Merge pull request #46 from fengyuentau/add_mobilenet_v1_v2

README.md

@@ -23,6 +23,8 @@ Guidelines:
 | [CRNN-EN](./models/text_recognition_crnn)             | 100x32   | 50.21  | 234.32  | 196.15 | 125.30 | ---   |
 | [CRNN-CN](./models/text_recognition_crnn)             | 100x32   | 73.52  | 322.16  | 239.76 | 166.79 | ---   |
 | [PP-ResNet](./models/image_classification_ppresnet)   | 224x224  | 56.05  | 602.58  | 98.64  | 75.45  | ---   |
+| [MobileNet-V1](./models/image_classification_mobilenet)| 224x224 | 7.76   | 85.09   | 20.78  | 45.78  | ---   |
+| [MobileNet-V2](./models/image_classification_mobilenet)| 224x224 | 7.48   | 74.45   | 23.92  | 104.05 | ---   |
 | [PP-HumanSeg](./models/human_segmentation_pphumanseg) | 192x192  | 19.92  | 105.32  | 67.97  | 74.77  | ---   |
 | [WeChatQRCode](./models/qrcode_wechatqrcode)          | 100x100  | 7.04   | 37.68   | ---    | ---    | ---   |
 | [DaSiamRPN](./models/object_tracking_dasiamrpn)       | 1280x720 | 36.15  | 705.48  | 76.82  | ---    | ---   |

benchmark/config/image_classification_mobilenetv1.yaml

@@ -0,0 +1,20 @@
+Benchmark:
+  name: "Image Classification Benchmark"
+  type: "Classification"
+  data:
+    path: "benchmark/data/image_classification"
+    files: ["coffee_mug.jpg", "umbrella.jpg", "wall_clock.jpg"]
+    sizes: [[256, 256]]
+    toRGB: True
+    centerCrop: 224
+  metric:
+    warmup: 30
+    repeat: 10
+    reduction: "median"
+  backend: "default"
+  target: "cpu"
+
+Model:
+  name: "MobileNetV1"
+  modelPath: "models/image_classification_mobilenet/mobilenet_v1.onnx"
+  labelPath: "models/image_classification_mobilenet/imagenet_labels.txt"

benchmark/config/image_classification_mobilenetv2.yaml

@@ -0,0 +1,20 @@
+Benchmark:
+  name: "Image Classification Benchmark"
+  type: "Classification"
+  data:
+    path: "benchmark/data/image_classification"
+    files: ["coffee_mug.jpg", "umbrella.jpg", "wall_clock.jpg"]
+    sizes: [[256, 256]]
+    toRGB: True
+    centerCrop: 224
+  metric:
+    warmup: 30
+    repeat: 10
+    reduction: "median"
+  backend: "default"
+  target: "cpu"
+
+Model:
+  name: "MobileNetV2"
+  modelPath: "models/image_classification_mobilenet/mobilenet_v2.onnx"
+  labelPath: "models/image_classification_mobilenet/imagenet_labels.txt"

models/__init__.py

@@ -7,6 +7,8 @@ from .human_segmentation_pphumanseg.pphumanseg import PPHumanSeg
 from .qrcode_wechatqrcode.wechatqrcode import WeChatQRCode
 from .object_tracking_dasiamrpn.dasiamrpn import DaSiamRPN
 from .person_reid_youtureid.youtureid import YoutuReID
+from .image_classification_mobilenet.mobilenet_v1 import MobileNetV1
+from .image_classification_mobilenet.mobilenet_v2 import MobileNetV2
 
 class Registery:
     def __init__(self, name):
@@ -28,4 +30,7 @@ MODELS.register(PPResNet)
 MODELS.register(PPHumanSeg)
 MODELS.register(WeChatQRCode)
 MODELS.register(DaSiamRPN)
-MODELS.register(YoutuReID)
+MODELS.register(YoutuReID)
+MODELS.register(MobileNetV1)
+MODELS.register(MobileNetV2)
+

models/image_classification_mobilenet/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2017-, Shicai Yang
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

