|
- # Builtin Configurations(DO NOT CHANGE THESE CONFIGURATIONS unless you know exactly what you are doing)
- enable_modelarts: False
- # Url for modelarts
- data_url: ""
- train_url: ""
- checkpoint_url: ""
- # Path for local
- data_path: "/cache/data"
- output_path: "/cache/train"
- load_path: "/cache/checkpoint_path"
- device_target: "Ascend"
- enable_profiling: False
-
- # ==============================================================================
- # prepare *.mindrecord* data
- coco_data_dir: ""
- mindrecord_dir: "" # also used by train.py
- mindrecord_prefix: "coco_det.train.mind"
-
- # train related
- save_result_dir: ""
- device_id: 0
- device_num: 1
-
- filter_weight: 'false'
- distribute: 'false'
- need_profiler: "false"
- profiler_path: "./profiler"
- epoch_size: 1
- batch_size: ""
- num_classes: ""
- lr_schedule: ""
- learning_rate: ""
- multi_epochs: ""
- end_learning_rate: ""
- train_steps: -1
- enable_save_ckpt: "true"
- do_shuffle: "true"
- enable_data_sink: "true"
- data_sink_steps: -1
- save_checkpoint_path: "checkpoints"
- load_checkpoint_path: ""
- save_checkpoint_steps: 1221
- save_checkpoint_num: 1
-
- # val related
- data_dir: ""
- run_mode: "test"
- enable_eval: "true"
- visual_image: "false"
-
- # export related
- export_load_ckpt: ''
- export_format: ''
- export_name: ''
-
- # 310 infer
- val_data_dir: ''
- predict_dir: ''
- result_path: ''
- label_path: ''
- meta_path: ''
- save_path: ''
-
- dataset_config:
- num_classes: 80
- max_objs: 128
- input_res: [512, 512]
- output_res: [128, 128]
- rand_crop: True
- shift: 0.1
- scale: 0.4
- down_ratio: 4
- aug_rot: 0.0
- rotate: 0
- flip_prop: 0.5
- color_aug: True
- coco_classes: ['background', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
- 'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
- 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
- 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra',
- 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie',
- 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
- 'kite', 'baseball bat', 'baseball glove', 'skateboard',
- 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup',
- 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
- 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
- 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed',
- 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
- 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
- 'refrigerator', 'book', 'clock', 'vase', 'scissors',
- 'teddy bear', 'hair drier', 'toothbrush']
- mean: np.array([0.40789654, 0.44719302, 0.47026115], dtype=np.float32)
- std: np.array([0.28863828, 0.27408164, 0.27809835], dtype=np.float32)
- eig_val: np.array([0.2141788, 0.01817699, 0.00341571], dtype=np.float32)
- eig_vec: np.array([[-0.58752847, -0.69563484, 0.41340352],
- [-0.5832747, 0.00994535, -0.81221408],
- [-0.56089297, 0.71832671, 0.41158938]], dtype=np.float32)
-
- net_config:
- num_stacks: 2
- down_ratio: 4
- num_classes: 80
- n: 5
- cnv_dim: 256
- modules: [2, 2, 2, 2, 2, 4]
- dims: [256, 256, 384, 384, 384, 512]
- dense_wh: False
- norm_wh: False
- cat_spec_wh: False
- reg_offset: True
- hm_weight: 1
- off_weight: 1
- wh_weight: 0.1
- mse_loss: False
- reg_loss: 'l1'
-
- train_config:
- batch_size: 12
- loss_scale_value: 1024
- optimizer: 'Adam'
- lr_schedule: 'MultiDecay'
- Adam:
- weight_decay: 0.0
- decay_filter: "lambda x: x.name.endswith('.bias') or x.name.endswith('.beta') or x.name.endswith('.gamma')"
- PolyDecay:
- learning_rate: 0.00024 # 2.4e-4
- end_learning_rate: 0.0000005 # 5e-7
- power: 5.0
- eps: 0.0000001 # 1e-7
- warmup_steps: 2000
- MultiDecay:
- learning_rate: 0.00024 # 2.4e-4
- eps: 0.0000001 # 1e-7
- warmup_steps: 2000
- multi_epochs: [105, 125]
- factor: 10
-
- eval_config:
- SOFT_NMS: True
- keep_res: True
- multi_scales: [1.0]
- K: 100
- score_thresh: 0.3
- valid_ids: [
- 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13,
- 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 25, 27, 28, 31, 32, 33, 34, 35, 36,
- 37, 38, 39, 40, 41, 42, 43, 44, 46, 47,
- 48, 49, 50, 51, 52, 53, 54, 55, 56, 57,
