| { |
| "audit_type": "BEVFORMER_DELIVERY_DEMO_SAMPLE4_MANIFEST", |
| "status": "PASS", |
| "mode": "self_contained_sample4_raw_camera_to_detection", |
| "total_frames": 4, |
| "scene_start_indices": [ |
| 0 |
| ], |
| "frame_range": [ |
| 0, |
| 3 |
| ], |
| "note": "Self-contained 4-frame continuous board demo sample. Image input starts from bundled raw camera JPEGs; Python preprocessing runs on board.", |
| "frames": { |
| "sample_000": { |
| "dataset_index": 0, |
| "sample_token": "3e8750f331d7499e9b5123e9eb70f2e2", |
| "scene_token": "fcbccedd61424f1b85dcbf8f897f9754", |
| "prev_token": "", |
| "next_token": "3950bd41f74548429c0f7700ff3d8269", |
| "is_scene_start": true, |
| "assets": { |
| "can_bus": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 36, |
| "path": "code/python/datasets/sample4/frames/sample_000/can_bus.raw", |
| "sha256": "974730a9cf60a4a0cae487ed4b296faf6621abec0bcd7276020ade042fd8dc3b" |
| }, |
| "lidar2img": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 6, |
| 4, |
| 4 |
| ], |
| "bytes": 192, |
| "path": "code/python/datasets/sample4/frames/sample_000/lidar2img.raw", |
| "sha256": "f1df04f672d707f2fbc8ea9799ee84d8795a1fe22f17ed89c08327e63f663501" |
| }, |
| "camera_images": { |
| "type": "raw_camera_jpeg_multiview", |
| "order": [ |
| "CAM_FRONT", |
| "CAM_FRONT_RIGHT", |
| "CAM_FRONT_LEFT", |
| "CAM_BACK", |
| "CAM_BACK_LEFT", |
| "CAM_BACK_RIGHT" |
| ], |
| "decode": "cv2.imread BGR", |
| "pipeline": "BGR -> RGB -> normalize(mean/std) -> resize(800,450) -> CHW -> pad to 480 rows", |
| "mean": [ |
| 123.675, |
| 116.28, |
| 103.53 |
| ], |
| "std": [ |
| 58.395, |
| 57.12, |
| 57.375 |
| ], |
| "to_rgb": true, |
| "resize": [ |
| 800, |
| 450 |
| ], |
| "output_shape_unpadded": [ |
| 6, |
| 3, |
| 450, |
| 800 |
| ], |
| "output_shape_padded": [ |
| 6, |
| 3, |
| 480, |
| 800 |
| ], |
| "reference_preprocessed_sha256": "87de4dfddc0cb554908b8c9a89d76125e8698bfbf5ece9d366de924a938d4b1d", |
| "images": [ |
| { |
| "name": "CAM_FRONT", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_FRONT.jpg", |
| "sha256": "0e2067a1618c4424050c45c393ada8c9dbf130fff8d6015004fce901dc07984d", |
| "bytes": 141976 |
| }, |
| { |
| "name": "CAM_FRONT_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_FRONT_RIGHT.jpg", |
| "sha256": "15cf59c79b086d14da6fae5a7ee5b0f4d0fac0c0a22c0a85faaa5fb215521191", |
| "bytes": 147910 |
| }, |
| { |
| "name": "CAM_FRONT_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_FRONT_LEFT.jpg", |
| "sha256": "8c52f73a3ef06a129c27ef51ac65704428caebfaa60c52f14a5953bbb0124a18", |
| "bytes": 144177 |
| }, |
| { |
| "name": "CAM_BACK", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_BACK.jpg", |
| "sha256": "047dd43f3f9fb7cc426b1d4ae369181242c5555b84baff5d7e1cbd0dc8b07259", |
| "bytes": 108796 |
| }, |
| { |
| "name": "CAM_BACK_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_BACK_LEFT.jpg", |
| "sha256": "27b2826991733662e4f17c509ad5a66e85e0ca66a6413063d8db9645fa608c11", |
| "bytes": 110941 |
| }, |
| { |
| "name": "CAM_BACK_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_000/cameras/CAM_BACK_RIGHT.jpg", |
| "sha256": "a998caf0e327816b82d2a142d2581a8c1f9c4e67d50b4af3718a381337b7e415", |
| "bytes": 124547 |
| } |
| ] |
| } |
| } |
| }, |
| "sample_001": { |
| "dataset_index": 1, |
| "sample_token": "3950bd41f74548429c0f7700ff3d8269", |
| "scene_token": "fcbccedd61424f1b85dcbf8f897f9754", |
| "prev_token": "3e8750f331d7499e9b5123e9eb70f2e2", |
| "next_token": "c5f58c19249d4137ae063b0e9ecd8b8e", |
| "is_scene_start": false, |
| "assets": { |
