File size: 1,846 Bytes
1539e85 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 | {
"major_version": 0,
"minor_version": 1,
"model_name": "vad-carla-tiny",
"training_dataset": "Bench2Drive CARLA",
"release_date": "2025-11-04",
"description": "VAD model trained on Bench2Drive CARLA dataset with 6-camera surround view",
"image_normalization": {
"mean": [123.675, 116.28, 103.53],
"std": [58.395, 57.12, 57.375],
"format": "RGB",
"note": "ImageNet normalization statistics"
},
"input_specs": {
"target_image_width": 640,
"target_image_height": 384,
"num_cameras": 6,
"camera_order": ["FRONT", "BACK", "FRONT_LEFT", "BACK_LEFT", "FRONT_RIGHT", "BACK_RIGHT"]
},
"class_definitions": {
"map_classes": ["Broken", "Solid", "SolidSolid", "Center", "TrafficLight", "StopSign"],
"object_classes": ["car", "van", "truck", "bicycle", "traffic_sign", "traffic_cone", "traffic_light", "pedestrian", "others"]
},
"network_architecture": {
"bev": {
"height": 106,
"width": 200,
"feature_dim": 256,
"downsample_factor": 32
},
"transformer": {
"num_decoder_layers": 3
},
"prediction": {
"num_queries": 300,
"num_classes": 9,
"bbox_pred_dim": 10,
"trajectory_modes": 6,
"timesteps": 6,
"bbox_format": "[cx, cy, w, l, cz, h, sin, cos, vx, vy]"
},
"planning": {
"ego_commands": 6,
"timesteps": 6
},
"map": {
"num_queries": 100,
"num_classes": 6,
"points_per_polyline": 20
},
"vehicle_state": {
"can_bus_dim": 18
}
},
"model_files": {
"backbone": "vad-carla-tiny_backbone.onnx",
"head": "vad-carla-tiny_head.onnx",
"head_no_prev": "vad-carla-tiny_head_no_prev.onnx"
},
"compatibility": {
"autoware_tensorrt_vad_version": ">= 0.1.0",
"tensorrt_version": ">= 8.6",
"cuda_version": ">= 11.4"
}
}
|