From 71632d27419529c7d50159b2dee7b2ef5239e7fd Mon Sep 17 00:00:00 2001 From: Vladislav Denisov Date: Sun, 22 Dec 2024 22:54:11 +0400 Subject: [PATCH] [TF|XLA] Validation classification models (#563) --- .../validation_results_tensorflow.md | 99 ++++++++++--------- 1 file changed, 50 insertions(+), 49 deletions(-) diff --git a/results/validation/validation_results_tensorflow.md b/results/validation/validation_results_tensorflow.md index 22acf91ec..24e4734b3 100644 --- a/results/validation/validation_results_tensorflow.md +++ b/results/validation/validation_results_tensorflow.md @@ -1,6 +1,7 @@ -# Validation results for the models inferring using Intel Optimizations for TensorFlow +# Validation results for the models inferring using Intel® Optimizations for TensorFlow ## Image classification +Файлы меток для параметра `--labels` расположены [здесь](../../src/inference/labels/). ### Test image #1 @@ -12,22 +13,22 @@ Image resolution: 709 x 510 -Model | Parameters | Python API | --|-|-| -densenet-121-tf |-|-| -efficientnet-b0 |-|-| -googlenet-v1-tf |-|-| -googlenet-v2-tf |-|-| -googlenet-v3 |-|-| -googlenet-v4-tf |-|-| -inception-resnet-v2-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|9.1747866 Granny Smith
4.0729303 pomegranate
3.7423978 orange
3.7375512 bell pepper
3.6937847 piggy bank, penny bank| -mixnet-l|-|-| -mobilenet-v1-1.0-224-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.1775393 necklace
0.1625960 saltshaker, salt shaker
0.0680758 pitcher, ewer
0.0600448 syringe
0.0574061 Granny Smith| -mobilenet-v2-1.0-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.8931151 Granny Smith
0.0335338 piggy bank, penny bank
0.0027360 saltshaker, salt shaker
0.0021255 vase
0.0016607 pitcher, ewer| -mobilenet-v2-1.4-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.7240402 Granny Smith
0.0312107 vase
0.0237109 fig
0.0122461 piggy bank, penny bank
0.0118888 saltshaker, salt shaker| -mobilenet-v3-small-1.0-224-tf |-|-| -mobilenet-v3-large-1.0-224-tf |-|-| -resnet-50-tf |Channel order is RGB.
Mean values - [123.68, 116.78, 103.94]|0.9553044 Granny Smith
0.0052123 lemon
0.0047184 piggy bank, penny bank
0.0045875 orange
0.0044232 necklace| +Model | Parameters | Python API (without using XLA) | Python API (with using XLA)| +-|-|-|-| +densenet-121-tf |--input_shape 224 224 3
--input_name keras_tensor:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--output_names output_0|0.9906962 Granny Smith
0.0014767 lemon
0.0012409 orange
0.0009354 tennis ball
0.0007776 piggy bank, penny bank
0.0006042 water jug
0.0004794 banana
0.0004392 vase
0.0004066 pitcher, ewer
0.0002944 teapot|0.9906962 Granny Smith
0.0014767 lemon
0.0012409 orange
0.0009354 tennis ball
0.0007776 piggy bank, penny bank
0.0006042 water jug
0.0004794 banana
0.0004392 vase
0.0004066 pitcher, ewer
0.0002944 teapot| +efficientnet-b0 |--input_name sub:0
--input_shape 224 224 3
--output_names logits
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset.txt|10.7337656 Granny Smith
4.8936863 lemon
4.3447976 bell pepper
4.3027458 orange
4.2535648 piggy bank, penny bank
4.1575651 tennis ball
3.5578172 teapot
