from mmdeploy.apis import inference_model

result = inference_model(
  model_cfg='${PATH_TO_MMDET}/configs/rtmdet/rtmdet_s_8xb32-300e_coco.py',
  deploy_cfg='${PATH_TO_MMDEPLOY}/configs/mmdet/detection/detection_tensorrt_static-640x640.py',
  backend_files=['work_dirs/rtmdet/end2end.engine'],
  img='demo/resources/det.jpg',
  device='cuda:0')

# in MMDeploy config
backend_config = dict(
    type='tensorrt',
    common_config=dict(
        fp16_mode=True  # enable fp16
    ))

# in MMDetection config
model = dict(
    test_cfg=dict(
        nms_pre=1000,  # keep top-k score bboxes before nms
        min_bbox_size=0,
        score_thr=0.3,  # score threshold to filter bboxes
        nms=dict(type='nms', iou_threshold=0.65),
        max_per_img=100)  # only keep top-100 as the final results.
)

from mmdeploy_python import Detector
import cv2

img = cv2.imread('demo/resources/det.jpg')

# create a detector
detector = Detector(model_path='work_dirs/rtmdet-sdk', device_name='cuda', device_id=0)
# run the inference
bboxes, labels, _ = detector(img)
# Filter the result according to threshold
indices = [i for i in range(len(bboxes))]
for index, bbox, label_id in zip(indices, bboxes, labels):
  [left, top, right, bottom], score = bbox[0:4].astype(int),  bbox[4]
  if score < 0.3:
      continue
  # draw bbox
  cv2.rectangle(img, (left, top), (right, bottom), (0, 255, 0))

cv2.imwrite('output_detection.png', img)

from mmdeploy.apis import inference_model

result = inference_model(
  model_cfg='${PATH_TO_MMDET}/configs/rtmdet/rtmdet-ins_s_8xb32-300e_coco.py',
  deploy_cfg='${PATH_TO_MMDEPLOY}/configs/mmdet/instance-seg/instance-seg_rtmdet-ins_tensorrt_static-640x640.py',
  backend_files=['work_dirs/rtmdet-ins/end2end.engine'],
  img='demo/resources/det.jpg',
  device='cuda:0')