models/image_classification_mobilenet/README.md

@@ -0,0 +1,35 @@
+# MobileNets
+
+MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
+
+MobileNetV2: Inverted Residuals and Linear Bottlenecks
+
+Models are taken from https://github.com/shicai/MobileNet-Caffe and converted to ONNX format using [caffe2onnx](https://github.com/asiryan/caffe2onnx):
+```
+python -m caffe2onnx.convert --prototxt mobilenet_deploy.prototxt --caffemodel mobilenet.caffemodel --onnx mobilenet_v1.onnx
+python -m caffe2onnx.convert --prototxt mobilenet_v2_deploy.prototxt --caffemodel mobilenet_v2.caffemodel --onnx mobilenet_v2.onnx
+```
+
+NOTE: Quantized MobileNet V1 & V2 have a great drop in accuracy. We are working on producing higher accuracy MobileNets.
+
+## Demo
+
+Run the following command to try the demo:
+```shell
+# MobileNet V1
+python demo.py --input /path/to/image
+# MobileNet V2
+python demo.py --input /path/to/image --model v2
+```
+
+## License
+
+Model weights are licensed under [BSD-3-Clause License](./LICENSE).
+Scripts are licensed unser [Apache 2.0 License](../../LICENSE).
+
+## Reference
+
+- MobileNet V1: https://arxiv.org/abs/1704.04861
+- MobileNet V2: https://arxiv.org/abs/1801.04381
+- https://github.com/shicai/MobileNet-Caffe
+

models/image_classification_mobilenet/demo.py

@@ -0,0 +1,59 @@
+import argparse
+
+import numpy as np
+import cv2 as cv
+
+from mobilenet_v1 import MobileNetV1
+from mobilenet_v2 import MobileNetV2
+
+def str2bool(v):
+    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
+        return True
+    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
+        return False
+    else:
+        raise NotImplementedError
+
+backends = [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_BACKEND_CUDA]
+targets = [cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_CUDA, cv.dnn.DNN_TARGET_CUDA_FP16]
+help_msg_backends = "Choose one of the computation backends: {:d}: OpenCV implementation (default); {:d}: CUDA"
+help_msg_targets = "Chose one of the target computation devices: {:d}: CPU (default); {:d}: CUDA; {:d}: CUDA fp16"
+try:
+    backends += [cv.dnn.DNN_BACKEND_TIMVX]
+    targets += [cv.dnn.DNN_TARGET_NPU]
+    help_msg_backends += "; {:d}: TIMVX"
+    help_msg_targets += "; {:d}: NPU"
+except:
+    print('This version of OpenCV does not support TIM-VX and NPU. Visit https://gist.github.com/fengyuentau/5a7a5ba36328f2b763aea026c43fa45f for more information.')
+
+parser = argparse.ArgumentParser(description='Demo for MobileNet V1 & V2.')
+parser.add_argument('--input', '-i', type=str, help='Path to the input image.')
+parser.add_argument('--model', '-m', type=str, choices=['v1', 'v2', 'v1-q', 'v2-q'], default='v1', help='Which model to use, either v1 or v2.')
+parser.add_argument('--backend', '-b', type=int, default=backends[0], help=help_msg_backends.format(*backends))
+parser.add_argument('--target', '-t', type=int, default=targets[0], help=help_msg_targets.format(*targets))
+parser.add_argument('--label', '-l', type=str, default='./imagenet_labels.txt', help='Path to the dataset labels.')
+args = parser.parse_args()
+
+if __name__ == '__main__':
+    # Instantiate ResNet
+    models = {
+        'v1': MobileNetV1(modelPath='./image_classification_mobilenetv1_2022apr.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
+        'v2': MobileNetV2(modelPath='./image_classification_mobilenetv2_2022apr.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
+        'v1-q': MobileNetV1(modelPath='./image_classification_mobilenetv1_2022apr-act_int8-wt_int8-quantized.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target),
+        'v2-q': MobileNetV2(modelPath='./image_classification_mobilenetv2_2022apr-act_int8-wt_int8-quantized.onnx', labelPath=args.label, backendId=args.backend, targetId=args.target)
+
+    }
+    model = models[args.model]
+
+    # Read image and get a 224x224 crop from a 256x256 resized
+    image = cv.imread(args.input)
+    image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
+    image = cv.resize(image, dsize=(256, 256))
+    image = image[16:240, 16:240, :]
+
+    # Inference
+    result = model.infer(image)
+
+    # Print result
+    print('label: {}'.format(result))
+

