talksik/mediapipe
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Metadata Writer: add object detection metadata writer.

Browse Source 
PiperOrigin-RevId: 513897494
This commit is contained in:
Yuqi Li
2023-03-06 07:11:10 -08:00
committed by Copybara-Service
parent 13db1c55d3
commit fe92d2e781
17 changed files with 1324 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
mediapipe/tasks/testdata/metadata/BUILD
Vendored
+20
View File
@@ -25,6 +25,12 @@ package(
mediapipe_files(srcs = [
"30k-clean.model",
"bert_text_classifier_no_metadata.tflite",
"category_tensor_float_meta.json",
"coco_ssd_mobilenet_v1_1.0_quant_2018_06_29_no_metadata.tflite",
"coco_ssd_mobilenet_v1_score_calibration.json",
"efficientdet_lite0_v1.json",
"efficientdet_lite0_v1.tflite",
"labelmap.txt",
"mobile_ica_8bit-with-metadata.tflite",
"mobile_ica_8bit-with-unsupported-metadata-version.tflite",
"mobile_ica_8bit-without-model-metadata.tflite",
@@ -35,6 +41,10 @@ mediapipe_files(srcs = [
"mobilenet_v2_1.0_224_quant_without_metadata.tflite",
"mobilenet_v2_1.0_224_without_metadata.tflite",
"movie_review.tflite",
"score_calibration.csv",
"ssd_mobilenet_v1_no_metadata.json",
"ssd_mobilenet_v1_no_metadata.tflite",
"tensor_group_meta.json",
])
exports_files([
@@ -74,6 +84,8 @@ filegroup(
srcs = [
"30k-clean.model",
"bert_text_classifier_no_metadata.tflite",
"coco_ssd_mobilenet_v1_1.0_quant_2018_06_29_no_metadata.tflite",
"efficientdet_lite0_v1.tflite",
"mobile_ica_8bit-with-metadata.tflite",
"mobile_ica_8bit-with-unsupported-metadata-version.tflite",
"mobile_ica_8bit-without-model-metadata.tflite",
@@ -83,6 +95,7 @@ filegroup(
"mobilenet_v2_1.0_224_quant_without_metadata.tflite",
"mobilenet_v2_1.0_224_without_metadata.tflite",
"movie_review.tflite",
"ssd_mobilenet_v1_no_metadata.tflite",
],
)
@@ -94,9 +107,12 @@ filegroup(
"bert_text_classifier_with_sentence_piece.json",
"bert_tokenizer_meta.json",
"bounding_box_tensor_meta.json",
"category_tensor_float_meta.json",
"classification_tensor_float_meta.json",
"classification_tensor_uint8_meta.json",
"classification_tensor_unsupported_meta.json",
"coco_ssd_mobilenet_v1_score_calibration.json",
"efficientdet_lite0_v1.json",
"external_file",
"feature_tensor_meta.json",
"general_meta.json",
@@ -107,6 +123,7 @@ filegroup(
"input_image_tensor_unsupported_meta.json",
"input_text_tensor_default_meta.json",
"input_text_tensor_meta.json",
"labelmap.txt",
"labels.txt",
"mobilebert_vocab.txt",
"mobilenet_v2_1.0_224.json",
@@ -114,10 +131,13 @@ filegroup(
"movie_review.json",
"movie_review_labels.txt",
"regex_vocab.txt",
"score_calibration.csv",
"score_calibration.txt",
"score_calibration_file_meta.json",
"score_calibration_tensor_meta.json",
"score_thresholding_meta.json",
"sentence_piece_tokenizer_meta.json",
"ssd_mobilenet_v1_no_metadata.json",
"tensor_group_meta.json",
],
)
mediapipe/tasks/testdata/metadata/category_tensor_float_meta.json
Vendored
+33
View File
@@ -0,0 +1,33 @@
{
"subgraph_metadata": [
{
"input_tensor_metadata": [
{
"name": "category",
"description": "The category tensor.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
}
},
"stats": {
},
"associated_files": [
{
"name": "labels.txt",
"description": "Labels for categories that the model can recognize.",
"type": "TENSOR_VALUE_LABELS",
"locale": "en"
},
{
"name": "labels_cn.txt",
"description": "Labels for categories that the model can recognize.",
"type": "TENSOR_VALUE_LABELS",
"locale": "cn"
}
]
}
]
}
]
}
mediapipe/tasks/testdata/metadata/coco_ssd_mobilenet_v1_score_calibration.json
Vendored
+140
View File
@@ -0,0 +1,140 @@
{
"name": "ObjectDetector",
"description": "Identify which of a known set of objects might be present and provide information about their positions within the given image or a video stream.",