3.2271135 pomegranate
3.1768432 saltshaker, salt shaker
3.1720369 acorn|10.7337656 Granny Smith
4.8936863 lemon
4.3447976 bell pepper
4.3027458 orange
4.2535648 piggy bank, penny bank
4.1575651 tennis ball
3.5578172 teapot
3.2271135 pomegranate
3.1768432 saltshaker, salt shaker
3.1720369 acorn| +googlenet-v1-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.6735917 Granny Smith
0.0737862 piggy bank, penny bank
0.0155381 vase
0.0154005 pitcher, ewer
0.0136553 saltshaker, salt shaker
0.0110440 bell pepper
0.0063354 pool table, billiard table, snooker table
0.0063268 soap dispenser
0.0057057 water jug
0.0056899 dumbbell|0.6735917 Granny Smith
0.0737862 piggy bank, penny bank
0.0155381 vase
0.0154005 pitcher, ewer
0.0136553 saltshaker, salt shaker
0.0110440 bell pepper
0.0063354 pool table, billiard table, snooker table
0.0063268 soap dispenser
0.0057057 water jug
0.0056899 dumbbell| +googlenet-v2-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9849941 Granny Smith
0.0010004 lemon
0.0009706 pomegranate
0.0006835 tennis ball
0.0006694 banana
0.0004955 orange
0.0003062 pitcher, ewer
0.0002888 piggy bank, penny bank
0.0001519 fig
0.0001152 bell pepper|0.9849941 Granny Smith
0.0010004 lemon
0.0009706 pomegranate
0.0006835 tennis ball
0.0006694 banana
0.0004955 orange
0.0003062 pitcher, ewer
0.0002888 piggy bank, penny bank
0.0001519 fig
0.0001152 bell pepper| +googlenet-v3 |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9867677 Granny Smith
0.0008529 bikini, two-piece
0.0005354 piggy bank, penny bank
0.0003701 pomegranate
0.0001682 pool table, billiard table, snooker table
0.0001114 brassiere, bra, bandeau
0.0001009 orange
0.0000922 Band Aid
0.0000916 tennis ball
0.0000896 syringe|0.9867677 Granny Smith
0.0008529 bikini, two-piece
0.0005354 piggy bank, penny bank
0.0003701 pomegranate
0.0001682 pool table, billiard table, snooker table
0.0001114 brassiere, bra, bandeau
0.0001009 orange
0.0000922 Band Aid
0.0000916 tennis ball
0.0000896 syringe| +googlenet-v4-tf |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9934987 Granny Smith
0.0002234 Rhodesian ridgeback
0.0000959 pineapple, ananas
0.0000871 hair slide
0.0000778 banana
0.0000679 orange
0.0000540 kuvasz
0.0000513 EntleBucher
0.0000490 bib
0.0000422 traffic light, traffic signal, stoplight|0.9934987 Granny Smith
0.0002234 Rhodesian ridgeback
0.0000959 pineapple, ananas
0.0000871 hair slide
0.0000778 banana
0.0000679 orange
0.0000540 kuvasz
0.0000513 EntleBucher
0.0000490 bib
0.0000422 traffic light, traffic signal, stoplight| +inception-resnet-v2-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|9.1747866 Granny Smith
4.0729303 pomegranate
3.7423978 orange
3.7375512 bell pepper
3.6937847 piggy bank, penny bank|9.1747866 Granny Smith
4.0729303 pomegranate
3.7423978 orange
3.7375512 bell pepper
3.6937847 piggy bank, penny bank| +mixnet-l|--input_name IteratorGetNext:0
--output_names logits
--input_shape 224 224 3|9.1395369 Granny Smith
4.2666969 piggy bank, penny bank
3.4046013 saltshaker, salt shaker
2.9367111 tennis ball
2.5734735 soap dispenser
2.5491297 syringe
2.4780371 candle, taper, wax light