models/image_classification_mobilenet/imagenet_labels.txt

@@ -0,0 +1,1000 @@
+tench
+goldfish
+great white shark
+tiger shark
+hammerhead
+electric ray
+stingray
+cock
+hen
+ostrich
+brambling
+goldfinch
+house finch
+junco
+indigo bunting
+robin
+bulbul
+jay
+magpie
+chickadee
+water ouzel
+kite
+bald eagle
+vulture
+great grey owl
+European fire salamander
+common newt
+eft
+spotted salamander
+axolotl
+bullfrog
+tree frog
+tailed frog
+loggerhead
+leatherback turtle
+mud turtle
+terrapin
+box turtle
+banded gecko
+common iguana
+American chameleon
+whiptail
+agama
+frilled lizard
+alligator lizard
+Gila monster
+green lizard
+African chameleon
+Komodo dragon
+African crocodile
+American alligator
+triceratops
+thunder snake
+ringneck snake
+hognose snake
+green snake
+king snake
+garter snake
+water snake
+vine snake
+night snake
+boa constrictor
+rock python
+Indian cobra
+green mamba
+sea snake
+horned viper
+diamondback
+sidewinder
+trilobite
+harvestman
+scorpion
+black and gold garden spider
+barn spider
+garden spider
+black widow
+tarantula
+wolf spider
+tick
+centipede
+black grouse
+ptarmigan
+ruffed grouse
+prairie chicken
+peacock
+quail
+partridge
+African grey
+macaw
+sulphur-crested cockatoo
+lorikeet
+coucal
+bee eater
+hornbill
+hummingbird
+jacamar
+toucan
+drake
+red-breasted merganser
+goose
+black swan
+tusker
+echidna
+platypus
+wallaby
+koala
+wombat
+jellyfish
+sea anemone
+brain coral
+flatworm
+nematode
+conch
+snail
+slug
+sea slug
+chiton
+chambered nautilus
+Dungeness crab
+rock crab
+fiddler crab
+king crab
+American lobster
+spiny lobster
+crayfish
+hermit crab
+isopod
+white stork
+black stork
+spoonbill
+flamingo
+little blue heron
+American egret
+bittern
+crane
+limpkin
+European gallinule
+American coot
+bustard
+ruddy turnstone
+red-backed sandpiper
+redshank
+dowitcher
+oystercatcher
+pelican
+king penguin
+albatross
+grey whale
+killer whale
+dugong
+sea lion
+Chihuahua
+Japanese spaniel
+Maltese dog
+Pekinese
+Shih-Tzu
+Blenheim spaniel
+papillon
+toy terrier
+Rhodesian ridgeback
+Afghan hound
+basset
+beagle
+bloodhound
+bluetick
+black-and-tan coonhound
+Walker hound
+English foxhound
+redbone
+borzoi
+Irish wolfhound
+Italian greyhound
+whippet
+Ibizan hound
+Norwegian elkhound
+otterhound
+Saluki
+Scottish deerhound
+Weimaraner
+Staffordshire bullterrier
+American Staffordshire terrier
+Bedlington terrier
+Border terrier
+Kerry blue terrier
+Irish terrier
+Norfolk terrier
+Norwich terrier
+Yorkshire terrier
+wire-haired fox terrier
+Lakeland terrier
+Sealyham terrier
+Airedale
+cairn
+Australian terrier
+Dandie Dinmont
+Boston bull
+miniature schnauzer
+giant schnauzer
+standard schnauzer
+Scotch terrier
+Tibetan terrier
+silky terrier
+soft-coated wheaten terrier
+West Highland white terrier
+Lhasa
+flat-coated retriever
+curly-coated retriever
+golden retriever
+Labrador retriever