"subgraph_metadata": [
{
"input_tensor_metadata": [
{
"name": "image",
"description": "Input image to be processed.",
"content": {
"content_properties_type": "ImageProperties",
"content_properties": {
"color_space": "RGB"
}
},
"process_units": [
{
"options_type": "NormalizationOptions",
"options": {
"mean": [
127.5
],
"std": [
127.5
]
}
}
],
"stats": {
"max": [
255.0
],
"min": [
0.0
]
}
}
],
"output_tensor_metadata": [
{
"name": "location",
"description": "The locations of the detected boxes.",
"content": {
"content_properties_type": "BoundingBoxProperties",
"content_properties": {
"index": [
1,
0,
3,
2
],
"type": "BOUNDARIES"
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
}
},
{
"name": "category",
"description": "The categories of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
},
"associated_files": [
{
"name": "labels.txt",
"description": "Labels for categories that the model can recognize.",
"type": "TENSOR_VALUE_LABELS"
}
]
},
{
"name": "score",
"description": "The scores of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"process_units": [
{
"options_type": "ScoreCalibrationOptions",
"options": {
"score_transformation": "INVERSE_LOGISTIC",
"default_score": 0.2
}
}
],
"stats": {
},
"associated_files": [
{
"name": "score_calibration.txt",
"description": "Contains sigmoid-based score calibration parameters. The main purposes of score calibration is to make scores across classes comparable, so that a common threshold can be used for all output classes.",
"type": "TENSOR_AXIS_SCORE_CALIBRATION"
}
]
},
{
"name": "number of detections",
"description": "The number of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
}
},
"stats": {
}
}
],
"output_tensor_groups": [
{
"name": "detection_result",
"tensor_names": [
"location",
"category",
"score"
]
}
]
}
],
"min_parser_version": "1.2.0"
}
mediapipe/tasks/testdata/metadata/efficientdet_lite0_v1.json
Vendored
+124
View File
@@ -0,0 +1,124 @@
{
"name": "ObjectDetector",
"description": "Identify which of a known set of objects might be present and provide information about their positions within the given image or a video stream.",
"subgraph_metadata": [
{
"input_tensor_metadata": [
{
"name": "image",
"description": "Input image to be processed.",
"content": {
"content_properties_type": "ImageProperties",
"content_properties": {
"color_space": "RGB"
}
},
"process_units": [
{
"options_type": "NormalizationOptions",
"options": {
"mean": [
127.5
],
"std": [
127.5
]
}
}
],
"stats": {
"max": [
255.0
],
"min": [
0.0
]
}
}
],
"output_tensor_metadata": [
{
"name": "score",
"description": "The scores of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
}
},
{
"name": "location",
"description": "The locations of the detected boxes.",
"content": {
"content_properties_type": "BoundingBoxProperties",
"content_properties": {
"index": [
1,
0,
3,
2
],
"type": "BOUNDARIES"
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
}
},
{
"name": "number of detections",
"description": "The number of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
}
},
"stats": {
}
},
{
"name": "category",
"description": "The categories of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
},
"associated_files": [
{
"name": "labels.txt",
"description": "Labels for categories that the model can recognize.",
"type": "TENSOR_VALUE_LABELS"
}
]
}
],
"output_tensor_groups": [
{
"name": "detection_result",
"tensor_names": [
"location",
"category",
"score"
]
}
]
}
],
"min_parser_version": "1.2.0"
}
mediapipe/tasks/testdata/metadata/labelmap.txt
Vendored
+90
View File
@@ -0,0 +1,90 @@