2.4671471 bakery, bakeshop, bakehouse
2.4141140 orange
2.2456863 pillow|9.1395369 Granny Smith
4.2666969 piggy bank, penny bank
3.4046013 saltshaker, salt shaker
2.9367111 tennis ball
2.5734735 soap dispenser
2.5491297 syringe
2.4780371 candle, taper, wax light
2.4671471 bakery, bakeshop, bakehouse
2.4141140 orange
2.2456863 pillow| +mobilenet-v1-1.0-224-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.1775393 necklace
0.1625960 saltshaker, salt shaker
0.0680758 pitcher, ewer
0.0600448 syringe
0.0574061 Granny Smith|0.1775393 necklace
0.1625960 saltshaker, salt shaker
0.0680758 pitcher, ewer
0.0600448 syringe
0.0574061 Granny Smith| +mobilenet-v2-1.0-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.8931151 Granny Smith
0.0335338 piggy bank, penny bank
0.0027360 saltshaker, salt shaker
0.0021255 vase
0.0016607 pitcher, ewer|0.8931151 Granny Smith
0.0335338 piggy bank, penny bank
0.0027360 saltshaker, salt shaker
0.0021255 vase
0.0016607 pitcher, ewer| +mobilenet-v2-1.4-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.7240402 Granny Smith
0.0312107 vase
0.0237109 fig
0.0122461 piggy bank, penny bank
0.0118888 saltshaker, salt shaker|0.7240402 Granny Smith
0.0312107 vase
0.0237109 fig
0.0122461 piggy bank, penny bank
0.0118888 saltshaker, salt shaker| +mobilenet-v3-small-1.0-224-tf |-|-|-| +mobilenet-v3-large-1.0-224-tf |-|-|-| +resnet-50-tf |--input_name map/TensorArrayStack/TensorArrayGatherV3:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset_first_class_base.txt|0.9553044 Granny Smith
0.0052123 lemon
0.0047184 piggy bank, penny bank
0.0045875 orange
0.0044232 necklace|0.9553044 Granny Smith
0.0052123 lemon
0.0047184 piggy bank, penny bank
0.0045875 orange
0.0044232 necklace| ### Test image #2 @@ -39,22 +40,22 @@ Image resolution: 500 x 500 -Model | Parameters | Python API | --|-|-| -densenet-121-tf |-|-| -efficientnet-b0 |-|-| -googlenet-v1-tf |-|-| -googlenet-v2-tf |-|-| -googlenet-v3 |-|-| -googlenet-v4-tf |-|-| -inception-resnet-v2-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|10.2994785 junco, snowbird
5.9667974 brambling, Fringilla montifringilla
3.8809638 indigo bunting, indigo finch, indigo bird, Passerina cyanea
3.7881403 house finch, linnet, Carpodacus mexicanus
3.4699843 goldfinch, Carduelis carduelis| -mixnet-l|-|-| -mobilenet-v1-1.0-224-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.| 0.9818491 junco, snowbird
0.0097170 house finch, linnet, Carpodacus mexicanus
0.0029993 brambling, Fringilla montifringilla
0.0022394 goldfinch, Carduelis carduelis
0.0022212 chickadee| -mobilenet-v2-1.0-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.8770270 junco, snowbird
0.0143872 water ouzel, dipper
0.0103318 chickadee
0.0063065 brambling, Fringilla montifringilla
0.0013868 red-backed sandpiper, dunlin, Erolia alpina| -mobilenet-v2-1.4-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.6637316 junco, snowbird
0.0811651 chickadee
0.0119593 water ouzel, dipper
0.0038528 brambling, Fringilla montifringilla
0.0022498 goldfinch, Carduelis carduelis| -mobilenet-v3-small-1.0-224-tf |-|-| -mobilenet-v3-large-1.0-224-tf |-|-| -resnet-50-tf |Channel order is RGB.
