RTMPose: got different results by using SDK Python API and demo of inferencing with onnxruntime in Python after model deployed

[MianMianMeow]

Hi,
I'm trying to inference with onnxruntime in Python of RTMPose model trained by my own dataset, but find https://github.com/open-mmlab/mmpose/blob/main/projects/rtmpose/examples/onnxruntime/main.py gives a wrong result which is different from the prediction of torch model. However, when I use the example of SDK Python API from https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose, the result is the same as the prediction of torch model.
Any hints for this problem or for the inference of RTMPose model by onnxrumtime only rather than using mmlab packages?Thanks a lot~

Below is my config for training:

 _base_ = ['mmpose::_base_/default_runtime.py', '_base_/datasets/card_keypoints.py']
num_keypoints = 4
input_size = (256, 256)

# runtime
max_epochs = 270
stage2_num_epochs = 40
base_lr = 4e-3 
train_batch_size = 128
val_batch_size = 32


load_from = 'work_dirs/rtmpose-t_ina/best_coco_AP_epoch_250_bk.pth'

train_cfg = dict(max_epochs=max_epochs, val_interval=5)
randomness = dict(seed=21)

optim_wrapper = dict(
    type='OptimWrapper',
    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.),
    clip_grad=dict(max_norm=35, norm_type=2),
    paramwise_cfg=dict(
        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))

# learning rate
param_scheduler = [
    dict(
        type='LinearLR',
        start_factor=1.0e-5,
        by_epoch=False,
        begin=0,
        end=1000),
    dict(
        type='CosineAnnealingLR',
        eta_min=base_lr * 0.05,
        begin=max_epochs // 2,
        end=max_epochs,
        T_max=max_epochs // 2,
        by_epoch=True,
        convert_to_iter_based=True),
]

# automatically scaling LR based on the actual training batch size
auto_scale_lr = dict(base_batch_size=512)

# codec settings
codec = dict(
    type='SimCCLabel',
    input_size=input_size,
    sigma=(6.66, 6.66),
    simcc_split_ratio=2.0,
    normalize=False,
    use_dark=False)

# model settings
model = dict(
    type='TopdownPoseEstimator',
    data_preprocessor=dict(
        type='PoseDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        bgr_to_rgb=True),
    backbone=dict(
        _scope_='mmdet',
        type='CSPNeXt',
        arch='P5',
        expand_ratio=0.5,
        deepen_factor=0.167,
        widen_factor=0.375,
        out_indices=(4, ),
        channel_attention=True,
        norm_cfg=dict(type='SyncBN'),
        act_cfg=dict(type='SiLU'),
        init_cfg=dict(
            type='Pretrained',
            prefix='backbone.',
            checkpoint='https://download.openmmlab.com/mmdetection/v3.0/'
            'rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e-3a2dd350.pth'  # noqa
        )),
    head=dict(
        type='RTMCCHead',
        in_channels=384,
        out_channels=num_keypoints,
        input_size=codec['input_size'],
        in_featuremap_size=tuple([s // 32 for s in codec['input_size']]),
        simcc_split_ratio=codec['simcc_split_ratio'],
        final_layer_kernel_size=7,
        gau_cfg=dict(
            hidden_dims=256,
            s=128,
            expansion_factor=2,
            dropout_rate=0.,
            drop_path=0.,
            act_fn='SiLU',
            use_rel_bias=False,
            pos_enc=False),
        loss=dict(
            type='KLDiscretLoss',
            use_target_weight=True,
            beta=10.,
            label_softmax=True),
        decoder=codec),
    test_cfg=dict(flip_test=True, ))

# base dataset settings
dataset_type = 'CocoDataset'
data_mode = 'topdown'
data_root = '/home/jovyan/mmpose/data/ina_card_aug/'

backend_args = dict(backend='local')