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
mediapipe/tasks/testdata/metadata/score_calibration.csv
Vendored
+89
View File
@@ -0,0 +1,89 @@
0.9876328110694885,0.36622241139411926,0.5352765321731567,0.71484375
0.9584911465644836,1.0602262020111084,0.2777034342288971,0.019999999552965164
0.9698624014854431,0.8795201778411865,0.539591908454895,0.00390625
0.7486230731010437,1.1876736879348755,2.552982807159424,0.019999999552965164
0.9745277166366577,0.3739396333694458,0.4621727764606476,0.19921875
0.9683839678764343,0.6996201276779175,0.7690851092338562,0.019999999552965164
0.6875,0.31044548749923706,1.0056899785995483,0.019999999552965164
0.9849396347999573,0.8532888889312744,-0.2361421436071396,0.03125
0.9878578186035156,1.0118975639343262,0.13313621282577515,0.359375
0.9915205836296082,0.4434199929237366,1.0268371105194092,0.05078125
0.9370332360267639,0.4586562216281891,-0.08101099729537964,0.019999999552965164
0.9905818104743958,0.8670706152915955,0.012704282067716122,0.019999999552965164
0.9080020189285278,0.8507471680641174,0.5081117749214172,0.019999999552965164
0.985953152179718,0.9933826923370361,-0.8114940524101257,0.109375
0.9819648861885071,1.12098228931427,-0.6330763697624207,0.01171875
0.9025918245315552,0.7803755402565002,0.03275677561759949,0.08984375
0.9863958954811096,0.11243592947721481,0.935604453086853,0.61328125
0.9905291795730591,0.3710605800151825,0.708966851234436,0.359375
0.9917052984237671,0.9596433043479919,0.19800108671188354,0.09765625
0.8762937188148499,0.3449830114841461,0.5352474451065063,0.0078125
0.9902125000953674,0.8918796181678772,-0.1306992471218109,0.26171875
0.9902340173721313,0.9177873134613037,-0.4322589933872223,0.019999999552965164
0.9707600474357605,0.7028177976608276,0.9813734889030457,0.019999999552965164
0.9823090434074402,1.0499590635299683,0.12045472860336304,0.0078125
0.990516185760498,0.9449402093887329,1.3773189783096313,0.019999999552965164
0.9875434041023254,0.577914297580719,1.282518982887268,0.0390625
0.9821421504020691,0.0967339277267456,0.8279788494110107,0.47265625
0.9875047206878662,0.9038218259811401,2.1208062171936035,0.38671875
0.9857864379882812,0.8627446889877319,0.18189261853694916,0.019999999552965164
0.9647751450538635,1.0752476453781128,-0.018294010311365128,0.0234375
0.9830358624458313,0.5638481378555298,0.8346489667892456,0.019999999552965164
0.9904966354370117,1.0160938501358032,-0.0573287308216095,0.00390625
0.8458405137062073,0.4868394434452057,0.6617084741592407,0.019999999552965164
0.9847381711006165,0.5939620137214661,0.008616370148956776,0.00390625
0.9375938773155212,0.723095178604126,0.6635608077049255,0.019999999552965164
0.9334303140640259,0.5689108967781067,0.37019580602645874,0.019999999552965164
0.9716793894767761,1.0037211179733276,0.5898993611335754,0.02734375
0.9197732210159302,0.46794334053993225,0.7365336418151855,0.640625
0.9857497811317444,0.7299028635025024,0.9195274114608765,0.0390625
0.8758038282394409,1.200216293334961,0.02580185979604721,0.019999999552965164
0.9841026067733765,0.8050475716590881,0.9698556661605835,0.0078125
0.9908539652824402,0.7911490201950073,0.19351358711719513,0.12109375
0.9179956316947937,0.023991893976926804,0.35193610191345215,0.04296875
0.9903728365898132,0.7744967341423035,0.2686336636543274,0.359375
0.906022846698761,0.5766159892082214,1.0600007772445679,0.04296875
0.9885554909706116,0.99117511510849,0.5611960291862488,0.4140625
0.9906331896781921,1.1376535892486572,1.45369291305542,0.019999999552965164
0.9640991687774658,0.5387894511222839,1.1824018955230713,0.019999999552965164
0.9932155609130859,0.4347895085811615,1.3938102722167969,0.0078125
0.9884702563285828,0.885567843914032,0.1556047648191452,0.1484375