| "can_bus": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 36, |
| "path": "code/python/datasets/sample4/frames/sample_001/can_bus.raw", |
| "sha256": "8ece2acd67155365b9394e1569b8242d69f3d9805cea19a5153cb51e79e55152" |
| }, |
| "shift": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 2 |
| ], |
| "bytes": 4, |
| "path": "code/python/datasets/sample4/frames/sample_001/shift.raw", |
| "sha256": "530492c17f13ce48ec402622565d7a4ba0987a57b988a3c4d824cc4987dfd5fc" |
| }, |
| "lidar2img": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 6, |
| 4, |
| 4 |
| ], |
| "bytes": 192, |
| "path": "code/python/datasets/sample4/frames/sample_001/lidar2img.raw", |
| "sha256": "63d7bcbf3a9c63e1184947d9e5112fe30bf4e8533ea29df44daeef3cb610a2ed" |
| }, |
| "rotation_can_bus": { |
| "dtype": "float32", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 72, |
| "path": "code/python/datasets/sample4/frames/sample_001/rotation_can_bus.raw", |
| "sha256": "741d75aad896829e7246d446635bc21331242c7e28ef869f986d70e048d40962" |
| }, |
| "camera_images": { |
| "type": "raw_camera_jpeg_multiview", |
| "order": [ |
| "CAM_FRONT", |
| "CAM_FRONT_RIGHT", |
| "CAM_FRONT_LEFT", |
| "CAM_BACK", |
| "CAM_BACK_LEFT", |
| "CAM_BACK_RIGHT" |
| ], |
| "decode": "cv2.imread BGR", |
| "pipeline": "BGR -> RGB -> normalize(mean/std) -> resize(800,450) -> CHW -> pad to 480 rows", |
| "mean": [ |
| 123.675, |
| 116.28, |
| 103.53 |
| ], |
| "std": [ |
| 58.395, |
| 57.12, |
| 57.375 |
| ], |
| "to_rgb": true, |
| "resize": [ |
| 800, |
| 450 |
| ], |
| "output_shape_unpadded": [ |
| 6, |
| 3, |
| 450, |
| 800 |
| ], |
| "output_shape_padded": [ |
| 6, |
| 3, |
| 480, |
| 800 |
| ], |
| "reference_preprocessed_sha256": "ecc0a38ce961abecd5063c3b5c8cb543a63cb423c032ca06fbdc8efc73b66f4a", |
| "images": [ |
| { |
| "name": "CAM_FRONT", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_FRONT.jpg", |
| "sha256": "d5624fcecf12310c3d0760362e097c38cdcdce987e032aaf2883071cd14e2732", |
| "bytes": 146297 |
| }, |
| { |
| "name": "CAM_FRONT_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_FRONT_RIGHT.jpg", |
| "sha256": "dd64d7463bc06bfd5d5378bdd494b40d68d0894307f3ed971eaaaf131022cf68", |
| "bytes": 143628 |
| }, |
| { |
| "name": "CAM_FRONT_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_FRONT_LEFT.jpg", |
| "sha256": "0fe15c0581db41e084df27acb2183b0ab9b0fd36da136ef1b4bcbda6f1a84c58", |
| "bytes": 146244 |
| }, |
| { |
| "name": "CAM_BACK", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_BACK.jpg", |
| "sha256": "fdbdaa77e60ed5a6a762a4ea9a8eb1cb2ca9a3d94c610a55a2399a05c04b6ba6", |
| "bytes": 109601 |
| }, |
| { |
| "name": "CAM_BACK_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_BACK_LEFT.jpg", |
| "sha256": "000f7943769e91ffa842a7dfd1bfc31e0c3f4b37325a98846e8261304028f2ad", |
| "bytes": 112425 |
| }, |
| { |
| "name": "CAM_BACK_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_001/cameras/CAM_BACK_RIGHT.jpg", |
| "sha256": "39d28a8a5a6f61370a7e7e1e965a6d8610b571195c50fd29da960e1fb2fbee80", |
| "bytes": 125712 |
| } |
| ] |
| } |
| } |
| }, |
| "sample_002": { |
| "dataset_index": 2, |
| "sample_token": "c5f58c19249d4137ae063b0e9ecd8b8e", |
| "scene_token": "fcbccedd61424f1b85dcbf8f897f9754", |
| "prev_token": "3950bd41f74548429c0f7700ff3d8269", |
| "next_token": "700c1a25559b4433be532de3475e58a9", |
| "is_scene_start": false, |
| "assets": { |
| "can_bus": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 36, |
| "path": "code/python/datasets/sample4/frames/sample_002/can_bus.raw", |