Mean values - [123.68, 116.78, 103.94]|0.9983400 junco, snowbird
0.0004680 brambling, Fringilla montifringilla
0.0003848 chickadee
0.0003656 water ouzel, dipper
0.0003383 goldfinch, Carduelis carduelis| +Model | Parameters | Python API (without using XLA) | Python API (with using XLA)| +-|-|-|-| +densenet-121-tf |--input_shape 224 224 3
--input_name keras_tensor:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--output_names output_0|0.9974865 junco, snowbird
0.0010784 brambling, Fringilla montifringilla
0.0006608 chickadee
0.0003314 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0001343 water ouzel, dipper
0.0000895 hummingbird
0.0000695 goldfinch, Carduelis carduelis
0.0000309 magpie
0.0000182 jay
0.0000166 house finch, linnet, Carpodacus mexicanus|0.9974865 junco, snowbird
0.0010784 brambling, Fringilla montifringilla
0.0006608 chickadee
0.0003314 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0001343 water ouzel, dipper
0.0000895 hummingbird
0.0000695 goldfinch, Carduelis carduelis
0.0000309 magpie
0.0000182 jay
0.0000166 house finch, linnet, Carpodacus mexicanus| +efficientnet-b0 |--input_name sub:0
--input_shape 224 224 3
--output_names logits
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset.txt|7.7920899 junco, snowbird
5.7337275 chickadee
5.4845691 water ouzel, dipper
3.9789405 brambling, Fringilla montifringilla
3.1936705 bulbul
2.9660630 goldfinch, Carduelis carduelis
2.3687637 red-backed sandpiper, dunlin, Erolia alpina
2.3143539 house finch, linnet, Carpodacus mexicanus
2.0986230 magpie
2.0537992 jay|7.7920899 junco, snowbird
5.7337275 chickadee
5.4845691 water ouzel, dipper
3.9789405 brambling, Fringilla montifringilla
3.1936705 bulbul
2.9660630 goldfinch, Carduelis carduelis
2.3687637 red-backed sandpiper, dunlin, Erolia alpina
2.3143539 house finch, linnet, Carpodacus mexicanus
2.0986230 magpie
2.0537992 jay| +googlenet-v1-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.7443175 junco, snowbird
0.0474521 brambling, Fringilla montifringilla
0.0457433 chickadee
0.0213393 goldfinch, Carduelis carduelis
0.0085103 house finch, linnet, Carpodacus mexicanus
0.0063562 water ouzel, dipper
0.0061872 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0021891 bulbul
0.0020557 jay
0.0009130 magpie|0.7443175 junco, snowbird
0.0474521 brambling, Fringilla montifringilla
0.0457433 chickadee
0.0213393 goldfinch, Carduelis carduelis
0.0085103 house finch, linnet, Carpodacus mexicanus
0.0063562 water ouzel, dipper
0.0061872 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0021891 bulbul
0.0020557 jay
0.0009130 magpie| +googlenet-v2-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9265916 junco, snowbird
0.0166746 brambling, Fringilla montifringilla
0.0058714 chickadee
0.0026126 water ouzel, dipper
0.0022344 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0022262 goldfinch, Carduelis carduelis
0.0015069 house finch, linnet, Carpodacus mexicanus
0.0006082 jay
0.0005987 loupe, jeweler's loupe
0.0003603 American coot, marsh hen, mud hen, water hen, Fulica americana|0.9265916 junco, snowbird
0.0166746 brambling, Fringilla montifringilla
0.0058714 chickadee
0.0026126 water ouzel, dipper
0.0022344 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0022262 goldfinch, Carduelis carduelis
0.0015069 house finch, linnet, Carpodacus mexicanus
0.0006082 jay
0.0005987 loupe, jeweler's loupe
0.0003603 American coot, marsh hen, mud hen, water hen, Fulica americana| +googlenet-v3 |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9488295 junco, snowbird
0.0005887 water ouzel, dipper
0.0004797 iron, smoothing iron
0.0003071 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0002692 cleaver, meat cleaver, chopper
0.0002677 ox
0.0002656 oxcart
0.0002526 photocopier
0.0002514 brambling, Fringilla montifringilla
0.0002449 cougar, puma, catamount, mountain lion, painter, panther, Felis concolor|0.9488295 junco, snowbird
