# Project export: BackSeat_Driver This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small. ## Project metadata - Hackathon: TreeHacks 2025 - Tagline: Our aim is to combine traffic related models to detect objects, position, and what is going on throughout a video paired with LLMS to make an inference/ answer a question provided by the Tesla team - Devpost: https://devpost.com/software/backseat_driver - GitHub: https://github.com/LuisArizmendi13/TreeHacks2025 - Video: https://www.youtube.com/embed/m8lP08DGeB0?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent - Team: 2 GitHub contributor(s) — LuisArizmendi13 (14 commits), silva31 (1 commits) ## Devpost submission (written by the team) ### Inspiration Our inspiration came from a series of different methods to detect traffic signs, cars, and scenerios on the rode. Our main usages are BLIP, CLIP, a RoboFlow model using LISA data, and YOLO8n model for car detection models to detect scenarios, cars, and traffic signs. We also have seen the power of LLM like chatGPT, so we used this model to do so. The project name was inspired by the fact that the model would be responding to traffic related scenarios, acting like an arrogant backseat driver, (by giving advice). Hopefully it proves helpful! ### What it does Our project uses pre-trained models to extract from videos different traffic related data, building a scenario into text in which then we feed to a chatGPT api in order to determine a related question. Videos and multiple choice questions are given to us by Tesla. ### How we built it We build our project on NVIDIA VMs, for that extra compute power on the cloud and in order to run some of our models like YOLO and BLIP. We used BLIP, CLIP, a LISA based model, and YOLO8n image model in order to extract what exists and what is going on in a driving scenario. Each model extracts different things, like a description of what is going on, specific traffic signs, object detection, or object movement. We harness each model's strength, by taking a video and frame by frame (8 frames per 5 sec video approximately), and running these models on each one. Afterwards we aggregate this data per video and feed it into chatGPT's API. Additionally we give it a multiple choice question and with that data, and prompting it will make an answer. Afterwards the answer is taken an converted into a csv file, which we use to submit. ### Challenges we ran into So many dependency issues, too many installations and conflicts! Training models is time consuming! We opted to use pre-trained ones to save time, but training them ourselves would have allowed for on device models paired with NVIDIA VMs, thus faster compute. ### Accomplishments we're proud of We were able to build a VLM while making use of several models! We also learned to use new tools like chatGPT and RoboFlow APIs and NVIDIA VMs! ### What we learned We learned to use new tools like chatGPT and RoboFlow APIs and NVIDIA VMs! ### What's next We hope to put many of the models we call via API onto actual device plus tune them with more data. ## README (from the GitHub repository) # Team: Luis Arizmendi and Miggy Silva # Sources: RoboFlow with LISA data set for detecting signs: https://universe.roboflow.com/kaggle-road-sign-dataset/lisa-bjgh5/model/2 Tesla Challenge dataset: https://www.kaggle.com/competitions/tesla-real-world-video-q-a/leaderboard #Inspiration: LISA: https://www.kaggle.com/datasets/mbornoe/lisa-traffic-light-dataset/data ## Detected evidence (automated analysis) Indexed codebase: 11 recognized source files, 10 KB. - Python (language) — detected in the code ## Codebase structure (from repository index) ### Files (120 of 2103) ``` .gitignore .ipynb_checkpoints/Hello-checkpoint.ipynb data/questions.csv data/questions.csv:Zone.Identifier data/submission_sample.csv data/submission_sample.csv:Zone.Identifier data/submission1 copy.csv data/submission2.csv data/submission3.csv data/traffic/LISA/LISA2/data.yaml data/traffic/LISA/LISA2/README.dataset.txt data/traffic/LISA/LISA2/README.roboflow.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image0_png.rf.a125bf76da0928c48fcf21b101742325.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image0_png.rf.e3818f188a8064833f7c284fabb898e1.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image2_png.rf.1a4af40c3ab9aa98f38559bfe9fff581.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image2_png.rf.749b263fa63b0145af6a7ab26d8f6da7.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image3_png.rf.4956a478feef3e9d5d8baed5206506f7.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image3_png.rf.56128d827f2bece9bcac152bf0ff0650.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image4_png.rf.aa892297472473fad5d7afa15b2ad622.