| "sha256": "e8badd418a0eb1905986c2a2a5e87fa6e16532dc4899cfff93f47dbe51bed9be" |
| }, |
| "shift": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 2 |
| ], |
| "bytes": 4, |
| "path": "code/python/datasets/sample4/frames/sample_002/shift.raw", |
| "sha256": "9cd32a1a7fbb67a9841ebee6acf497db1fa6142ec9e3ec5c9bb1596dd8be81e8" |
| }, |
| "lidar2img": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 6, |
| 4, |
| 4 |
| ], |
| "bytes": 192, |
| "path": "code/python/datasets/sample4/frames/sample_002/lidar2img.raw", |
| "sha256": "7d524fefbeec4c1014ab2773b722aaa13774cb4787fb950e27b1b4de7cc3d403" |
| }, |
| "rotation_can_bus": { |
| "dtype": "float32", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 72, |
| "path": "code/python/datasets/sample4/frames/sample_002/rotation_can_bus.raw", |
| "sha256": "a08e149204cd22c460e8b5cc62726de1b29d22fb05b6c33b450e1f94a162d3c1" |
| }, |
| "camera_images": { |
| "type": "raw_camera_jpeg_multiview", |
| "order": [ |
| "CAM_FRONT", |
| "CAM_FRONT_RIGHT", |
| "CAM_FRONT_LEFT", |
| "CAM_BACK", |
| "CAM_BACK_LEFT", |
| "CAM_BACK_RIGHT" |
| ], |
| "decode": "cv2.imread BGR", |
| "pipeline": "BGR -> RGB -> normalize(mean/std) -> resize(800,450) -> CHW -> pad to 480 rows", |
| "mean": [ |
| 123.675, |
| 116.28, |
| 103.53 |
| ], |
| "std": [ |
| 58.395, |
| 57.12, |
| 57.375 |
| ], |
| "to_rgb": true, |
| "resize": [ |
| 800, |
| 450 |
| ], |
| "output_shape_unpadded": [ |
| 6, |
| 3, |
| 450, |
| 800 |
| ], |
| "output_shape_padded": [ |
| 6, |
| 3, |
| 480, |
| 800 |
| ], |
| "reference_preprocessed_sha256": "97fc26501e167d58279ce6229847cd6753b13b2b1795effba7dcbf282f99fc2e", |
| "images": [ |
| { |
| "name": "CAM_FRONT", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_FRONT.jpg", |
| "sha256": "0bb82b89f9e6ce47d9e1bcd747b01fe3fd342ccc67eb7a9c693a3fc3fc73a6bc", |
| "bytes": 145856 |
| }, |
| { |
| "name": "CAM_FRONT_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_FRONT_RIGHT.jpg", |
| "sha256": "70856b9d713c279b4b3d5911be30944f339760cc81da5a8f2c4d90a20276c1d3", |
| "bytes": 132652 |
| }, |
| { |
| "name": "CAM_FRONT_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_FRONT_LEFT.jpg", |
| "sha256": "4782aaa9180ef1fe153e702031a3249ada09bdb056ad13ff69abaa2f9e59e35a", |
| "bytes": 145095 |
| }, |
| { |
| "name": "CAM_BACK", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_BACK.jpg", |
| "sha256": "a9a05b52aea16ccf730447170eb836697c26928a112a74249caf423d91d28306", |
| "bytes": 111521 |
| }, |
| { |
| "name": "CAM_BACK_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_BACK_LEFT.jpg", |
| "sha256": "a28438e9ff68ccab2ce3a8da4151591a2b15780aecdc21185a911318ed923f72", |
| "bytes": 112445 |
| }, |
| { |
| "name": "CAM_BACK_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_002/cameras/CAM_BACK_RIGHT.jpg", |
| "sha256": "1578ba72afd2cc91abb1295c3404a432e41ffc7385b4031a43b586acfb693872", |
| "bytes": 132515 |
| } |
| ] |
| } |
| } |
| }, |
| "sample_003": { |
| "dataset_index": 3, |
| "sample_token": "700c1a25559b4433be532de3475e58a9", |
| "scene_token": "fcbccedd61424f1b85dcbf8f897f9754", |
| "prev_token": "c5f58c19249d4137ae063b0e9ecd8b8e", |
| "next_token": "747aa46b9a4641fe90db05d97db2acea", |
| "is_scene_start": false, |
| "assets": { |
| "can_bus": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 36, |
| "path": "code/python/datasets/sample4/frames/sample_003/can_bus.raw", |
| "sha256": "dbc4945c65d5804131f75f04578e3fbc288330ff5fa977f224eda07eb96e463a" |
| }, |
| "shift": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 2 |
| ], |
| "bytes": 4, |
