Converted MobileNetV3-SSDLite pretrained on the COCO dataset provided by torchvision to HEF.
However, we encountered a problem that the detection results were not good on real images.
NMS configuration and detection results are attached.
{
"nms_scores_th": 0.001,
"nms_iou_th": 0.55,
"max_proposals_per_class": 20,
"image_dims": [
320,
320
],
"centers_scale_factor": 10,
"bbox_dimensions_scale_factor": 5,
"classes": 91,
"background_removal": true,
"background_removal_index": 0,
"bbox_decoders": [
{
"name": "bbox_decoder26",
"h": [
0.2,
0.264575131106459,
0.1414213562373095,
0.28284271247461906,
0.11547005383792516,
0.34641016151377546
],
"w": [
0.2,
0.264575131106459,
0.28284271247461906,
0.1414213562373095,
0.34641016151377546,
0.11547005383792516
],
"reg_layer": "conv27",
"cls_layer": "conv26"
},
{
"name": "bbox_decoder35",
"h": [
0.35,
0.4183300132670378,
0.2474873734152916,
0.4949747468305833,
0.20207259421636903,
0.606217782649107
],
"w": [
0.35,
0.4183300132670378,
0.4949747468305833,
0.2474873734152916,
0.606217782649107,
0.20207259421636903
],
"reg_layer": "conv36",
"cls_layer": "conv35"
},
{
"name": "bbox_decoder39",
"h": [
0.5,
0.570087712549569,
0.35355339059327373,
0.7071067811865476,
0.2886751345948129,
0.8660254037844386
],
"w": [
0.5,
0.570087712549569,
0.7071067811865476,
0.35355339059327373,
0.8660254037844386,
0.2886751345948129
],
"reg_layer": "conv40",
"cls_layer": "conv39"
},
{
"name": "bbox_decoder43",
"h": [
0.65,
0.7211102550927979,
0.4596194077712559,
0.9192388155425119,
0.37527767497325676,
1.12583302491977
],
"w": [
0.65,
0.7211102550927979,
0.9192388155425119,
0.4596194077712559,
1.12583302491977,
0.37527767497325676
],
"reg_layer": "conv44",
"cls_layer": "conv43"
},
{
"name": "bbox_decoder47",
"h": [
0.8,
0.8717797887081347,
0.565685424949238,
1.1313708498984762,
0.46188021535170065,
1.3856406460551018
],
"w": [
0.8,
0.8717797887081347,
1.1313708498984762,
0.565685424949238,
1.3856406460551018,
0.46188021535170065
],
"reg_layer": "conv48",
"cls_layer": "conv47"
},
{
"name": "bbox_decoder50",
"h": [
0.95,
0.9746794344808963,
0.67175144212722,
1.3435028842544403,
0.5484827557301445,
1.6454482671904334
],
"w": [
0.95,
0.9746794344808963,
1.3435028842544403,
0.67175144212722,
1.6454482671904334,
0.5484827557301445
],
"reg_layer": "conv51",
"cls_layer": "conv50"
}
]
}
This results in a detection score of 0.99 or higher.
Your help would be appreciated.