# pipelines
train_pipeline = [
    dict(type='LoadImage', backend_args=backend_args),
    dict(type='GetBBoxCenterScale', padding=1.5),
    dict(type='RandomFlip', direction='diagonal'), 
#     dict(type='RandomHalfBody'), 
    dict(
        type='RandomBBoxTransform', scale_factor=[0.9, 1.1], rotate_factor=90),

    dict(type='TopdownAffine', input_size=codec['input_size']),
    dict(type='mmdet.YOLOXHSVRandomAug'),
    dict(
        type='Albumentation',
        transforms=[
            dict(type='Blur', p=0.1),
            dict(type='MedianBlur', p=0.1),
            dict(
                type='CoarseDropout',
                max_holes=1,
                max_height=0.2,
                max_width=0.2,
                min_holes=1,
                min_height=0.05,
                min_width=0.05,
                p=0.5),
        ]),
    dict(type='GenerateTarget', encoder=codec),
    dict(type='PackPoseInputs')
]
val_pipeline = [
    dict(type='LoadImage', backend_args=backend_args),
    dict(type='GetBBoxCenterScale'), 
    dict(type='TopdownAffine', input_size=codec['input_size']),
    dict(type='PackPoseInputs')
]

train_pipeline_stage2 = [
    dict(type='LoadImage', backend_args=backend_args),
    dict(type='GetBBoxCenterScale', padding=1.5), 
    dict(type='RandomFlip', direction='diagonal'),
#     dict(type='RandomHalfBody'),
    dict(
        type='RandomBBoxTransform',
        shift_factor=0.,
        scale_factor=[0.9, 1.1],
        rotate_factor=60),

    dict(type='TopdownAffine', input_size=codec['input_size']),
    dict(type='mmdet.YOLOXHSVRandomAug'),
    dict(
        type='Albumentation',
        transforms=[
            dict(type='Blur', p=0.05),
            dict(type='MedianBlur', p=0.05),
            dict(
                type='CoarseDropout',
                max_holes=1,
                max_height=0.2,
                max_width=0.2,
                min_holes=1,
                min_height=0.05,
                min_width=0.05,
                p=0.2),
        ]),
    dict(type='GenerateTarget', encoder=codec),
    dict(type='PackPoseInputs')
]

# data loaders
train_dataloader = dict(
    batch_size=train_batch_size,
    num_workers=10,
    persistent_workers=True,
    sampler=dict(type='DefaultSampler', shuffle=True),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        data_mode=data_mode,
        ann_file='annotations/train.json',
        data_prefix=dict(img='images/Train'),
        pipeline=train_pipeline,
        metainfo=dict(from_file='configs/_base_/datasets/card_keypoints.py')
    ))
val_dataloader = dict(
    batch_size=val_batch_size,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        data_mode=data_mode,
        ann_file='annotations/val.json',
        data_prefix=dict(img='images/Validation'),
        test_mode=True,
        pipeline=val_pipeline,
        metainfo=dict(from_file='configs/_base_/datasets/card_keypoints.py')
    ))
test_dataloader = dict(
    batch_size=val_batch_size,
    num_workers=4,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
    dataset=dict(
        type=dataset_type,
        data_root=data_root,
        data_mode=data_mode,
        ann_file='annotations/val.json',
        data_prefix=dict(img='images/Validation'),
        test_mode=True,
        pipeline=val_pipeline,
        metainfo=dict(from_file='configs/_base_/datasets/card_keypoints.py')
    ))
test_dataloader = val_dataloader


# hooks
default_hooks = dict(
    checkpoint=dict(save_best='coco/AP', rule='greater', max_keep_ckpts=1))

custom_hooks = [
    dict(
        type='EMAHook',
        ema_type='ExpMomentumEMA',
        momentum=0.0002,
        update_buffers=True,
        priority=49),
    dict(
        type='mmdet.PipelineSwitchHook',
        switch_epoch=max_epochs - stage2_num_epochs,
        switch_pipeline=train_pipeline_stage2)
]

# evaluators
val_evaluator = dict(
    type='CocoMetric',
    ann_file=data_root + 'annotations/val.json',
)
test_evaluator = val_evaluator

Below is my command of model deployment:

python mmdeploy/tools/deploy.py \
    mmdeploy/configs/mmpose/pose-detection_simcc_onnxruntime_dynamic_card.py \
    mmpose/configs/rtmpose-t_ina.py \
    mmpose/published_models/rtmpose_card.pth \
    test_images/kp_input2.jpg \
    --work-dir onnx_models/rtmpose-t_card \
    --device cpu \
    --dump-info  

[MianMianMeow]

Solved. I forget to modify the padding factor in https://github.com/open-mmlab/mmpose/blob/main/projects/rtmpose/examples/onnxruntime/main.py