0.9891508221626282,0.04143073782324791,0.6111864447593689,0.0078125
0.8935436010360718,0.2937895655632019,0.3215920031070709,0.00390625
0.8327123522758484,0.8381986021995544,-0.026293788105249405,0.019999999552965164
0.9839455485343933,0.9581400156021118,1.495324969291687,0.640625
0.9904995560646057,0.9168422818183899,0.33293962478637695,0.015625
0.9856975674629211,1.0433714389801025,0.5954801440238953,0.019999999552965164
0.9942344427108765,0.7206616997718811,1.666426181793213,0.9609375
0.8182767033576965,0.9546273946762085,0.5500107407569885,0.019999999552965164
0.9631295800209045,0.6277880668640137,0.05952891707420349,0.05859375
0.9819005727767944,1.0826934576034546,0.7444049715995789,0.30859375
0.9884315133094788,1.0500890016555786,1.1161768436431885,0.019999999552965164
0.9175815582275391,0.09232989698648453,1.596696138381958,0.47265625
0.9868760108947754,0.903079628944397,-0.15774966776371002,0.8515625
0.9866015911102295,0.7533788084983826,0.7489103078842163,0.03125
0.8074312806129456,0.8615151643753052,0.40621864795684814,0.00390625
0.9829285144805908,0.8954831957817078,0.4462486207485199,0.02734375
0.9681841135025024,0.6257772445678711,0.43809664249420166,0.38671875
0.9872947931289673,0.9947993159294128,0.9271130561828613,0.26171875
0.7997345328330994,0.3995186686515808,-0.3755347430706024,0.019999999552965164
0.9922754168510437,1.1357101202011108,-0.10267537832260132,0.5
0.9861471652984619,0.8725204467773438,1.1657888889312744,0.019999999552965164
0.9888646006584167,1.2098380327224731,-0.27832522988319397,0.05078125
0.5641342997550964,1.0501892566680908,1.9519661664962769,0.019999999552965164
0.9548168778419495,0.8971696496009827,1.378737449645996,0.00390625
0.9875019788742065,0.8718118071556091,0.5476236939430237,0.0078125
0.9725168347358704,0.6989551782608032,-1.3157455921173096,0.61328125
0.9864014983177185,0.7576251029968262,-0.41650667786598206,0.00390625
0.960071861743927,0.13068856298923492,0.4819187819957733,0.019999999552965164
0.9849705100059509,0.7724528908729553,0.3877875804901123,0.03125
0.9703006744384766,0.8848260641098022,-1.1767181158065796,0.80078125
0.9837008714675903,0.7015050053596497,0.18209102749824524,0.00390625
0.9579976797103882,0.053806986659765244,2.7309608459472656,0.4000000059604645
0.9896979928016663,0.41135814785957336,0.5738034844398499,0.019999999552965164
0.9853873252868652,0.5438565611839294,0.20562179386615753,0.02734375
0.9784129858016968,0.6330984830856323,-0.1789831817150116,0.015625
0.9375,0.855596125125885,-0.1933964192867279,0.019999999552965164
0.9524176716804504,0.08709807693958282,0.6299692988395691,0.33203125
1 0.9876328110694885 0.36622241139411926 0.5352765321731567 0.71484375
2 0.9584911465644836 1.0602262020111084 0.2777034342288971 0.019999999552965164
3 0.9698624014854431 0.8795201778411865 0.539591908454895 0.00390625
4 0.7486230731010437 1.1876736879348755 2.552982807159424 0.019999999552965164
5 0.9745277166366577 0.3739396333694458 0.4621727764606476 0.19921875
6 0.9683839678764343 0.6996201276779175 0.7690851092338562 0.019999999552965164
7 0.6875 0.31044548749923706 1.0056899785995483 0.019999999552965164
8 0.9849396347999573 0.8532888889312744 -0.2361421436071396 0.03125
9 0.9878578186035156 1.0118975639343262 0.13313621282577515 0.359375
10 0.9915205836296082 0.4434199929237366 1.0268371105194092 0.05078125
11 0.9370332360267639 0.4586562216281891 -0.08101099729537964 0.019999999552965164
12 0.9905818104743958 0.8670706152915955 0.012704282067716122 0.019999999552965164
13 0.9080020189285278 0.8507471680641174 0.5081117749214172 0.019999999552965164
14 0.985953152179718 0.9933826923370361 -0.8114940524101257 0.109375