0.0005887 water ouzel, dipper
0.0004797 iron, smoothing iron
0.0003071 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0002692 cleaver, meat cleaver, chopper
0.0002677 ox
0.0002656 oxcart
0.0002526 photocopier
0.0002514 brambling, Fringilla montifringilla
0.0002449 cougar, puma, catamount, mountain lion, painter, panther, Felis concolor| +googlenet-v4-tf |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9399364 junco, snowbird
0.0005925 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0005340 chickadee
0.0005273 brambling, Fringilla montifringilla
0.0004121 house finch, linnet, Carpodacus mexicanus
0.0004003 water ouzel, dipper
0.0003616 hamster
0.0002994 goldfinch, Carduelis carduelis
0.0002704 koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus
0.0002471 robin, American robin, Turdus migratorius|0.9399364 junco, snowbird
0.0005925 indigo bunting, indigo finch, indigo bird, Passerina cyanea
0.0005340 chickadee
0.0005273 brambling, Fringilla montifringilla
0.0004121 house finch, linnet, Carpodacus mexicanus
0.0004003 water ouzel, dipper
0.0003616 hamster
0.0002994 goldfinch, Carduelis carduelis
0.0002704 koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus
0.0002471 robin, American robin, Turdus migratorius| +inception-resnet-v2-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|10.2994785 junco, snowbird
5.9667974 brambling, Fringilla montifringilla
3.8809638 indigo bunting, indigo finch, indigo bird, Passerina cyanea
3.7881403 house finch, linnet, Carpodacus mexicanus
3.4699843 goldfinch, Carduelis carduelis|10.2994785 junco, snowbird
5.9667974 brambling, Fringilla montifringilla
3.8809638 indigo bunting, indigo finch, indigo bird, Passerina cyanea
3.7881403 house finch, linnet, Carpodacus mexicanus
3.4699843 goldfinch, Carduelis carduelis| +mixnet-l|--input_name IteratorGetNext:0
--output_names logits
--input_shape 224 224 3|8.9584866 junco, snowbird
5.7800508 brambling, Fringilla montifringilla
4.1285877 water ouzel, dipper
3.8712854 goldfinch, Carduelis carduelis
3.6966913 chickadee
3.1218438 indigo bunting, indigo finch, indigo bird, Passerina cyanea
2.9483540 house finch, linnet, Carpodacus mexicanus
1.7852575 face powder
1.7800363 chain
1.6861986 hamster|8.9584866 junco, snowbird
5.7800508 brambling, Fringilla montifringilla
4.1285877 water ouzel, dipper
3.8712854 goldfinch, Carduelis carduelis
3.6966913 chickadee
3.1218438 indigo bunting, indigo finch, indigo bird, Passerina cyanea
2.9483540 house finch, linnet, Carpodacus mexicanus
1.7852575 face powder
1.7800363 chain
1.6861986 hamster| +mobilenet-v1-1.0-224-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.9818491 junco, snowbird
0.0097170 house finch, linnet, Carpodacus mexicanus
0.0029993 brambling, Fringilla montifringilla
0.0022394 goldfinch, Carduelis carduelis
0.0022212 chickadee|0.9818491 junco, snowbird
0.0097170 house finch, linnet, Carpodacus mexicanus
0.0029993 brambling, Fringilla montifringilla
0.0022394 goldfinch, Carduelis carduelis
0.0022212 chickadee| +mobilenet-v2-1.0-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.8770270 junco, snowbird
0.0143872 water ouzel, dipper
0.0103318 chickadee
0.0063065 brambling, Fringilla montifringilla
0.0013868 red-backed sandpiper, dunlin, Erolia alpina|0.8770270 junco, snowbird
0.0143872 water ouzel, dipper
0.0103318 chickadee
0.0063065 brambling, Fringilla montifringilla
0.0013868 red-backed sandpiper, dunlin, Erolia alpina| +mobilenet-v2-1.4-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.6637316 junco, snowbird
0.0811651 chickadee
0.0119593 water ouzel, dipper
0.0038528 brambling, Fringilla montifringilla
0.0022498 goldfinch, Carduelis carduelis|0.6637316 junco, snowbird
0.0811651 chickadee
0.0119593 water ouzel, dipper
0.0038528 brambling, Fringilla montifringilla
