文件列表:

RealCar/ (0, 2023-11-22)
RealCar/lib/ (0, 2023-11-22)
RealCar/lib/config.py (1959, 2023-11-22)
RealCar/lib/datamodule.py (2049, 2023-11-22)
RealCar/lib/dataset.py (1267, 2023-11-22)
RealCar/lib/utils.py (8801, 2023-11-22)
RealCar/model/ (0, 2023-11-22)
RealCar/model/E2EResNet.py (1970, 2023-11-22)
RealCar/scripts/ (0, 2023-11-22)
RealCar/scripts/data_augmentation.py (3554, 2023-11-22)
RealCar/scripts/data_pre_process.py (2902, 2023-11-22)
RealCar/scripts/train.py (803, 2023-11-22)
demo/ (0, 2023-11-22)
demo/Simulator.png (2171852, 2023-11-22)
demo/demo_gif.gif (24175282, 2023-11-22)
lib/ (0, 2023-11-22)
lib/config.py (1971, 2023-11-22)
lib/datamodule.py (2037, 2023-11-22)
lib/dataset.py (1815, 2023-11-22)
lib/utils.py (8349, 2023-11-22)
model/ (0, 2023-11-22)
model/E2EResNet.py (1962, 2023-11-22)
model/E2EResNet_Pytorch.py (485, 2023-11-22)
requirements.txt (2224, 2023-11-22)
scripts/ (0, 2023-11-22)
scripts/data_pre_processing.py (3669, 2023-11-22)
scripts/delete_zero_steering_image.py (1220, 2023-11-22)
scripts/drive.py (2229, 2023-11-22)
scripts/file_name_process.py (1097, 2023-11-22)
scripts/train.py (754, 2023-11-22)
scripts/train_Pytorch.py (2927, 2023-11-22)

# Masterpraktikum - Simulation-Based Autonomous Driving in Crowded City (IN2106, IN4348) # End to End Learning for Self Driving Cars ## Introduction This program is part of the Masterpraktikum - Simulation-Based Autonomous Driving in Crowded City at the Technical University of Munich. In this work, I basically reproduce the work of [End to End Learning for Self-Driving Cars](https://arxiv.org/pdf/1604.07316.pdf). ## Result As you can see from the GIF below, the Resnet50-based self-driving model has been able to keep the car on the track for some distance, however the car eventually veers off the track.

## Installation 1. Environment requirements * Python 3.8 * Pytorch 1.11 * CUDA 11.3 The following installation guild suppose ``python=3.8`` ``pytorch=1.11`` and ``cuda=11.3``. You may change them according to your system. Create a conda virtual environment and activate it. ``` conda create -n SDC python=3.8 conda activate SDC ``` 2. Clone the repository. ``` git clone https://github.com/LuckyMax0722/SelfDrivingCars.git ``` 3. Install the dependencies. ``` conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch pip install pytorch-lightning==2.0.2 pip install -r requirements.txt ``` ## Simulator Preparation * Simulator can be found at: * [Windows 64 bit](https://d17h27t6h515a5.cloudfront.net/topher/2016/November/5831f3a4_simulator-windows-64/simulator-windows-64.zip) * [Linux](https://d17h27t6h515a5.cloudfront.net/topher/2016/November/5831f0f7_simulator-linux/simulator-linux.zip)

## Data Preparation * You can either collect data manually using the training mode in the simulator * Or you can download the existing training [data](https://d17h27t6h515a5.cloudfront.net/topher/2016/December/584f6edd_data/data.zip) After acquiring the training data, please move the data folder to the root directory. Your folder should look like this: ``` SelfDrivingCars ├──data │ ├── IMG │ ├── center... │ ├── ... │ ├── left... │ ├── ... │ ├── right... │ ├── ... │ ├── driving_log.csv │ ├──data_val │ ├── IMG │ ├── center... │ ├── ... │ ├── left... │ ├── ... │ ├── right... │ ├── ... │ ├── driving_log.csv ``` ### Useful scripts ## Training You can use the following code to train your own model based on the default configuration or you can download the pre-trained model [here](https://drive.google.com/file/d/1je9zkc7ruVa-F6uovzH5fq_cWajqncOs/view?usp=sharing). However, before you do that, you must set the project path in ``lib/config.py``. ```shell cd scripts python train.py ``` Of course, you can also change the relevant configuration for customized training. ## Testing Before you test the model, make sure the project path has been reset (see Section [Training](https://github.com/LuckyMax0722/End_to_End_Learning_for_Self_Driving_Cars#training)). ```shell cd scripts python drive.py ``` Finally open the simulator and select autonomous mode

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：