.core.bbox import (Box3DMode, CameraInstance3DBoxes, Coord3DMode,
                                DepthInstance3DBoxes, LiDARInstance3DBoxes)
 from mmdet3d.core.visualizer import (show_multi_modality_result, show_result,

autonomous_driving/openlane-v2/tools/misc/fuse_conv_bn.py

@@ -3,9 +3,8 @@ import argparse
 
 import torch
 from mmcv.runner import save_checkpoint
-from torch import nn as nn
-
 from mmdet3d.apis import init_model
+from torch import nn as nn
 
 
 def fuse_conv_bn(conv, bn):

autonomous_driving/openlane-v2/tools/misc/visualize_results.py

@@ -3,7 +3,6 @@ import argparse
 
 import mmcv
 from mmcv import Config
-
 from mmdet3d.datasets import build_dataset
 
 

autonomous_driving/openlane-v2/tools/model_converters/convert_h3dnet_checkpoints.py

@@ -5,7 +5,6 @@ import tempfile
 import torch
 from mmcv import Config
 from mmcv.runner import load_state_dict
-
 from mmdet3d.models import build_detector
 
 

autonomous_driving/openlane-v2/tools/model_converters/convert_votenet_checkpoints.py

@@ -5,7 +5,6 @@ import tempfile
 import torch
 from mmcv import Config
 from mmcv.runner import load_state_dict
-
 from mmdet3d.models import build_detector
 
 

autonomous_driving/openlane-v2/tools/test.py

@@ -4,14 +4,13 @@ import os
 import warnings
 
 import mmcv
+import mmdet
 import torch
 from mmcv import Config, DictAction
 from mmcv.cnn import fuse_conv_bn
 from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
 from mmcv.runner import (get_dist_info, init_dist, load_checkpoint,
                          wrap_fp16_model)
-
-import mmdet
 from mmdet3d.apis import single_gpu_test
 from mmdet3d.datasets import build_dataloader, build_dataset
 from mmdet3d.models import build_model

autonomous_driving/openlane-v2/tools/train.py

 # Copyright (c) OpenMMLab. All rights reserved.
 from __future__ import division
+
 import argparse
 import copy
 import os
@@ -12,7 +13,6 @@ import torch
 import torch.distributed as dist
 from mmcv import Config, DictAction
 from mmcv.runner import get_dist_info, init_dist
-
 from mmdet import __version__ as mmdet_version
 from mmdet3d import __version__ as mmdet3d_version
 from mmdet3d.apis import init_random_seed, train_model

autonomous_driving/openlane-v2/tools/update_data_coords.py

@@ -4,7 +4,6 @@ from os import path as osp
 
 import mmcv
 import numpy as np
-
 from mmdet3d.core.bbox import limit_period
 
 
@@ -61,7 +60,6 @@ def update_outdoor_dbinfos(root_dir, out_dir, pkl_files):
 
 
 def update_nuscenes_or_lyft_infos(root_dir, out_dir, pkl_files):
-
     print(f'{pkl_files} will be modified because '
           f'of the refactor of the LIDAR coordinate system.')
     if root_dir == out_dir:

classification/README.md

@@ -3,14 +3,16 @@
 This folder contains the implementation of the InternImage for image classification.
 
 <!-- TOC -->
-* [Install](#install)
-* [Data Preparation](#data-preparation)
-* [Evaluation](#evaluation)
-* [Training from Scratch on ImageNet-1K](#training-from-scratch-on-imagenet-1k)
-* [Manage Jobs with Slurm](#manage-jobs-with-slurm)
-* [Training with Deepspeed](#training-with-deepspeed)
-* [Extracting Intermediate Features](#extracting-intermediate-features)
-* [Export](#export)
+
+- [Install](#install)
+- [Data Preparation](#data-preparation)
+- [Evaluation](#evaluation)
+- [Training from Scratch on ImageNet-1K](#training-from-scratch-on-imagenet-1k)
+- [Manage Jobs with Slurm](#manage-jobs-with-slurm)
+- [Training with Deepspeed](#training-with-deepspeed)
+- [Extracting Intermediate Features](#extracting-intermediate-features)
+- [Export](#export)
+
 <!-- TOC -->
 
 ## Usage
@@ -36,6 +38,7 @@ conda activate internimage
 - Install `PyTorch>=1.10.0` and `torchvision>=0.9.0` with `CUDA>=10.2`:
 
