AI Powered Image Recognition in .NET with ML.NET and ONNX Runtime
MLNET
2 Articles
Table of Contents
What we gonna do?
In this blog, we will explore how to build an AI-powered image recognition application using ML.NET and ONNX Runtime.
Why we gonna do?
ONNX Runtime is a cross-platform inference and training machine-learning accelerator. This means we can use models trained from other available frameworks like TensorFlow, PyTorch, and Scikit-learn in our .NET applications.
Image recognition using machine learning allows computers to automatically "see" and understand images — just like humans, but at scale and with consistency. Machine learning turns raw images into smart decisions — fast, accurate, and at scale.
How we gonna do?
The steps to do image recognition are as follows:
- Download the resnet50-v2-7.onnx ONNX model to our machine.
- Install Microsoft.ML.OnnxRuntime And SixLabors.ImageSharp nuget package.
-
Read the image. Note, we're specifically reading the Rgb24 type so we can efficiently preprocess the
image in a later step.
var imageFilePath = "test-image.webp"; using Image<Rgb24> image = Image.Load<Rgb24>(imageFilePath); -
Next, we will resize the image to the appropriate size that the model is expecting; 224 pixels by 224 pixels.
Note, we're doing a centered crop resize to preserve aspect ratio.
using Stream imageStream = new MemoryStream(); image.Mutate(x => { x.Resize(new ResizeOptions { Size = new Size(224, 224), Mode = ResizeMode.Crop }); }); image.Save(imageStream, image.DetectEncoder(imageFilePath)); -
Next, we will preprocess the image according to the
requirements of the model:
Here, we're creating a Tensor of the required size (batch-size, channels, height, width), accessing the pixel values, preprocessing them and finally assigning them to the tensor at the appropriate indicies.// We use DenseTensor for multi-dimensional access to populate the image data Tensor<float> input = new DenseTensor<float>(new[] { 1, 3, 224, 224 }); var mean = new[] { 0.485f, 0.456f, 0.406f }; var stddev = new[] { 0.229f, 0.224f, 0.225f }; image.ProcessPixelRows(accessor => { for (int y = 0; y < accessor.Height; y++) { Span<Rgb24> pixelSpan = accessor.GetRowSpan(y); for (int x = 0; x < accessor.Width; x++) { input[0, 0, y, x] = ((pixelSpan[x].R / 255f) - mean[0]) / stddev[0]; input[0, 1, y, x] = ((pixelSpan[x].G / 255f) - mean[1]) / stddev[1]; input[0, 2, y, x] = ((pixelSpan[x].B / 255f) - mean[2]) / stddev[2]; } } }); -
Next, we will create the inputs to the model. To check the input node names for an ONNX model, you can use
Netron to visualise the model and see input/output names.
In this case, this model has data as the input node name.
var inputs = new List<NamedOnnxValue> { NamedOnnxValue.CreateFromTensor("data", input) }; -
Next, we will create an inference session and run the input through it:
// Run inference var modelFilePath = "resnet50-v2-7.onnx"; using var session = new InferenceSession(modelFilePath); using IDisposableReadOnlyCollection<DisposableNamedOnnxValue> results = session.Run(inputs); -
Next, we will need to postprocess the output to get the softmax vector, as this is not handled by the model itself:
Other models may apply a Softmax node before the output, in which case you won't need this step. Again, you can use Netron to see the model outputs.// Postprocess to get softmax vector IEnumerable<float> output = results.First().AsEnumerable<float>(); float sum = output.Sum(x => (float)Math.Exp(x)); IEnumerable<float> softmax = output.Select(x => (float)Math.Exp(x) / sum); -
Include LabelMappings as we need items-center for results mapping.