0.0022498 goldfinch, Carduelis carduelis| +mobilenet-v3-small-1.0-224-tf |-|-|-| +mobilenet-v3-large-1.0-224-tf |-|-|-| +resnet-50-tf |--input_name map/TensorArrayStack/TensorArrayGatherV3:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset_first_class_base.txt|0.9983400 junco, snowbird
0.0004680 brambling, Fringilla montifringilla
0.0003848 chickadee
0.0003656 water ouzel, dipper
0.0003383 goldfinch, Carduelis carduelis|0.9983400 junco, snowbird
0.0004680 brambling, Fringilla montifringilla
0.0003848 chickadee
0.0003656 water ouzel, dipper
0.0003383 goldfinch, Carduelis carduelis| ### Test image #3 @@ -66,22 +67,22 @@ Image resolution: 333 x 500 -Model | Parameters | Python API | --|-|-| -densenet-121-tf |-|-| -efficientnet-b0 |-|-| -googlenet-v1-tf |-|-| -googlenet-v2-tf |-|-| -googlenet-v3 |-|-| -googlenet-v4-tf |-|-| -inception-resnet-v2-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|6.6930799 fireboat
6.1025167 breakwater, groin, groyne, mole, bulwark, seawall, jetty
6.0896273 lifeboat
5.7389712 container ship, containership, container vessel
5.4940562 dock, dockage, docking facility| -mixnet-l|-|-| -mobilenet-v1-1.0-224-tf |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.| 0.3759801 liner, ocean liner
0.1252522 lifeboat
0.1200093 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0882490 beacon, lighthouse, beacon light, pharos
0.0568063 fireboat| -mobilenet-v2-1.0-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.1885883 beacon, lighthouse, beacon light, pharos
0.1434043 liner, ocean liner
0.0768170 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0497303 drilling platform, offshore rig
0.0225758 container ship, containership, container vessel| -mobilenet-v2-1.4-224 |Channel order is RGB.
Mean values - [127.5, 127.5, 127.5],
scale value - 127.5.|0.1300134 container ship, containership, container vessel
0.0765783 lifeboat
0.0406071 dock, dockage, docking facility
0.0393021 drilling platform, offshore rig
0.0381023 liner, ocean liner| -mobilenet-v3-small-1.0-224-tf |Channel order is RGB.|-| -mobilenet-v3-large-1.0-224-tf |Channel order is RGB.|-| -resnet-50-tf |Channel order is RGB.
Mean values - [123.68, 116.78, 103.94]|0.2357705 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.1480758 liner, ocean liner
0.1104694 container ship, containership, container vessel
0.1095414 drilling platform, offshore rig
0.0915567 beacon, lighthouse, beacon light, pharos| +Model | Parameters | Python API (without using XLA) | Python API (with using XLA)| +-|-|-|-| +densenet-121-tf |--input_shape 224 224 3
--input_name keras_tensor:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--output_names output_0|0.4439965 liner, ocean liner
0.1304450 drilling platform, offshore rig
0.0822599 container ship, containership, container vessel
0.0457604 aircraft carrier, carrier, flattop, attack aircraft carrier
0.0422195 dock, dockage, docking facility
0.0352443 fireboat
0.0330128 submarine, pigboat, sub, U-boat
0.0322974 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0270287 lifeboat
0.0120249 beacon, lighthouse, beacon light, pharos|0.4439965 liner, ocean liner
0.1304450 drilling platform, offshore rig
0.0822599 container ship, containership, container vessel
0.0457604 aircraft carrier, carrier, flattop, attack aircraft carrier
0.0422195 dock, dockage, docking facility
0.0352443 fireboat
0.0330128 submarine, pigboat, sub, U-boat
0.0322974 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0270287 lifeboat
0.0120249 beacon, lighthouse, beacon light, pharos| +efficientnet-b0 |--input_name sub:0
--input_shape 224 224 3
--output_names logits
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset.txt|6.3308706 breakwater, groin, groyne, mole, bulwark, seawall, jetty
5.6206555 beacon, lighthouse, beacon light, pharos
5.5816450 liner, ocean liner
5.2046542 submarine, pigboat, sub, U-boat