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323813414-avi_image4_png.rf.acfeebe761166d2edeb2e0846b24442c.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image10_png.rf.275dd4f9c28dac22165da7a532be7244.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image10_png.rf.f016025744219ea6c8773512a58898ee.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image11_png.rf.27de9d333feaeea6ba953acb093e31e2.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image11_png.rf.bf82feae67a32049a79e8efc9dba7acf.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image12_png.rf.812c8cabd7e4bf4404ad11aa4e8bf9db.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image12_png.rf.cc4a2f643d018baf2856032f28c03f3d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image2_png.rf.5044898c12563ba2da8d15b87e4f2e77.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image2_png.rf.fd2d68cfacbfb10b9485e29a4083d7bf.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image3_png.rf.4d492b140aeb240ce11ac1d5774dcdaa.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image3_png.rf.83643d5157686a7463d11e526f4d8d45.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image4_png.rf.69f38557f869a25b3e1c81255223a83b.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image4_png.rf.ccf312d5c6c946b87512e89486362827.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image5_png.rf.557803ba98344f9f4fb63e3a2204ee4d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image5_png.rf.57af8a2389cb12061763cd72c8d747af.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image6_png.rf.07065132c0a6de989b5bd5abdf341b00.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image6_png.rf.87433f4963cf8950eb7b5953b973f971.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image7_png.rf.b5312e8f7314149bbeb5ca4cd5437f65.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816833-avi_image7_png.rf.e736c50f16f9e68b27d01fb41a328628.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image0_png.rf.8cab1f2376025e69383561eb207df1f5.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image0_png.rf.fa5125dc4d719ca77441e92eb87ed62e.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image1_png.rf.661df24c87091a58341781bfca49a8eb.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image1_png.rf.dfca3f7b2aa612378a3a3fb1dde73488.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image5_png.rf.1c0340dfa31fda0b6ee330264e5fb431.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323816988-avi_image5_png.rf.47c643b5a08e4e0171ab0ec59c938add.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image1_png.rf.5426204e668fbf5ea0cddaf1902377c2.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image1_png.rf.836263042265dc16c0b4c639d9f25056.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image10_png.rf.0d24a2ab48df27051ec18f3a056f6471.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image10_png.rf.cce4a5e9f28cb2e5580ac6825e1de29e.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image11_png.rf.4fb05e15e451445abd284705caa25cbc.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image11_png.rf.8252458e17b992f42262adfb19df28e1.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image12_png.rf.7c67df048164f84995af6f48639dc8cd.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image12_png.rf.e6e596496cacd4b816e81c3f5d1543d7.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image13_png.rf.c07e47cb675298901b7c860103ef71ba.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image13_png.rf.c9938b21ee0e14bd4d08b10b63f644e8.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image14_png.rf.4b4aa4e16c55181903b956bec7634e33.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image14_png.rf.53a463dbae9cd45814e0abf1e45d1027.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image15_png.rf.4f7f4dcc8857e91d19e0e837f18d55c1.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image15_png.rf.6d3b16f2f26caf1068e61dd2ab2eabd6.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image2_png.rf.3ba6caa7d6142c07d2af054238318632.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image2_png.rf.7703d5ad3c437840a405d78ab317bd37.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image4_png.rf.80bc17da7e5b927ff42a55cc97b8684a.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image4_png.rf.a73c8e75c69c7a0283382a9aac2843db.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image6_png.rf.22807a28ed8b765414fe1a475c87fe2d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image6_png.rf.c42df4a3387a9e6951583682b6176cb8.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image7_png.rf.60af98c5fd2fc6595c7b7ecfaaa8852d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image7_png.rf.f40d6da52bf9f6947fc19ff4b4c212ed.