format code

.flake8

@@ -1,4 +1,4 @@
 [flake8]
 max-line-length = 90
-exclude = file1.py, **/__init__.py
+exclude = ./Chapter08-FinalProject/OccNet/projects/mmdet3d_plugin/bevformer/modules/voxel_encoder.py, **/__init__.py
 

.gitmodules

@@ -49,14 +49,17 @@
     url = https://github.com/OpenDriveLab/UniAD
 
 [submodule "SurroundOcc"]
-    path = code/SurroundOcc
+    path = dataset/SurroundOcc
     url = https://github.com/weiyithu/SurroundOcc
 [submodule "Occ3D"]
-    path = code/Occ3D
+    path = dataset/Occ3D
     url = https://github.com/Tsinghua-MARS-Lab/Occ3D
 [submodule "OpenScene"]
-    path = code/OpenScene
+    path = dataset/OpenScene
     url = https://github.com/OpenDriveLab/OpenScene
+[submodule "OpenOccupancy"]
+    path = dataset/OpenOccupancy
+    url = https://github.com/JeffWang987/OpenOccupancy
 
 
 [submodule "Deformable-DETR"]

Chapter03-重要数据集和Benchmark介绍/README.md

@@ -1,3 +1,26 @@
+## nuScenes: A Multimodal Dataset for Autonomous Driving
+
+https://www.youtube.com/watch?v=C6KbbndonGg
+
+https://www.nuscenes.org/nuscenes#download
+
+### Viz
+
+- streetscape.gl
+    - https://www.youtube.com/watch?v=irS9H0fU-ig
+    - https://github.com/prodramp/DeepWorks/tree/main/selfdrivingtech/streetscape.gl_demo
+- apollo-DreamView
+    - https://github.com/ApolloAuto/apollo/tree/master/modules/dreamview
+- Carla 
+    - https://www.bilibili.com/video/BV1eN4y1Z7Zy
+- lgsvl https://github.com/lgsvl/simulator
+- Foxglove Studio https://github.com/foxglove/studio
+    - https://github.com/foxglove/nuscenes2mcap
+## Occ3D datasets
+
+- Occ3D
+- OpenOccupancy
+- SurroundOcc
 
 ### 3D Occupancy Prediction Challenge at CVPR 2023 (Server remains `active`)
 

Chapter06-占据网络部署小试：模型量化加速与部署/BEVFormer_tensorrt/configs/bevformer/bevformer_base.py

@@ -286,7 +286,10 @@
 optimizer = dict(
     type="AdamW",
     lr=2e-4,
-    paramwise_cfg=dict(custom_keys={"img_backbone": dict(lr_mult=0.1),}),
+    paramwise_cfg=dict(
+        custom_keys={
+            'img_backbone': dict(lr_mult=0.1),
+        }),
     weight_decay=0.01,
 )
 

Chapter06-占据网络部署小试：模型量化加速与部署/BEVFormer_tensorrt/configs/bevformer/bevformer_small.py

@@ -298,7 +298,10 @@
 optimizer = dict(
     type="AdamW",
     lr=2e-4,
-    paramwise_cfg=dict(custom_keys={"img_backbone": dict(lr_mult=0.1),}),
+    paramwise_cfg=dict(
+        custom_keys={
+            'img_backbone': dict(lr_mult=0.1),
+        }),
     weight_decay=0.01,
 )
 

Chapter06-占据网络部署小试：模型量化加速与部署/BEVFormer_tensorrt/configs/bevformer/bevformer_tiny.py

@@ -295,7 +295,10 @@
 optimizer = dict(
     type="AdamW",
     lr=2e-4,
-    paramwise_cfg=dict(custom_keys={"img_backbone": dict(lr_mult=0.1),}),
+    paramwise_cfg=dict(
+        custom_keys={
+            'img_backbone': dict(lr_mult=0.1),
+        }),
     weight_decay=0.01,
 )
 

Chapter07-课程展望与总结/README.md

@@ -2,7 +2,7 @@
  * @Author: Charmve [email protected]
  * @Date: 2023-10-10 10:49:13
  * @LastEditors: Charmve [email protected]
- * @LastEditTime: 2024-01-31 22:58:00
+ * @LastEditTime: 2024-02-02 01:16:50
  * @FilePath: /OccNet-Course/Chapter07-课程展望与总结/README.md
  * @Version: 1.0.1
  * @Blogs: charmve.blog.csdn.net
@@ -16,12 +16,19 @@
 