5.1616158 lifeboat
4.8865576 drilling platform, offshore rig
4.8124046 seashore, coast, seacoast, sea-coast
4.6078129 wreck
4.2392783 fireboat
4.1382837 container ship, containership, container vessel|6.3308706 breakwater, groin, groyne, mole, bulwark, seawall, jetty
5.6206555 beacon, lighthouse, beacon light, pharos
5.5816450 liner, ocean liner
5.2046542 submarine, pigboat, sub, U-boat
5.1616158 lifeboat
4.8865576 drilling platform, offshore rig
4.8124046 seashore, coast, seacoast, sea-coast
4.6078129 wreck
4.2392783 fireboat
4.1382837 container ship, containership, container vessel| +googlenet-v1-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.1235983 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.1017589 liner, ocean liner
0.0949445 drilling platform, offshore rig
0.0817945 container ship, containership, container vessel
0.0486889 fireboat
0.0372103 lifeboat
0.0222339 submarine, pigboat, sub, U-boat
0.0194757 beacon, lighthouse, beacon light, pharos
0.0187142 aircraft carrier, carrier, flattop, attack aircraft carrier
0.0149769 dock, dockage, docking facility|0.1235983 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.1017589 liner, ocean liner
0.0949445 drilling platform, offshore rig
0.0817945 container ship, containership, container vessel
0.0486889 fireboat
0.0372103 lifeboat
0.0222339 submarine, pigboat, sub, U-boat
0.0194757 beacon, lighthouse, beacon light, pharos
0.0187142 aircraft carrier, carrier, flattop, attack aircraft carrier
0.0149769 dock, dockage, docking facility| +googlenet-v2-tf |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.2662658 container ship, containership, container vessel
0.0966039 dock, dockage, docking facility
0.0876836 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0488675 beacon, lighthouse, beacon light, pharos
0.0343598 drilling platform, offshore rig
0.0228717 lifeboat
0.0226615 liner, ocean liner
0.0193398 fireboat
0.0147396 water bottle
0.0085407 submarine, pigboat, sub, U-boat|0.2662658 container ship, containership, container vessel
0.0966039 dock, dockage, docking facility
0.0876836 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0488675 beacon, lighthouse, beacon light, pharos
0.0343598 drilling platform, offshore rig
0.0228717 lifeboat
0.0226615 liner, ocean liner
0.0193398 fireboat
0.0147396 water bottle
0.0085407 submarine, pigboat, sub, U-boat| +googlenet-v3 |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.4653859 beacon, lighthouse, beacon light, pharos
0.3437518 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0512174 submarine, pigboat, sub, U-boat
0.0174646 liner, ocean liner
0.0134647 lifeboat
0.0114189 container ship, containership, container vessel
0.0101290 fireboat
0.0070726 wreck
0.0037166 drilling platform, offshore rig
0.0036825 promontory, headland, head, foreland|0.4653859 beacon, lighthouse, beacon light, pharos
0.3437518 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0512174 submarine, pigboat, sub, U-boat
0.0174646 liner, ocean liner
0.0134647 lifeboat
0.0114189 container ship, containership, container vessel
0.0101290 fireboat
0.0070726 wreck
0.0037166 drilling platform, offshore rig
0.0036825 promontory, headland, head, foreland| +googlenet-v4-tf |--input_name input:0
--input_shape 299 299 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.4704932 beacon, lighthouse, beacon light, pharos
0.1695956 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0431101 lifeboat
0.0307511 fireboat
0.0149649 dock, dockage, docking facility
0.0143449 pier
0.0133830 drilling platform, offshore rig
0.0108169 submarine, pigboat, sub, U-boat
0.0082825 wreck
0.0072376 container ship, containership, container vessel|0.4704932 beacon, lighthouse, beacon light, pharos
0.1695956 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0431101 lifeboat
0.0307511 fireboat
0.0149649 dock, dockage, docking facility