15 0.9819648861885071 1.12098228931427 -0.6330763697624207 0.01171875
16 0.9025918245315552 0.7803755402565002 0.03275677561759949 0.08984375
17 0.9863958954811096 0.11243592947721481 0.935604453086853 0.61328125
18 0.9905291795730591 0.3710605800151825 0.708966851234436 0.359375
19 0.9917052984237671 0.9596433043479919 0.19800108671188354 0.09765625
20 0.8762937188148499 0.3449830114841461 0.5352474451065063 0.0078125
21 0.9902125000953674 0.8918796181678772 -0.1306992471218109 0.26171875
22 0.9902340173721313 0.9177873134613037 -0.4322589933872223 0.019999999552965164
23 0.9707600474357605 0.7028177976608276 0.9813734889030457 0.019999999552965164
24 0.9823090434074402 1.0499590635299683 0.12045472860336304 0.0078125
25 0.990516185760498 0.9449402093887329 1.3773189783096313 0.019999999552965164
26 0.9875434041023254 0.577914297580719 1.282518982887268 0.0390625
27 0.9821421504020691 0.0967339277267456 0.8279788494110107 0.47265625
28 0.9875047206878662 0.9038218259811401 2.1208062171936035 0.38671875
29 0.9857864379882812 0.8627446889877319 0.18189261853694916 0.019999999552965164
30 0.9647751450538635 1.0752476453781128 -0.018294010311365128 0.0234375
31 0.9830358624458313 0.5638481378555298 0.8346489667892456 0.019999999552965164
32 0.9904966354370117 1.0160938501358032 -0.0573287308216095 0.00390625
33 0.8458405137062073 0.4868394434452057 0.6617084741592407 0.019999999552965164
34 0.9847381711006165 0.5939620137214661 0.008616370148956776 0.00390625
35 0.9375938773155212 0.723095178604126 0.6635608077049255 0.019999999552965164
36 0.9334303140640259 0.5689108967781067 0.37019580602645874 0.019999999552965164
37 0.9716793894767761 1.0037211179733276 0.5898993611335754 0.02734375
38 0.9197732210159302 0.46794334053993225 0.7365336418151855 0.640625
39 0.9857497811317444 0.7299028635025024 0.9195274114608765 0.0390625
40 0.8758038282394409 1.200216293334961 0.02580185979604721 0.019999999552965164
41 0.9841026067733765 0.8050475716590881 0.9698556661605835 0.0078125
42 0.9908539652824402 0.7911490201950073 0.19351358711719513 0.12109375
43 0.9179956316947937 0.023991893976926804 0.35193610191345215 0.04296875
44 0.9903728365898132 0.7744967341423035 0.2686336636543274 0.359375
45 0.906022846698761 0.5766159892082214 1.0600007772445679 0.04296875
46 0.9885554909706116 0.99117511510849 0.5611960291862488 0.4140625
47 0.9906331896781921 1.1376535892486572 1.45369291305542 0.019999999552965164
48 0.9640991687774658 0.5387894511222839 1.1824018955230713 0.019999999552965164
49 0.9932155609130859 0.4347895085811615 1.3938102722167969 0.0078125
50 0.9884702563285828 0.885567843914032 0.1556047648191452 0.1484375
51 0.9891508221626282 0.04143073782324791 0.6111864447593689 0.0078125
52 0.8935436010360718 0.2937895655632019 0.3215920031070709 0.00390625
53 0.8327123522758484 0.8381986021995544 -0.026293788105249405 0.019999999552965164
54 0.9839455485343933 0.9581400156021118 1.495324969291687 0.640625
55 0.9904995560646057 0.9168422818183899 0.33293962478637695 0.015625
56 0.9856975674629211 1.0433714389801025 0.5954801440238953 0.019999999552965164
57 0.9942344427108765 0.7206616997718811 1.666426181793213 0.9609375
58 0.8182767033576965 0.9546273946762085 0.5500107407569885 0.019999999552965164
59 0.9631295800209045 0.6277880668640137 0.05952891707420349 0.05859375
60 0.9819005727767944 1.0826934576034546 0.7444049715995789 0.30859375
61 0.9884315133094788 1.0500890016555786 1.1161768436431885 0.019999999552965164
62 0.9175815582275391 0.09232989698648453 1.596696138381958 0.47265625
63 0.9868760108947754 0.903079628944397 -0.15774966776371002 0.8515625
64 0.9866015911102295 0.7533788084983826 0.7489103078842163 0.03125