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image8_png.rf.8d568d2f9cc65ebe219d69d7c61ccd02.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image8_png.rf.c9a8822937333c77407f3b6d4670cd7b.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image9_png.rf.cef6d40d88ffc5695ab415f6ac442478.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323817202-avi_image9_png.rf.f96ef4af216447b600b569f678d5b0db.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image0_png.rf.319479ce13a5bf80eaa5f2d8395cac26.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image0_png.rf.cb58200b3dda59970b8de8528cd95f17.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image1_png.rf.74ff6af3c3b93f01085124bf5e9240cb.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image1_png.rf.7fdc1b04a83d34e08ebe3ada325c3381.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image2_png.rf.7a3364c3f018cc1e695a65594a509a6c.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image2_png.rf.dd4bd02c85d5c7a1fa05c8317911c4a0.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image3_png.rf.807f2c631a0cea135a7aca31987871f3.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image3_png.rf.e9520f2dd98ede1c243421c892d4a103.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image4_png.rf.c2c7d59a73f2fcf1b7b02bbf8d281be5.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image4_png.rf.c8b215410541c13fe7648f4ac2aeddf7.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image5_png.rf.67339476d8c1c83384030f203e3d9b39.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image5_png.rf.e26ae3abbb0f5f41ef04d8e730442e4d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image6_png.rf.0fdf8a1ef9bbc5fcbe0fbed38b0db198.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image6_png.rf.3e56508946a500f98eeaab0be12993e3.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image7_png.rf.4c19fbdec7cc2c727d6ef7ccda96f9dd.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820177-avi_image7_png.rf.4e2b52c75df4dab9e72b22e8ebc2e696.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image0_png.rf.1036d95b03665ba2b76c12d3ddc9c167.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image0_png.rf.d0cee5c07f9a34ace95b8e6591eb3d9b.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image10_png.rf.2d6061440d542870780b089fc8ede6b5.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image10_png.rf.6dc21cf62391c105048b7c04edab589f.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image12_png.rf.13c4a71cdc49fe4ccffdc37dff2e1668.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image12_png.rf.c7ec802cc40c8745d949f491453e2b4d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image9_png.rf.0b41926771706d53454974a8ce5a24b5.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820215-avi_image9_png.rf.c59739fee29ba9ee25104353559c13f9.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image0_png.rf.ba65b374a7ee2c4ec7c6cb92b560a4c4.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image0_png.rf.d64083aa66d02ec5409c79bf3da4c908.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image2_png.rf.2bc3d740207cea033311e412c71bccb3.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image2_png.rf.7fd8bbdcea2e9a662522f672ee1a6ccc.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image3_png.rf.3ccdc523d71c54c9acae054de8555cf2.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image3_png.rf.c4064d94a2e1cf32e0a7aee949e33656.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image4_png.rf.10c6625a596c9398a4d7650c5b687e4d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image4_png.rf.2ae7da753e28e0049fb65727359ee268.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image5_png.rf.3de3cf576ca8ee8cb4d11ca95e7251f0.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image5_png.rf.53d1f5763f147ac5d78f2db3b2a4c14f.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image6_png.rf.25ac1b7ece0d2c335ea64e8af3dbf9c9.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323820280-avi_image6_png.rf.276ab6e5089f2124bd6cad8ff438cb0d.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image0_png.rf.20558b3e0888dd645cc32d8a23df73b7.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image0_png.rf.de13a3161218228cd5a4d6cf05083e19.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image1_png.rf.c48a9ab8d9860c11367491c79e6a5346.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image1_png.rf.ee98d5bb26fe2b15e581ee156d46d65e.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image11_png.rf.3bbdfdb7cd4ec413a2d5af477655be42.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image11_png.rf.3f60580183afb4b96ff9ec30b861233a.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image12_png.rf.0b130ffc9d2ba81fb326f9dbe27340c0.