public class LabelMap { public static readonly string[] Labels = new[] {"tench", "goldfish", "great white shark", "tiger shark", "hammerhead shark", "electric ray", "stingray", "cock", "hen", "ostrich", "brambling", "goldfinch", "house finch", "junco", "indigo bunting", "American robin", "bulbul", "jay", "magpie", "chickadee", "American dipper", "kite", "bald eagle", "vulture", "great grey owl", "fire salamander", "smooth newt", "newt", "spotted salamander", "axolotl", "American bullfrog", "tree frog", "tailed frog", "loggerhead sea turtle", "leatherback sea turtle", "mud turtle", "terrapin", "box turtle", "banded gecko", "green iguana", "Carolina anole", "desert grassland whiptail lizard", "agama", "frilled-necked lizard", "alligator lizard", "Gila monster", "European green lizard", "chameleon", "Komodo dragon", "Nile crocodile", "American alligator", "triceratops", "worm snake", "ring-necked snake", "eastern hog-nosed snake", "smooth green snake", "kingsnake", "garter snake", "water snake", "vine snake", "night snake", "boa constrictor", "African rock python", "Indian cobra", "green mamba", "sea snake", "Saharan horned viper", "eastern diamondback rattlesnake", "sidewinder", "trilobite", "harvestman", "scorpion", "yellow garden spider", "barn spider", "European garden spider", "southern black widow", "tarantula", "wolf spider", "tick", "centipede", "black grouse", "ptarmigan", "ruffed grouse", "prairie grouse", "peacock", "quail", "partridge", "grey parrot", "macaw", "sulphur-crested cockatoo", "lorikeet", "coucal", "bee eater", "hornbill", "hummingbird", "jacamar", "toucan", "duck", "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", "red king crab", "American lobster", "spiny lobster", "crayfish", "hermit crab", "isopod", "white stork", "black stork", "spoonbill", "flamingo", "little blue heron", "great egret", "bittern", "crane (bird)", "limpkin", "common gallinule", "American coot", "bustard", "ruddy turnstone", "dunlin", "common redshank", "dowitcher", "oystercatcher", "pelican", "king penguin", "albatross", "grey whale", "killer whale", "dugong", "sea lion", "Chihuahua", "Japanese Chin", "Maltese", "Pekingese", "Shih Tzu", "King Charles Spaniel", "Papillon", "toy terrier", "Rhodesian Ridgeback", "Afghan Hound", "Basset Hound", "Beagle", "Bloodhound", "Bluetick Coonhound", "Black and Tan Coonhound", "Treeing Walker Coonhound", "English foxhound", "Redbone Coonhound", "borzoi", "Irish Wolfhound", "Italian Greyhound", "Whippet", "Ibizan Hound", "Norwegian Elkhound", "Otterhound", "Saluki", "Scottish Deerhound", "Weimaraner", "Staffordshire Bull Terrier", "American Staffordshire Terrier", "Bedlington Terrier", "Border Terrier", "Kerry Blue Terrier", "Irish Terrier", "Norfolk Terrier", "Norwich Terrier", "Yorkshire Terrier", "Wire Fox Terrier", "Lakeland Terrier", "Sealyham Terrier", "Airedale Terrier", "Cairn Terrier", "Australian Terrier", "Dandie Dinmont Terrier", "Boston Terrier", "Miniature Schnauzer", "Giant Schnauzer", "Standard Schnauzer", "Scottish Terrier", "Tibetan Terrier", "Australian Silky Terrier", "Soft-coated Wheaten Terrier", "West Highland White Terrier", "Lhasa Apso", "Flat-Coated Retriever", "Curly-coated Retriever", "Golden Retriever", "Labrador Retriever", "Chesapeake Bay Retriever", "German Shorthaired Pointer", "Vizsla", "English Setter", "Irish Setter", "Gordon Setter", "Brittany", "Clumber Spaniel", "English Springer Spaniel", "Welsh Springer Spaniel", "Cocker Spaniels", "Sussex Spaniel", "Irish Water Spaniel", "Kuvasz", "Schipperke", "Groenendael", "Malinois", "Briard", "Australian Kelpie", "Komondor", "Old English Sheepdog", "Shetland Sheepdog", "collie", "Border Collie", "Bouvier des Flandres", "Rottweiler", "German Shepherd Dog", "Dobermann", "Miniature Pinscher", "Greater Swiss Mountain Dog", "Bernese Mountain Dog", "Appenzeller Sennenhund", "Entlebucher Sennenhund", "Boxer", "Bullmastiff", "Tibetan Mastiff", "French Bulldog", "Great Dane", "St. Bernard", "husky", "Alaskan Malamute", "Siberian Husky", "Dalmatian", "Affenpinscher", "Basenji", "pug", "Leonberger", "Newfoundland", "Pyrenean Mountain Dog", "Samoyed", "Pomeranian", "Chow Chow", "Keeshond", "Griffon Bruxellois", "Pembroke Welsh Corgi", "Cardigan Welsh Corgi", "Toy Poodle", "Miniature Poodle", "Standard Poodle", "Mexican hairless dog", "grey wolf", "Alaskan tundra wolf", "red wolf", "coyote", "dingo", "dhole", "African wild dog", "hyena", "red fox", "kit fox", "Arctic fox", "grey fox", "tabby cat", "tiger cat", "Persian cat", "Siamese cat", "Egyptian Mau", "cougar", "lynx", "leopard", "snow leopard", "jaguar", "lion", "tiger", "cheetah", "brown bear", "American black bear", "polar bear", "sloth