mmdeploy/configs/mmpose/pose-detection_simcc_tensorrt_dynamic-256x192.py
RunningLeon 0efc9e3c6d
[Feat]: Support simcc from mmpose (#1187)
* add rewriting for simcc

* add simccdecode for sdk

* remove debug lines

* fix cpp lint

* move simcc decode to sdk

* add simcc sdk config

* update docs and regression yaml

* update yml
2022-10-27 11:42:50 +08:00

25 lines
618 B
Python

_base_ = ['./pose-detection_static.py', '../_base_/backends/tensorrt.py']
onnx_config = dict(
input_shape=[192, 256],
output_names=['simcc_x', 'simcc_y'],
dynamic_axes={
'input': {
0: 'batch',
},
'output': {
0: 'batch'
}
})
backend_config = dict(
common_config=dict(max_workspace_size=1 << 30),
model_inputs=[
dict(
input_shapes=dict(
input=dict(
min_shape=[1, 3, 256, 192],
opt_shape=[2, 3, 256, 192],
max_shape=[4, 3, 256, 192])))
])