+Chesapeake Bay retriever
+German short-haired pointer
+vizsla
+English setter
+Irish setter
+Gordon setter
+Brittany spaniel
+clumber
+English springer
+Welsh springer spaniel
+cocker spaniel
+Sussex spaniel
+Irish water spaniel
+kuvasz
+schipperke
+groenendael
+malinois
+briard
+kelpie
+komondor
+Old English sheepdog
+Shetland sheepdog
+collie
+Border collie
+Bouvier des Flandres
+Rottweiler
+German shepherd
+Doberman
+miniature pinscher
+Greater Swiss Mountain dog
+Bernese mountain dog
+Appenzeller
+EntleBucher
+boxer
+bull mastiff
+Tibetan mastiff
+French bulldog
+Great Dane
+Saint Bernard
+Eskimo dog
+malamute
+Siberian husky
+dalmatian
+affenpinscher
+basenji
+pug
+Leonberg
+Newfoundland
+Great Pyrenees
+Samoyed
+Pomeranian
+chow
+keeshond
+Brabancon griffon
+Pembroke
+Cardigan
+toy poodle
+miniature poodle
+standard poodle
+Mexican hairless
+timber wolf
+white wolf
+red wolf
+coyote
+dingo
+dhole
+African hunting dog
+hyena
+red fox
+kit fox
+Arctic fox
+grey fox
+tabby
+tiger cat
+Persian cat
+Siamese cat
+Egyptian cat
+cougar
+lynx
+leopard
+snow leopard
+jaguar
+lion
+tiger
+cheetah
+brown bear
+American black bear
+ice bear
+sloth bear
+mongoose
+meerkat
+tiger beetle
+ladybug
+ground beetle
+long-horned beetle
+leaf beetle
+dung beetle
+rhinoceros beetle
+weevil
+fly
+bee
+ant
+grasshopper
+cricket
+walking stick
+cockroach
+mantis
+cicada
+leafhopper
+lacewing
+dragonfly
+damselfly
+admiral
+ringlet
+monarch
+cabbage butterfly
+sulphur butterfly
+lycaenid
+starfish
+sea urchin
+sea cucumber
+wood rabbit
+hare
+Angora
+hamster
+porcupine
+fox squirrel
+marmot
+beaver
+guinea pig
+sorrel
+zebra
+hog
+wild boar
+warthog
+hippopotamus
+ox
+water buffalo
+bison
+ram
+bighorn
+ibex
+hartebeest
+impala
+gazelle
+Arabian camel
+llama
+weasel
+mink
+polecat
+black-footed ferret
+otter
+skunk
+badger
+armadillo
+three-toed sloth
+orangutan
+gorilla
+chimpanzee
+gibbon
+siamang
+guenon
+patas
+baboon
+macaque
+langur
+colobus
+proboscis monkey
+marmoset
+capuchin
+howler monkey
+titi
+spider monkey
+squirrel monkey
+Madagascar cat
+indri
+Indian elephant
+African elephant
+lesser panda
+giant panda
+barracouta
+eel
+coho
+rock beauty
+anemone fish
+sturgeon
+gar
+lionfish
+puffer
+abacus
+abaya
+academic gown
+accordion
+acoustic guitar
+aircraft carrier
+airliner
+airship
+altar
+ambulance
+amphibian
+analog clock
+apiary
+apron
+ashcan
+assault rifle
+backpack
+bakery
+balance beam
+balloon
+ballpoint
+Band Aid
+banjo
+bannister
+barbell
+barber chair
+barbershop
+barn
+barometer
+barrel
+barrow
+baseball
+basketball
+bassinet
+bassoon
+bathing cap
+bath towel
+bathtub
+beach wagon
+beacon
+beaker
+bearskin
+beer bottle
+beer glass
+bell cote
+bib
+bicycle-built-for-two
+bikini
+binder
+binoculars
+birdhouse
+boathouse
+bobsled
+bolo tie
+bonnet
+bookcase
+bookshop
+bottlecap
+bow
+bow tie
+brass
+brassiere
+breakwater
+breastplate
+broom