0.0143449 pier
0.0133830 drilling platform, offshore rig
0.0108169 submarine, pigboat, sub, U-boat
0.0082825 wreck
0.0072376 container ship, containership, container vessel| +inception-resnet-v2-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|6.6930799 fireboat
6.1025167 breakwater, groin, groyne, mole, bulwark, seawall, jetty
6.0896273 lifeboat
5.7389712 container ship, containership, container vessel
5.4940562 dock, dockage, docking facility|6.6930799 fireboat
6.1025167 breakwater, groin, groyne, mole, bulwark, seawall, jetty
6.0896273 lifeboat
5.7389712 container ship, containership, container vessel
5.4940562 dock, dockage, docking facility| +mixnet-l|--input_name IteratorGetNext:0
--output_names logits
--input_shape 224 224 3|8.3550520 breakwater, groin, groyne, mole, bulwark, seawall, jetty
7.1289797 container ship, containership, container vessel
6.9460378 beacon, lighthouse, beacon light, pharos
6.7993770 lifeboat
6.4594803 fireboat
6.4359784 catamaran
6.4354229 wreck
6.3726940 drilling platform, offshore rig
6.2994452 amphibian, amphibious vehicle
5.8687139 submarine, pigboat, sub, U-boat|8.3550520 breakwater, groin, groyne, mole, bulwark, seawall, jetty
7.1289797 container ship, containership, container vessel
6.9460378 beacon, lighthouse, beacon light, pharos
6.7993770 lifeboat
6.4594803 fireboat
6.4359784 catamaran
6.4354229 wreck
6.3726940 drilling platform, offshore rig
6.2994452 amphibian, amphibious vehicle
5.8687139 submarine, pigboat, sub, U-boat| +mobilenet-v1-1.0-224-tf |--input_name input:0
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.3759801 liner, ocean liner
0.1252522 lifeboat
0.1200093 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0882490 beacon, lighthouse, beacon light, pharos
0.0568063 fireboat|0.3759801 liner, ocean liner
0.1252522 lifeboat
0.1200093 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0882490 beacon, lighthouse, beacon light, pharos
0.0568063 fireboat| +mobilenet-v2-1.0-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.1885883 beacon, lighthouse, beacon light, pharos
0.1434043 liner, ocean liner
0.0768170 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0497303 drilling platform, offshore rig
0.0225758 container ship, containership, container vessel|0.1885883 beacon, lighthouse, beacon light, pharos
0.1434043 liner, ocean liner
0.0768170 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.0497303 drilling platform, offshore rig
0.0225758 container ship, containership, container vessel| +mobilenet-v2-1.4-224 |--input_name input:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 127.5 127.5 127.5
--input_scale 127.5 127.5 127.5
--labels image_net_synset_first_class_base.txt|0.1300134 container ship, containership, container vessel
0.0765783 lifeboat
0.0406071 dock, dockage, docking facility
0.0393021 drilling platform, offshore rig
0.0381023 liner, ocean liner|0.1300134 container ship, containership, container vessel
0.0765783 lifeboat
0.0406071 dock, dockage, docking facility
0.0393021 drilling platform, offshore rig
0.0381023 liner, ocean liner| +mobilenet-v3-small-1.0-224-tf |-|-|-| +mobilenet-v3-large-1.0-224-tf |-|-|-| +resnet-50-tf |--input_name map/TensorArrayStack/TensorArrayGatherV3:0
--input_shape 224 224 3
--channel_swap 2 1 0
--mean 123.68 116.78 103.94
--labels image_net_synset_first_class_base.txt|0.2357705 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.1480758 liner, ocean liner
0.1104694 container ship, containership, container vessel
0.1095414 drilling platform, offshore rig
0.0915567 beacon, lighthouse, beacon light, pharos|0.2357705 breakwater, groin, groyne, mole, bulwark, seawall, jetty
0.1480758 liner, ocean liner
0.1104694 container ship, containership, container vessel
0.1095414 drilling platform, offshore rig
0.0915567 beacon, lighthouse, beacon light, pharos| ## Object detection