| "path": "code/python/datasets/sample4/frames/sample_003/shift.raw", |
| "sha256": "8cc4c98a9615a420d40104ae51d4f1f50b719a9cfec4be8d1b65b4b704517def" |
| }, |
| "lidar2img": { |
| "dtype": "float16", |
| "shape": [ |
| 1, |
| 6, |
| 4, |
| 4 |
| ], |
| "bytes": 192, |
| "path": "code/python/datasets/sample4/frames/sample_003/lidar2img.raw", |
| "sha256": "64cd7874438918c64f54414d1b873b0b0fcf05b2b601f2014c4fe5a8316e7a2c" |
| }, |
| "rotation_can_bus": { |
| "dtype": "float32", |
| "shape": [ |
| 1, |
| 18 |
| ], |
| "bytes": 72, |
| "path": "code/python/datasets/sample4/frames/sample_003/rotation_can_bus.raw", |
| "sha256": "3c88129317e663a14f4ba55a3c0c3cc25e9ec2cd4c497276567e4ecfed8a9ab6" |
| }, |
| "camera_images": { |
| "type": "raw_camera_jpeg_multiview", |
| "order": [ |
| "CAM_FRONT", |
| "CAM_FRONT_RIGHT", |
| "CAM_FRONT_LEFT", |
| "CAM_BACK", |
| "CAM_BACK_LEFT", |
| "CAM_BACK_RIGHT" |
| ], |
| "decode": "cv2.imread BGR", |
| "pipeline": "BGR -> RGB -> normalize(mean/std) -> resize(800,450) -> CHW -> pad to 480 rows", |
| "mean": [ |
| 123.675, |
| 116.28, |
| 103.53 |
| ], |
| "std": [ |
| 58.395, |
| 57.12, |
| 57.375 |
| ], |
| "to_rgb": true, |
| "resize": [ |
| 800, |
| 450 |
| ], |
| "output_shape_unpadded": [ |
| 6, |
| 3, |
| 450, |
| 800 |
| ], |
| "output_shape_padded": [ |
| 6, |
| 3, |
| 480, |
| 800 |
| ], |
| "reference_preprocessed_sha256": "da157bc039b66254cb57f827adcdfde783d324a078a15af9740a3701697eba15", |
| "images": [ |
| { |
| "name": "CAM_FRONT", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_FRONT.jpg", |
| "sha256": "54384bc8c4896f349bdc643b573f398fbb03ee842ac2af2af2c602a62f48f79d", |
| "bytes": 147138 |
| }, |
| { |
| "name": "CAM_FRONT_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_FRONT_RIGHT.jpg", |
| "sha256": "4c5209d28a7e3a5f29bd7c02c29bd0f53c669afc43b17af2db098371a9711dc1", |
| "bytes": 145853 |
| }, |
| { |
| "name": "CAM_FRONT_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_FRONT_LEFT.jpg", |
| "sha256": "1f20956c425bdc84da1bf2610b7214d48930652782394aa0f1f3bef94ce0be35", |
| "bytes": 146337 |
| }, |
| { |
| "name": "CAM_BACK", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_BACK.jpg", |
| "sha256": "34e84e10e04ab229864bd0ddd3067442c0b58e249eeb48088ab417cb259b4985", |
| "bytes": 112516 |
| }, |
| { |
| "name": "CAM_BACK_LEFT", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_BACK_LEFT.jpg", |
| "sha256": "cdf1f064c61add58e17d7011713aebbe40be9d7e8290c8816f585fca3841e033", |
| "bytes": 113884 |
| }, |
| { |
| "name": "CAM_BACK_RIGHT", |
| "path": "code/python/datasets/sample4/frames/sample_003/cameras/CAM_BACK_RIGHT.jpg", |
| "sha256": "eae354ba8407662caa6c50934b6ee306a4e5aaaeec0b0f2e40c2f6b481485d3f", |
| "bytes": 135629 |
| } |
| ] |
| } |
| } |
| } |
| }, |
| "contract": { |
| "image_pipeline": "cv2.imread BGR -> RGB -> normalize(mean=[123.675,116.28,103.53], std=[58.395,57.12,57.375]) -> cv2.resize(800,450) -> CHW -> zero-pad to (6,3,480,800)", |
| "camera_order": [ |
| "CAM_FRONT", |
| "CAM_FRONT_RIGHT", |
| "CAM_FRONT_LEFT", |
| "CAM_BACK", |
| "CAM_BACK_LEFT", |
| "CAM_BACK_RIGHT" |
| ], |
| "model_path": "W8A8 backbone + scene-start/temporal encoder + decoder AidLite QNN contexts", |
| "temporal_state": "scene-start uses reset semantics; temporal frames use previous live bev_embed as prev_bev", |
| "scene_start_inputs": "camera_images + can_bus + lidar2img; no prev_bev/shift input is required for scene-start encoder", |
| "temporal_inputs": "camera_images + can_bus + lidar2img + shift + rotated previous live bev_embed" |
| } |
| } |
|
|