+bucket
+buckle
+bulletproof vest
+bullet train
+butcher shop
+cab
+caldron
+candle
+cannon
+canoe
+can opener
+cardigan
+car mirror
+carousel
+carpenters kit
+carton
+car wheel
+cash machine
+cassette
+cassette player
+castle
+catamaran
+CD player
+cello
+cellular telephone
+chain
+chainlink fence
+chain mail
+chain saw
+chest
+chiffonier
+chime
+china cabinet
+Christmas stocking
+church
+cinema
+cleaver
+cliff dwelling
+cloak
+clog
+cocktail shaker
+coffee mug
+coffeepot
+coil
+combination lock
+computer keyboard
+confectionery
+container ship
+convertible
+corkscrew
+cornet
+cowboy boot
+cowboy hat
+cradle
+crane
+crash helmet
+crate
+crib
+Crock Pot
+croquet ball
+crutch
+cuirass
+dam
+desk
+desktop computer
+dial telephone
+diaper
+digital clock
+digital watch
+dining table
+dishrag
+dishwasher
+disk brake
+dock
+dogsled
+dome
+doormat
+drilling platform
+drum
+drumstick
+dumbbell
+Dutch oven
+electric fan
+electric guitar
+electric locomotive
+entertainment center
+envelope
+espresso maker
+face powder
+feather boa
+file
+fireboat
+fire engine
+fire screen
+flagpole
+flute
+folding chair
+football helmet
+forklift
+fountain
+fountain pen
+four-poster
+freight car
+French horn
+frying pan
+fur coat
+garbage truck
+gasmask
+gas pump
+goblet
+go-kart
+golf ball
+golfcart
+gondola
+gong
+gown
+grand piano
+greenhouse
+grille
+grocery store
+guillotine
+hair slide
+hair spray
+half track
+hammer
+hamper
+hand blower
+hand-held computer
+handkerchief
+hard disc
+harmonica
+harp
+harvester
+hatchet
+holster
+home theater
+honeycomb
+hook
+hoopskirt
+horizontal bar
+horse cart
+hourglass
+iPod
+iron
+jack-o-lantern
+jean
+jeep
+jersey
+jigsaw puzzle
+jinrikisha
+joystick
+kimono
+knee pad
+knot
+lab coat
+ladle
+lampshade
+laptop
+lawn mower
+lens cap
+letter opener
+library
+lifeboat
+lighter
+limousine
+liner
+lipstick
+Loafer
+lotion
+loudspeaker
+loupe
+lumbermill
+magnetic compass
+mailbag
+mailbox
+maillot
+maillot
+manhole cover
+maraca
+marimba
+mask
+matchstick
+maypole
+maze
+measuring cup
+medicine chest
+megalith
+microphone
+microwave
+military uniform
+milk can
+minibus
+miniskirt
+minivan
+missile
+mitten
+mixing bowl
+mobile home
+Model T
+modem
+monastery
+monitor
+moped
+mortar
+mortarboard
+mosque
+mosquito net
+motor scooter
+mountain bike
+mountain tent
+mouse
+mousetrap
+moving van
+muzzle
+nail
+neck brace
+necklace
+nipple
+notebook
+obelisk
+oboe
+ocarina
+odometer
+oil filter
+organ
+oscilloscope
+overskirt
+oxcart
+oxygen mask
+packet
+paddle
+paddlewheel
+padlock
+paintbrush
+pajama
+palace
+panpipe
+paper towel
+parachute
+parallel bars
+park bench
+parking meter
+passenger car
+patio
+pay-phone
+pedestal
+pencil box
+pencil sharpener
+perfume
+Petri dish
+photocopier
+pick
+pickelhaube
+picket fence
+pickup
+pier
+piggy bank
+pill bottle
+pillow
+ping-pong ball
+pinwheel
+pirate
+pitcher
+plane
+planetarium