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image12_png.rf.67be94128f84cf6044839342d37dbf90.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image13_png.rf.19a16f3b6a6d2396d8cde6fb18c302c1.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image13_png.rf.7e63cae92d39e3cc0f07cbef0e82aa06.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image14_png.rf.1ae1b76b1905451689abc7870e79aacc.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image14_png.rf.9de6a9630f321418ad47c1e36dc7161a.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image3_png.rf.444a55a95c8280d95eb707fdd323b7e0.txt data/traffic/LISA/LISA2/train/labels/addedLane_1323821747-avi_image3_png.rf.d52fe388742de4b0a0100fd4e750c5fc.txt [1983 more files omitted for size] ``` ### Dependencies No dependency index available. ### Recent commits (newest first) - Update my_vars.py - done2 - done - Merge branch 'master' of https://github.com/LuisArizmendi13/TreeHacks2025 - final - Update README.md - Create README.md - Ignore large Miniconda files - Ignore large files - Merge branch 'master' of https://github.com/LuisArizmendi13/TreeHacks2025 - please - more env stuff - Starting code - envirnoment - hello ## Key source files (fetched from GitHub, selected and truncated for size) ### my_vars.py ```python ROBO = ``` ### setup/environment.yml ```yaml name: treehack channels: - conda-forge - defaults dependencies: - python=3.10 - numpy<2.0.0 # Fix numpy version for ultralytics - opencv - pytorch - torchvision - jupyterlab - pip - pip: - ultralytics - ultralytics-thop>=2.0.0 # Required dependency - torch - transformers - deep-sort-realtime ``` ### runs/detect/train/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: ./traffic/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 8 project: null name: train exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train ``` ### runs/detect/train3/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: data/LISA/LISA2/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 4 project: null name: train3 exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train3 ``` ### runs/detect/train4/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: data/traffic/LISA/LISA2/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 4 project: null name: train4 exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train4 ``` ### runs/detect/train5/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: data/traffic/LISA/LISA2/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 4 project: null name: train5 exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train5 ``` ### runs/detect/train6/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: data/traffic/LISA/LISA2/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 4 project: null name: train6 exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train6 ``` ### runs/detect/train2/args.yaml ```yaml task: detect mode: train model: yolov8n.pt data: /path/to/lisa_yolo_dataset/data.yaml epochs: 50 time: null patience: 100 batch: 16 imgsz: 640 save: true save_period: -1 cache: false device: cuda workers: 4 project: null name: train2 exist_ok: false pretrained: true optimizer: auto verbose: true seed: 0 deterministic: true single_cls: false rect: false cos_lr: false close_mosaic: 10 resume: false amp: true fraction: 1.0 profile: false freeze: null multi_scale: false overlap_mask: true mask_ratio: 4 dropout: 0.0 val: true split: val save_json: false save_hybrid: false conf: null iou: 0.7 max_det: 300 half: false dnn: false plots: true source: null vid_stride: 1 stream_buffer: false visualize: false augment: false agnostic_nms: false classes: null retina_masks: false embed: null show: false save_frames: false save_txt: false save_conf: false save_crop: false show_labels: true show_conf: true show_boxes: true line_width: null format: torchscript keras: false optimize: false int8: false dynamic: false simplify: true opset: null workspace: null nms: false lr0: 0.01 lrf: 0.01 momentum: 0.937 weight_decay: 0.0005 warmup_epochs: 3.0 warmup_momentum: 0.8 warmup_bias_lr: 0.1 box: 7.5 cls: 0.5 dfl: 1.5 pose: 12.0 kobj: 1.0 nbs: 64 hsv_h: 0.015 hsv_s: 0.7 hsv_v: 0.4 degrees: 0.0 translate: 0.1 scale: 0.5 shear: 0.0 perspective: 0.0 flipud: 0.0 fliplr: 0.5 bgr: 0.0 mosaic: 1.0 mixup: 0.0 copy_paste: 0.0 copy_paste_mode: flip auto_augment: randaugment erasing: 0.4 crop_fraction: 1.0 cfg: null tracker: botsort.yaml save_dir: runs/detect/train2 ``` ### data/traffic/LISA/LISA2/data.yaml ```yaml train: ../train/images val: ../valid/images test: ../test/images nc: 4 names: ['pedestrianCrossing', 'signalAhead', 'stop', 'yield'] roboflow: workspace: dakota-smith project: lisa-road-signs version: 2 license: CC BY 4.0 url: https://universe.roboflow.com/dakota-smith/lisa-road-signs/dataset/2 ```