 在本专题课程的课程展望和总结中，主要从算法框架、数据、仿真和其他四个方面做未来展望，以及对本课程做一个总结。
 
-- <b>算法框</b>
-    - 数据驱动的端到端 UniAD
+- <b>算法框架</b>
+    - 数据驱动的端到端 [UniAD](https://github.com/OpenDriveLab/UniAD)
+      - https://mp.weixin.qq.com/s/qcNtRsBD5aadkavU9TfpFA
       - https://github.com/OpenDriveLab/End-to-end-Autonomous-Driving
+            - End-to-end Interpretable Neural Motion Planner [paper](https://arxiv.org/abs/2101.06679)
+            - End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners [paper](https://arxiv.org/abs/1803.10158)
       - https://github.com/E2E-AD/AD-MLP
-      - https://github.com/OpenDriveLab/ST-P3
-    - 大模型 LMDrive [关于大模型和自动驾驶的几个迷思](关于大模型和自动驾驶的几个迷思.md)
+      - ST-P3 [paper](https://arxiv.org/abs/2207.07601) | [code](https://github.com/OpenDriveLab/ST-P3)
+      - MP3 [paper](https://arxiv.org/abs/2101.06806) | [video](https://www.bilibili.com/video/BV1tQ4y1k7BX)
+      - TCP [NeurIPS 2022] Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline. [paper](https://arxiv.org/abs/2206.08129) | [video](https://www.bilibili.com/video/BV1Pe4y1x7E3/?spm_id_from=333.337.search-card.all.click&vd_source=57394ba751fad8e6886be567cccfa5bb) ｜[code](https://github.com/OpenDriveLab/TCP)
+      - 鉴智机器人 GraphAD 
+      - 
+    - 大模型 [LMDrive](https://github.com/opendilab/LMDrive) [关于大模型和自动驾驶的几个迷思](关于大模型和自动驾驶的几个迷思.md)
     - 世界模型：Drive-WM、DriveDreamer
     - 矢量地图在线建图：MapTRv2、ScalableMap、VectorMapNet、HDMapNet、GeMap、MapEX
     - BEV-OCC-Transformer: OccFormer、OccWorld、Occupancy Flow
@@ -30,14 +37,17 @@
     - 4D数据自动标注: 
       - OCC与Nerf联合标注
       - [面向BEV感知的4D标注方案](https://zhuanlan.zhihu.com/p/642735557?utm_psn=1706841959639998464)
-    - 数据生成：DrivingDiffusion、[MagicDrive](https://zhuanlan.zhihu.com/p/675303127)、UrbanSyn
+    - 数据合成：DrivingDiffusion、[MagicDrive](https://zhuanlan.zhihu.com/p/675303127)、UrbanSyn
+    - https://github.com/runnanchen/CLIP2Scene
 
 - <b>仿真</b>
-    - UniSim
+    - [UniSim](https://waabi.ai/unisim/)
   - DRIVE Sim
 
 - <b>其他</b>
     - 舱驾一体
     - AI 编译器: MLIR、TVM、XLA、Triton
     - 模型剪枝、模型蒸馏、模型压缩、模型量化（PTQ、QAT）
 
+
+关注科技前沿公司：[Waabi](https://waabi.ai/unisim/)、[Wayve](https://wayve.ai/)

Chapter08-FinalProject/OccNet/projects/configs/_base_/datasets/coco_instance.py

@@ -1,48 +1,54 @@
-dataset_type = 'CocoDataset'
-data_root = 'data/coco/'
+dataset_type = "CocoDataset"
+data_root = "data/coco/"
 img_norm_cfg = dict(
-    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True
+)
 train_pipeline = [
-    dict(type='LoadImageFromFile'),
-    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
-    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
-    dict(type='RandomFlip', flip_ratio=0.5),
-    dict(type='Normalize', **img_norm_cfg),
-    dict(type='Pad', size_divisor=32),
-    dict(type='DefaultFormatBundle'),
-    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
+    dict(type="LoadImageFromFile"),
+    dict(type="LoadAnnotations", with_bbox=True, with_mask=True),
+    dict(type="Resize", img_scale=(1333, 800), keep_ratio=True),
+    dict(type="RandomFlip", flip_ratio=0.5),
+    dict(type="Normalize", **img_norm_cfg),
+    dict(type="Pad", size_divisor=32),
+    dict(type="DefaultFormatBundle"),
+    dict(type="Collect", keys=["img", "gt_bboxes", "gt_labels", "gt_masks"]),
 ]
 test_pipeline = [
-    dict(type='LoadImageFromFile'),
+    dict(type="LoadImageFromFile"),
     dict(
-        type='MultiScaleFlipAug',
+        type="MultiScaleFlipAug",
         img_scale=(1333, 800),
         flip=False,
         transforms=[
-            dict(type='Resize', keep_ratio=True),
-            dict(type='RandomFlip'),
-            dict(type='Normalize', **img_norm_cfg),
-            dict(type='Pad', size_divisor=32),
-            dict(type='ImageToTensor', keys=['img']),
-            dict(type='Collect', keys=['img']),
-        ])
+            dict(type="Resize", keep_ratio=True),
+            dict(type="RandomFlip"),
+            dict(type="Normalize", **img_norm_cfg),
+            dict(type="Pad", size_divisor=32),
+            dict(type="ImageToTensor", keys=["img"]),
+            dict(type="Collect", keys=["img"]),
+        ],
+    ),
 ]
 data = dict(
     samples_per_gpu=2,
     workers_per_gpu=2,
     train=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/instances_train2017.json',
-        img_prefix=data_root + 'train2017/',
-        pipeline=train_pipeline),
+        ann_file=data_root + "annotations/instances_train2017.json",
+        img_prefix=data_root + "train2017/",
+        pipeline=train_pipeline,
+    ),
     val=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline),
+        ann_file=data_root + "annotations/instances_val2017.json",
+        img_prefix=data_root + "val2017/",
+        pipeline=test_pipeline,
+    ),
     test=dict(
         type=dataset_type,
-        ann_file=data_root + 'annotations/instances_val2017.json',
-        img_prefix=data_root + 'val2017/',
-        pipeline=test_pipeline))
-evaluation = dict(metric=['bbox', 'segm'])
+        ann_file=data_root + "annotations/instances_val2017.json",
+        img_prefix=data_root + "val2017/",
+        pipeline=test_pipeline,
+    ),
+)
+evaluation = dict(metric=["bbox", "segm"])