+plastic bag
+plate rack
+plow
+plunger
+Polaroid camera
+pole
+police van
+poncho
+pool table
+pop bottle
+pot
+potters wheel
+power drill
+prayer rug
+printer
+prison
+projectile
+projector
+puck
+punching bag
+purse
+quill
+quilt
+racer
+racket
+radiator
+radio
+radio telescope
+rain barrel
+recreational vehicle
+reel
+reflex camera
+refrigerator
+remote control
+restaurant
+revolver
+rifle
+rocking chair
+rotisserie
+rubber eraser
+rugby ball
+rule
+running shoe
+safe
+safety pin
+saltshaker
+sandal
+sarong
+sax
+scabbard
+scale
+school bus
+schooner
+scoreboard
+screen
+screw
+screwdriver
+seat belt
+sewing machine
+shield
+shoe shop
+shoji
+shopping basket
+shopping cart
+shovel
+shower cap
+shower curtain
+ski
+ski mask
+sleeping bag
+slide rule
+sliding door
+slot
+snorkel
+snowmobile
+snowplow
+soap dispenser
+soccer ball
+sock
+solar dish
+sombrero
+soup bowl
+space bar
+space heater
+space shuttle
+spatula
+speedboat
+spider web
+spindle
+sports car
+spotlight
+stage
+steam locomotive
+steel arch bridge
+steel drum
+stethoscope
+stole
+stone wall
+stopwatch
+stove
+strainer
+streetcar
+stretcher
+studio couch
+stupa
+submarine
+suit
+sundial
+sunglass
+sunglasses
+sunscreen
+suspension bridge
+swab
+sweatshirt
+swimming trunks
+swing
+switch
+syringe
+table lamp
+tank
+tape player
+teapot
+teddy
+television
+tennis ball
+thatch
+theater curtain
+thimble
+thresher
+throne
+tile roof
+toaster
+tobacco shop
+toilet seat
+torch
+totem pole
+tow truck
+toyshop
+tractor
+trailer truck
+tray
+trench coat
+tricycle
+trimaran
+tripod
+triumphal arch
+trolleybus
+trombone
+tub
+turnstile
+typewriter keyboard
+umbrella
+unicycle
+upright
+vacuum
+vase
+vault
+velvet
+vending machine
+vestment
+viaduct
+violin
+volleyball
+waffle iron
+wall clock
+wallet
+wardrobe
+warplane
+washbasin
+washer
+water bottle
+water jug
+water tower
+whiskey jug
+whistle
+wig
+window screen
+window shade
+Windsor tie
+wine bottle
+wing
+wok
+wooden spoon
+wool
+worm fence
+wreck
+yawl
+yurt
+web site
+comic book
+crossword puzzle
+street sign
+traffic light
+book jacket
+menu
+plate
+guacamole
+consomme
+hot pot
+trifle
+ice cream
+ice lolly
+French loaf
+bagel
+pretzel
+cheeseburger
+hotdog
+mashed potato
+head cabbage
+broccoli
+cauliflower
+zucchini
+spaghetti squash
+acorn squash
+butternut squash
+cucumber
+artichoke
+bell pepper
+cardoon
+mushroom
+Granny Smith
+strawberry
+orange
+lemon
+fig
+pineapple
+banana
+jackfruit
+custard apple
+pomegranate
+hay
+carbonara
+chocolate sauce
+dough
+meat loaf
+pizza
+potpie
+burrito
+red wine
+espresso
+cup
+eggnog
+alp
+bubble
+cliff
+coral reef
+geyser
+lakeside
+promontory
+sandbar
+seashore
+valley
+volcano
+ballplayer
+groom
+scuba diver
+rapeseed
+daisy
+yellow ladys slipper
+corn
+acorn
+hip
+buckeye
+coral fungus
+agaric
+gyromitra
+stinkhorn
+earthstar
+hen-of-the-woods
+bolete
+ear
+toilet tissue