 For examples, to install torch==1.11 with CUDA==11.3:
+
 ```bash
 pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113  -f https://download.pytorch.org/whl/torch_stable.html
 ```
@@ -55,20 +58,24 @@ pip install opencv-python termcolor yacs pyyaml scipy
 ```
 
 - Compiling CUDA operators
+
 ```bash
 cd ./ops_dcnv3
 sh ./make.sh
 # unit test (should see all checking is True)
 python test.py
 ```
+
 - You can also install the operator using .whl files
-[DCNv3-1.0-whl](https://github.com/OpenGVLab/InternImage/releases/tag/whl_files)
+  [DCNv3-1.0-whl](https://github.com/OpenGVLab/InternImage/releases/tag/whl_files)
+
 ### Data Preparation
 
 We use standard ImageNet dataset, you can download it from http://image-net.org/. We provide the following two ways to
 load data:
 
 - For standard folder dataset, move validation images to labeled sub-folders. The file structure should look like:
+
   ```bash
   $ tree data
   imagenet
@@ -92,8 +99,10 @@ load data:
       └── ...
 
   ```
+
 - To boost the slow speed when reading images from massive small files, we also support zipped ImageNet, which includes
   four files:
+
   - `train.zip`, `val.zip`: which store the zipped folder for train and validate splits.
   - `train.txt`, `val.txt`: which store the relative path in the corresponding zip file and ground truth
     label. Make sure the data folder looks like this:
@@ -121,6 +130,7 @@ load data:
   n01440764/n01440764_10040.JPEG	0
   n01440764/n01440764_10042.JPEG	0
   ```
+
 - For ImageNet-22K dataset, make a folder named `fall11_whole` and move all images to labeled sub-folders in this
   folder. Then download the train-val split
   file ([ILSVRC2011fall_whole_map_train.txt](https://github.com/SwinTransformer/storage/releases/download/v2.0.1/ILSVRC2011fall_whole_map_train.txt)
@@ -220,6 +230,7 @@ pip install deepspeed==0.8.3
 
 Then you could launch the training in a slurm system with 8 GPUs as follows (tiny and huge as examples).
 The default zero stage is 1 and it could config via command line args `--zero-stage`.
+
 ```
 GPUS=8 GPUS_PER_NODE=8 sh train_in1k_deepspeed.sh vc_research_4 train configs/internimage_t_1k_224.yaml --batch-size 128 --accumulation-steps 4
 GPUS=8 GPUS_PER_NODE=8 sh train_in1k_deepspeed.sh vc_research_4 train configs/internimage_t_1k_224.yaml --batch-size 128 --accumulation-steps 4 --eval --resume ckpt.pth
@@ -228,7 +239,6 @@ GPUS=8 GPUS_PER_NODE=8 sh train_in1k_deepspeed.sh vc_research_4 train configs/in
 GPUS=8 GPUS_PER_NODE=8 sh train_in1k_deepspeed.sh vc_research_4 train configs/internimage_h_22kto1k_640.yaml --batch-size 16 --accumulation-steps 4 --pretrained ckpt/internimage_h_jointto22k_384.pth --zero-stage 3
 ```
 
-
 🤗 **Huggingface Accelerate Integration of Deepspeed**
 
 Optionally, you could use our [Huggingface accelerate](https://github.com/huggingface/accelerate) integration to use deepspeed.
@@ -250,7 +260,7 @@ Here is the reference GPU memory cost for InternImage-H with 8 GPUs.
 - total batch size = 512, 16 batch size for each GPU, gradient accumulation steps = 4.
 
 | Resolution | Deepspeed | Cpu offloading | Memory |
-| --- | --- | --- | --- |
+| ---------- | --------- | -------------- | ------ |
 | 640        | zero1     | False          | 22572  |
 | 640        | zero3     | False          | 20000  |
 | 640        | zero3     | True           | 19144  |
@@ -280,16 +290,16 @@ For example, extract features of `b.png` from layers `patch_embed` and `levels.0
 python extract_feature.py --cfg configs/internimage_t_1k_224.yaml --img b.png --keys patch_embed levels.0.downsample --save --resume internimage_t_1k_224.pth
 ```
 
-
-
 ### Export
 
 To export `InternImage-T` from PyTorch to ONNX, run:
+
 ```shell
 python export.py --model_name internimage_t_1k_224 --ckpt_dir /path/to/ckpt/dir --onnx
 ```
 
 To export `InternImage-T` from PyTorch to TensorRT, run:
+
 ```shell
 python export.py --model_name internimage_t_1k_224 --ckpt_dir /path/to/ckpt/dir --trt
 ```

classification/config.py

@@ -5,6 +5,7 @@
 # --------------------------------------------------------
 
 import os
+
 import yaml
 from yacs.config import CfgNode as CN
 
@@ -82,7 +83,6 @@ _C.MODEL.INTERN_IMAGE.CENTER_FEATURE_SCALE = False
 _C.MODEL.INTERN_IMAGE.REMOVE_CENTER = False
 
 
-
 # -----------------------------------------------------------------------------
 # Training settings
 # -----------------------------------------------------------------------------