65 0.8074312806129456 0.8615151643753052 0.40621864795684814 0.00390625
66 0.9829285144805908 0.8954831957817078 0.4462486207485199 0.02734375
67 0.9681841135025024 0.6257772445678711 0.43809664249420166 0.38671875
68 0.9872947931289673 0.9947993159294128 0.9271130561828613 0.26171875
69 0.7997345328330994 0.3995186686515808 -0.3755347430706024 0.019999999552965164
70 0.9922754168510437 1.1357101202011108 -0.10267537832260132 0.5
71 0.9861471652984619 0.8725204467773438 1.1657888889312744 0.019999999552965164
72 0.9888646006584167 1.2098380327224731 -0.27832522988319397 0.05078125
73 0.5641342997550964 1.0501892566680908 1.9519661664962769 0.019999999552965164
74 0.9548168778419495 0.8971696496009827 1.378737449645996 0.00390625
75 0.9875019788742065 0.8718118071556091 0.5476236939430237 0.0078125
76 0.9725168347358704 0.6989551782608032 -1.3157455921173096 0.61328125
77 0.9864014983177185 0.7576251029968262 -0.41650667786598206 0.00390625
78 0.960071861743927 0.13068856298923492 0.4819187819957733 0.019999999552965164
79 0.9849705100059509 0.7724528908729553 0.3877875804901123 0.03125
80 0.9703006744384766 0.8848260641098022 -1.1767181158065796 0.80078125
81 0.9837008714675903 0.7015050053596497 0.18209102749824524 0.00390625
82 0.9579976797103882 0.053806986659765244 2.7309608459472656 0.4000000059604645
83 0.9896979928016663 0.41135814785957336 0.5738034844398499 0.019999999552965164
84 0.9853873252868652 0.5438565611839294 0.20562179386615753 0.02734375
85 0.9784129858016968 0.6330984830856323 -0.1789831817150116 0.015625
86 0.9375 0.855596125125885 -0.1933964192867279 0.019999999552965164
87 0.9524176716804504 0.08709807693958282 0.6299692988395691 0.33203125
mediapipe/tasks/testdata/metadata/ssd_mobilenet_v1_no_metadata.json
Vendored
+124
View File
@@ -0,0 +1,124 @@
{
"name": "ObjectDetector",
"description": "Identify which of a known set of objects might be present and provide information about their positions within the given image or a video stream.",
"subgraph_metadata": [
{
"input_tensor_metadata": [
{
"name": "image",
"description": "Input image to be processed.",
"content": {
"content_properties_type": "ImageProperties",
"content_properties": {
"color_space": "RGB"
}
},
"process_units": [
{
"options_type": "NormalizationOptions",
"options": {
"mean": [
127.5
],
"std": [
127.5
]
}
}
],
"stats": {
"max": [
255.0
],
"min": [
0.0
]
}
}
],
"output_tensor_metadata": [
{
"name": "location",
"description": "The locations of the detected boxes.",
"content": {
"content_properties_type": "BoundingBoxProperties",
"content_properties": {
"index": [
1,
0,
3,
2
],
"type": "BOUNDARIES"
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
}
},
{
"name": "category",
"description": "The categories of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
},
"associated_files": [
{
"name": "labels.txt",
"description": "Labels for categories that the model can recognize.",
"type": "TENSOR_VALUE_LABELS"
}
]
},
{
"name": "score",
"description": "The scores of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
},
"range": {
"min": 2,
"max": 2
}
},
"stats": {
}
},
{
"name": "number of detections",
"description": "The number of the detected boxes.",
"content": {
"content_properties_type": "FeatureProperties",
"content_properties": {
}
},
"stats": {
}
}
],
"output_tensor_groups": [
{
"name": "detection_result",
"tensor_names": [
"location",
"category",
"score"
]
}
]
}
],
"min_parser_version": "1.2.0"
}
mediapipe/tasks/testdata/metadata/tensor_group_meta.json
Vendored
+16
View File
@@ -0,0 +1,16 @@
{
"subgraph_metadata": [
{
"output_tensor_groups": [
{
"name": "detection_result",
"tensor_names": [
"location",
"category",
"score"
]
}
]
}
]
}