models/image_classification_mobilenet/mobilenet_v1.py

@@ -0,0 +1,65 @@
+import numpy as np
+import cv2 as cv
+
+class MobileNetV1:
+    def __init__(self, modelPath, labelPath, backendId=0, targetId=0):
+        self.model_path = modelPath
+        self.label_path = labelPath
+        self.backend_id = backendId
+        self.target_id = targetId
+
+        self.model = cv.dnn.readNet(self.model_path)
+        self.model.setPreferableBackend(self.backend_id)
+        self.model.setPreferableTarget(self.target_id)
+
+        self.input_names = ''
+        self.output_names = ''
+        self.input_size = [224, 224]
+        self.mean = [103.94,116.78,123.68]
+        self.scale = 0.017
+
+        # load labels
+        self.labels = self._load_labels()
+
+    def _load_labels(self):
+        labels = []
+        with open(self.label_path, 'r') as f:
+            for line in f:
+                labels.append(line.strip())
+        return labels
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackend(self, backendId):
+        self.backend_id = backendId
+        self.model.setPreferableBackend(self.backend_id)
+
+    def setTarget(self, targetId):
+        self.target_id = targetId
+        self.model.setPreferableTarget(self.target_id)
+
+    def _preprocess(self, image):
+        return cv.dnn.blobFromImage(image, scalefactor=self.scale, size=self.input_size, mean=self.mean)
+
+    def infer(self, image):
+        # Preprocess
+        input_blob = self._preprocess(image)
+
+        # Forward
+        self.model.setInput(input_blob, self.input_names)
+        output_blob = self.model.forward(self.output_names)
+
+        # Postprocess
+        results = self._postprocess(output_blob)
+
+        return results
+
+    def _postprocess(self, output_blob):
+        predicted_labels = []
+        for o in output_blob:
+            class_id = np.argmax(o)
+            predicted_labels.append(self.labels[class_id])
+        return predicted_labels
+

models/image_classification_mobilenet/mobilenet_v2.py

@@ -0,0 +1,65 @@
+import numpy as np
+import cv2 as cv
+
+class MobileNetV2:
+    def __init__(self, modelPath, labelPath, backendId=0, targetId=0):
+        self.model_path = modelPath
+        self.label_path = labelPath
+        self.backend_id = backendId
+        self.target_id = targetId
+
+        self.model = cv.dnn.readNet(self.model_path)
+        self.model.setPreferableBackend(self.backend_id)
+        self.model.setPreferableTarget(self.target_id)
+
+        self.input_names = ''
+        self.output_names = ''
+        self.input_size = [224, 224]
+        self.mean = [103.94,116.78,123.68]
+        self.scale = 0.017
+
+        # load labels
+        self.labels = self._load_labels()
+
+    def _load_labels(self):
+        labels = []
+        with open(self.label_path, 'r') as f:
+            for line in f:
+                labels.append(line.strip())
+        return labels
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def setBackend(self, backendId):
+        self.backend_id = backendId
+        self.model.setPreferableBackend(self.backend_id)
+
+    def setTarget(self, targetId):
+        self.target_id = targetId
+        self.model.setPreferableTarget(self.target_id)
+
+    def _preprocess(self, image):
+        return cv.dnn.blobFromImage(image, scalefactor=self.scale, size=self.input_size, mean=self.mean)
+
+    def infer(self, image):
+        # Preprocess
+        input_blob = self._preprocess(image)
+
+        # Forward
+        self.model.setInput(input_blob, self.input_names)
+        output_blob = self.model.forward(self.output_names)
+
+        # Postprocess
+        results = self._postprocess(output_blob)
+
+        return results
+
+    def _postprocess(self, output_blob):
+        predicted_labels = []
+        for o in output_blob:
+            class_id = np.argmax(o)
+            predicted_labels.append(self.labels[class_id])
+        return predicted_labels
+

tools/quantize/quantize.py

@@ -14,7 +14,7 @@ from onnx import version_converter
 import onnxruntime
 from onnxruntime.quantization import quantize_static, CalibrationDataReader, QuantType
 