- 58, 59, 60, 61, 62, 63, 64, 65, 67, 70,
- 72, 73, 74, 75, 76, 77, 78, 79, 80, 81,
- 82, 84, 85, 86, 87, 88, 89, 90]
- color_list: [0.000, 0.800, 1.000,
- 0.850, 0.325, 0.098,
- 0.929, 0.694, 0.125,
- 0.494, 0.184, 0.556,
- 0.466, 0.674, 0.188,
- 0.301, 0.745, 0.933,
- 0.635, 0.078, 0.184,
- 0.300, 0.300, 0.300,
- 0.600, 0.600, 0.600,
- 1.000, 0.000, 0.000,
- 1.000, 0.500, 0.000,
- 0.749, 0.749, 0.000,
- 0.000, 1.000, 0.000,
- 0.000, 0.000, 1.000,
- 0.667, 0.000, 1.000,
- 0.333, 0.333, 0.000,
- 0.333, 0.667, 0.333,
- 0.333, 1.000, 0.000,
- 0.667, 0.333, 0.000,
- 0.667, 0.667, 0.000,
- 0.667, 1.000, 0.000,
- 1.000, 0.333, 0.000,
- 1.000, 0.667, 0.000,
- 1.000, 1.000, 0.000,
- 0.000, 0.333, 0.500,
- 0.000, 0.667, 0.500,
- 0.000, 1.000, 0.500,
- 0.333, 0.000, 0.500,
- 0.333, 0.333, 0.500,
- 0.333, 0.667, 0.500,
- 0.333, 1.000, 0.500,
- 0.667, 0.000, 0.500,
- 0.667, 0.333, 0.500,
- 0.667, 0.667, 0.500,
- 0.667, 1.000, 0.500,
- 1.000, 0.000, 0.500,
- 1.000, 0.333, 0.500,
- 1.000, 0.667, 0.500,
- 1.000, 1.000, 0.500,
- 0.000, 0.333, 1.000,
- 0.000, 0.667, 1.000,
- 0.000, 1.000, 1.000,
- 0.333, 0.000, 1.000,
- 0.333, 0.333, 1.000,
- 0.333, 0.667, 1.000,
- 0.333, 1.000, 1.000,
- 0.667, 0.000, 1.000,
- 0.667, 0.333, 1.000,
- 0.667, 0.667, 1.000,
- 0.667, 1.000, 1.000,
- 1.000, 0.000, 1.000,
- 1.000, 0.333, 1.000,
- 1.000, 0.667, 1.000,
- 0.167, 0.800, 0.000,
- 0.333, 0.000, 0.000,
- 0.500, 0.000, 0.000,
- 0.667, 0.000, 0.000,
- 0.833, 0.000, 0.000,
- 1.000, 0.000, 0.000,
- 0.000, 0.667, 0.400,
- 0.000, 0.333, 0.000,
- 0.000, 0.500, 0.000,
- 0.000, 0.667, 0.000,
- 0.000, 0.833, 0.000,
- 0.000, 1.000, 0.000,
- 0.000, 0.000, 0.167,
- 0.000, 0.000, 0.333,
- 0.000, 0.000, 0.500,
- 0.000, 0.000, 0.667,
- 0.000, 0.000, 0.833,
- 0.000, 0.000, 1.000,
- 0.000, 0.200, 0.800,
- 0.143, 0.143, 0.543,
- 0.286, 0.286, 0.286,
- 0.429, 0.429, 0.429,
- 0.571, 0.571, 0.571,
- 0.714, 0.714, 0.714,
- 0.857, 0.857, 0.857,
- 0.000, 0.447, 0.741,
- 0.50, 0.5, 0]
-
- export_config:
- input_res: dataset_config.input_res
- ckpt_file: "./ckpt_file.ckpt"
- export_format: "AIR"
- export_name: "CenterNet_Hourglass"
-
- ---
- # Help description for each configuration
- enable_modelarts: "Whether training on modelarts, default: False"
- data_url: "Url for modelarts"
- train_url: "Url for modelarts"
- data_path: "The location of the input data."
- output_path: "The location of the output file."
- device_target: "Running platform, default is Ascend."
- enable_profiling: 'Whether enable profiling while training, default: False'
-
- distribute: "Run distribute, default is false."
- need_profiler: "Profiling to parsing runtime info, default is false."
- profiler_path: "The path to save profiling data"
- epoch_size: "Epoch size, default is 1."
- train_steps: "Training Steps, default is -1, i.e. run all steps according to epoch number."
- device_id: "Device id, default is 0."
- device_num: "Use device nums, default is 1."
- enable_save_ckpt: "Enable save checkpoint, default is true."
- do_shuffle: "Enable shuffle for dataset, default is true."
- enable_data_sink: "Enable data sink, default is true."
- data_sink_steps: "Sink steps for each epoch, default is 1."
- save_checkpoint_path: "Save checkpoint path"
- load_checkpoint_path: "Load checkpoint file path"
- save_checkpoint_steps: "Save checkpoint steps, default is 1000."
- save_checkpoint_num: "Save checkpoint numbers, default is 1."
- mindrecord_dir: "Mindrecord dataset files directory"
- mindrecord_prefix: "Prefix of MindRecord dataset filename."
- visual_image: "Visulize the ground truth and predicted image"
- save_result_dir: "The path to save the predict results"
-
- data_dir: "Dataset directory, the absolute image path is joined by the data_dir, and the relative path in anno_path"
- run_mode: "test or validation, default is test."
- enable_eval: "Whether evaluate accuracy after prediction"
-
- ---
- device_target: ['Ascend']
- distribute: ["true", "false"]
- need_profiler: ["true", "false"]
- enable_save_ckpt: ["true", "false"]
- do_shuffle: ["true", "false"]
- enable_data_sink: ["true", "false"]
- export_format: ["MINDIR", "AIR"]
|