model = dict(
    type='RTMDet',  # The name of detector
    data_preprocessor=dict(  # The config of data preprocessor, usually includes image normalization and padding
        type='DetDataPreprocessor',  # The type of the data preprocessor. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.data_preprocessors.DetDataPreprocessor
        mean=[103.53, 116.28, 123.675],  # Mean values used to pre-training the pre-trained backbone models, ordered in R, G, B
        std=[57.375, 57.12, 58.395],  # Standard variance used to pre-training the pre-trained backbone models, ordered in R, G, B
        bgr_to_rgb=False,  # whether to convert image from BGR to RGB
        batch_augments=None),  # Batch-level augmentations
    backbone=dict(  # The config of backbone
        type='CSPNeXt',  # The type of backbone network. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.backbones.CSPNeXt
        arch='P5',  # Architecture of CSPNeXt, from {P5, P6}. Defaults to P5
        expand_ratio=0.5,  # Ratio to adjust the number of channels of the hidden layer. Defaults to 0.5
        deepen_factor=1,  # Depth multiplier, multiply number of blocks in CSP layer by this amount. Defaults to 1.0
        widen_factor=1,  # Width multiplier, multiply number of channels in each layer by this amount. Defaults to 1.0
        channel_attention=True,  # Whether to add channel attention in each stage. Defaults to True
        norm_cfg=dict(type='SyncBN'),  # Dictionary to construct and config norm layer. Defaults to dict(type=’BN’, requires_grad=True)
        act_cfg=dict(type='SiLU', inplace=True)),  # Config dict for activation layer. Defaults to dict(type=’SiLU’)
    neck=dict(
        type='CSPNeXtPAFPN',  # The type of neck is CSPNeXtPAFPN. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.necks.CSPNeXtPAFPN
        in_channels=[256, 512, 1024],  # Number of input channels per scale
        out_channels=256,  # Number of output channels (used at each scale)
        num_csp_blocks=3,  # Number of bottlenecks in CSPLayer. Defaults to 3
        expand_ratio=0.5,  # Ratio to adjust the number of channels of the hidden layer. Default: 0.5
        norm_cfg=dict(type='SyncBN'),  # Config dict for normalization layer. Default: dict(type=’BN’)
        act_cfg=dict(type='SiLU', inplace=True)),  # Config dict for activation layer. Default: dict(type=’Swish’)
    bbox_head=dict(
        type='RTMDetSepBNHead',  # The type of bbox_head is RTMDetSepBNHead. RTMDetHead with separated BN layers and shared conv layers. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.dense_heads.RTMDetSepBNHead
        num_classes=80,  # Number of categories excluding the background category
        in_channels=256,  # Number of channels in the input feature map
        stacked_convs=2,  # Whether to share conv layers between stages. Defaults to True
        feat_channels=256,  # Feature channels of convolutional layers in the head
        anchor_generator=dict(  # The config of anchor generator
            type='MlvlPointGenerator',  # The methods use MlvlPointGenerator. Refer to https://github.com/open-mmlab/mmdetection/blob/main/mmdet/models/task_modules/prior_generators/point_generator.py#L92
            offset=0,  # The offset of points, the value is normalized with corresponding stride. Defaults to 0.5
            strides=[8, 16, 32]),  # Strides of anchors in multiple feature levels in order (w, h)
        bbox_coder=dict(type='DistancePointBBoxCoder'),  # Distance Point BBox coder.This coder encodes gt bboxes (x1, y1, x2, y2) into (top, bottom, left,right) and decode it back to the original. Refer to https://github.com/open-mmlab/mmdetection/blob/main/mmdet/models/task_modules/coders/distance_point_bbox_coder.py#L9
        loss_cls=dict(  # Config of loss function for the classification branch
            type='QualityFocalLoss',  # Type of loss for classification branch. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.losses.QualityFocalLoss
            use_sigmoid=True,  # Whether sigmoid operation is conducted in QFL. Defaults to True
            beta=2.0,  # The beta parameter for calculating the modulating factor. Defaults to 2.0
            loss_weight=1.0),  #  Loss weight of current loss
        loss_bbox=dict(  # Config of loss function for the regression branch
            type='GIoULoss',  # Type of loss. Refer to https://mmdetection.readthedocs.io/en/latest/api.html#mmdet.models.losses.GIoULoss
            loss_weight=2.0),  # Loss weight of the regression branch
        with_objectness=False,  # Whether to add an objectness branch. Defaults to True
        exp_on_reg=True,  # Whether to use .exp() in regression
        share_conv=True,  # Whether to share conv layers between stages. Defaults to True
        pred_kernel_size=1,  # Kernel size of prediction layer. Defaults to 1
        norm_cfg=dict(type='SyncBN'),  # Config dict for normalization layer. Defaults to dict(type='BN', momentum=0.03, eps=0.001)
        act_cfg=dict(type='SiLU', inplace=True)),  # Config dict for activation layer. Defaults to dict(type='SiLU')
    train_cfg=dict(  # Config of training hyperparameters for ATSS
        assigner=dict(  # Config of assigner
            type='DynamicSoftLabelAssigner',   # Type of assigner. DynamicSoftLabelAssigner computes matching between predictions and ground truth with dynamic soft label assignment. Refer to https://github.com/open-mmlab/mmdetection/blob/main/mmdet/models/task_modules/assigners/dynamic_soft_label_assigner.py#L40
            topk=13),  # Select top-k predictions to calculate dynamic k best matches for each gt. Defaults to 13
        allowed_border=-1,  # The border allowed after padding for valid anchors
        pos_weight=-1,  # The weight of positive samples during training
        debug=False),  # Whether to set the debug mode
    test_cfg=dict(  # Config for testing hyperparameters for ATSS
        nms_pre=30000,  # The number of boxes before NMS
        min_bbox_size=0,  # The allowed minimal box size
        score_thr=0.001,  # Threshold to filter out boxes
        nms=dict(  # Config of NMS in the second stage
            type='nms',  # Type of NMS
            iou_threshold=0.65),  # NMS threshold
        max_per_img=300),  # Max number of detections of each image
)