-from transform import Compose, Resize, ColorConvert
+from transform import Compose, Resize, CenterCrop, Normalize, ColorConvert
 
 class DataReader(CalibrationDataReader):
     def __init__(self, model_path, image_dir, transforms):
@@ -30,13 +30,14 @@ class DataReader(CalibrationDataReader):
     def get_calibration_data(self, image_dir):
         blobs = []
         for image_name in os.listdir(image_dir):
-            if not image_name.endswith('jpg'):
+            image_name_suffix = image_name.split('.')[-1].lower()
+            if image_name_suffix == 'jpg' or image_name_suffix != 'jpeg':
                 continue
             img = cv.imread(os.path.join(image_dir, image_name))
             img = self.transforms(img)
             blob = cv.dnn.blobFromImage(img)
             blobs.append(blob)
-        return blobs
+        return blobs[:100]
 
 class Quantize:
     def __init__(self, model_path, calibration_image_dir, transforms=Compose(), per_channel=False, act_type='int8', wt_type='int8'):
@@ -90,6 +91,12 @@ models=dict(
     ppresnet50=Quantize(model_path='../../models/image_classification_ppresnet/image_classification_ppresnet50_2022jan.onnx',
                         calibration_image_dir='../../benchmark/data/image_classification',
                         transforms=Compose([Resize(size=(224, 224))])),
+    mobilenetv1=Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv1_2022apr.onnx',
+                        calibration_image_dir='../../benchmark/data/image_classification',
+                        transforms=Compose([Resize(size=(256, 256)), CenterCrop(size=(224, 224)), Normalize(mean=[103.94, 116.78, 123.68], std=[0.017, 0.017, 0.017])])),
+    mobilenetv2=Quantize(model_path='../../models/image_classification_mobilenet/image_classification_mobilenetv2_2022apr.onnx',
+                        calibration_image_dir='../../benchmark/data/image_classification',
+                        transforms=Compose([Resize(size=(256, 256)), CenterCrop(size=(224, 224)), Normalize(mean=[103.94, 116.78, 123.68], std=[0.017, 0.017, 0.017])])),
     # TBD: DaSiamRPN
     youtureid=Quantize(model_path='../../models/person_reid_youtureid/person_reid_youtu_2021nov.onnx',
                        calibration_image_dir='../../benchmark/data/person_reid',

tools/quantize/transform.py

@@ -4,6 +4,7 @@
 # Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
 # Third party copyrights are property of their respective owners.
 
+import collections
 import numpy as numpy
 import cv2 as cv
 
@@ -24,9 +25,35 @@ class Resize:
     def __call__(self, img):
         return cv.resize(img, self.size)
 
+class CenterCrop:
+    def __init__(self, size):
+        self.size = size # w, h
+
+    def __call__(self, img):
+        h, w, _ = img.shape
+        ws = int(w / 2 - self.size[0] / 2)
+        hs = int(h / 2 - self.size[1] / 2)
+        return img[hs:hs+self.size[1], ws:ws+self.size[0], :]
+
+class Normalize:
+    def __init__(self, mean=None, std=None):
+        self.mean = mean
+        self.std = std
+
+    def __call__(self, img):
+        if self.mean is not None:
+            img[:, :, 0] = img[:, :, 0] - self.mean[0]
+            img[:, :, 1] = img[:, :, 1] - self.mean[1]
+            img[:, :, 2] = img[:, :, 2] - self.mean[2]
+        if self.std is not None:
+            img[:, :, 0] = img[:, :, 0] / self.std[0]
+            img[:, :, 1] = img[:, :, 1] / self.std[1]
+            img[:, :, 2] = img[:, :, 2] / self.std[2]
+        return img
+
 class ColorConvert:
     def __init__(self, ctype):
         self.ctype = ctype
 
     def __call__(self, img):
-        return cv.cvtColor(img, self.ctype)
+        return cv.cvtColor(img, self.ctype)