bear", "mongoose", "meerkat", "tiger beetle", "ladybug", "ground beetle", "longhorn beetle", "leaf beetle", "dung beetle", "rhinoceros beetle", "weevil", "fly", "bee", "ant", "grasshopper", "cricket", "stick insect", "cockroach", "mantis", "cicada", "leafhopper", "lacewing", "dragonfly", "damselfly", "red admiral", "ringlet", "monarch butterfly", "small white", "sulphur butterfly", "gossamer-winged butterfly", "starfish", "sea urchin", "sea cucumber", "cottontail rabbit", "hare", "Angora rabbit", "hamster", "porcupine", "fox squirrel", "marmot", "beaver", "guinea pig", "common sorrel", "zebra", "pig", "wild boar", "warthog", "hippopotamus", "ox", "water buffalo", "bison", "ram", "bighorn sheep", "Alpine ibex", "hartebeest", "impala", "gazelle", "dromedary", "llama", "weasel", "mink", "European polecat", "black-footed ferret", "otter", "skunk", "badger", "armadillo", "three-toed sloth", "orangutan", "gorilla", "chimpanzee", "gibbon", "siamang", "guenon", "patas monkey", "baboon", "macaque", "langur", "black-and-white colobus", "proboscis monkey", "marmoset", "white-headed capuchin", "howler monkey", "titi", "Geoffroy's spider monkey", "common squirrel monkey", "ring-tailed lemur", "indri", "Asian elephant", "African bush elephant", "red panda", "giant panda", "snoek", "eel", "coho salmon", "rock beauty", "clownfish", "sturgeon", "garfish", "lionfish", "pufferfish", "abacus", "abaya", "academic gown", "accordion", "acoustic guitar", "aircraft carrier", "airliner", "airship", "altar", "ambulance", "amphibious vehicle", "analog clock", "apiary", "apron", "waste container", "assault rifle", "backpack", "bakery", "balance beam", "balloon", "ballpoint pen", "Band-Aid", "banjo", "baluster", "barbell", "barber chair", "barbershop", "barn", "barometer", "barrel", "wheelbarrow", "baseball", "basketball", "bassinet", "bassoon", "swimming cap", "bath towel", "bathtub", "station wagon", "lighthouse", "beaker", "military cap", "beer bottle", "beer glass", "bell-cot", "bib", "tandem bicycle", "bikini", "ring binder", "binoculars", "birdhouse", "boathouse", "bobsleigh", "bolo tie", "poke bonnet", "bookcase", "bookstore", "bottle cap", "bow", "bow tie", "brass", "bra", "breakwater", "breastplate", "broom", "bucket", "buckle", "bulletproof vest", "high-speed train", "butcher shop", "taxicab", "cauldron", "candle", "cannon", "canoe", "can opener", "cardigan", "car mirror", "carousel", "tool kit", "carton", "car wheel", "automated teller machine", "cassette", "cassette player", "castle", "catamaran", "CD player", "cello", "mobile phone", "chain", "chain-link fence", "chain mail", "chainsaw", "chest", "chiffonier", "chime", "china cabinet", "Christmas stocking", "church", "movie theater", "cleaver", "cliff dwelling", "cloak", "clogs", "cocktail shaker", "coffee mug", "coffeemaker", "coil", "combination lock", "computer keyboard", "confectionery store", "container ship", "convertible", "corkscrew", "cornet", "cowboy boot", "cowboy hat", "cradle", "crane (machine)", "crash helmet", "crate", "infant bed", "Crock Pot", "croquet ball", "crutch", "cuirass", "dam", "desk", "desktop computer", "rotary dial telephone", "diaper", "digital clock", "digital watch", "dining table", "dishcloth", "dishwasher", "disc brake", "dock", "dog sled", "dome", "doormat", "drilling rig", "drum", "drumstick", "dumbbell", "Dutch oven", "electric fan", "electric guitar", "electric locomotive", "entertainment center", "envelope", "espresso machine", "face powder", "feather boa", "filing cabinet", "fireboat", "fire engine", "fire screen sheet", "flagpole", "flute", "folding chair", "football helmet", "forklift", "fountain", "fountain pen", "four-poster bed", "freight car", "French horn", "frying pan", "fur coat", "garbage truck", "gas mask", "gas pump", "goblet", "go-kart", "golf ball", "golf cart", "gondola", "gong", "gown", "grand piano", "greenhouse", "grille", "grocery store", "guillotine", "barrette", "hair spray", "half-track", "hammer", "hamper", "hair dryer", "hand-held computer", "handkerchief", "hard disk drive", "harmonica", "harp", "harvester", "hatchet", "holster", "home theater", "honeycomb", "hook", "hoop skirt", "horizontal bar", "horse-drawn vehicle", "hourglass", "iPod", "clothes iron", "jack-o'-lantern", "jeans", "jeep", "T-shirt", "jigsaw puzzle", "pulled rickshaw", "joystick", "kimono", "knee pad", "knot", "lab coat", "ladle", "lampshade", "laptop computer", "lawn mower", "lens cap", "paper knife", "library", "lifeboat", "lighter", "limousine", "ocean liner", "lipstick", "slip-on shoe", "lotion", "speaker", "loupe", "sawmill", "magnetic compass", "mail bag", "mailbox", "tights", "tank suit", "manhole cover", "maraca", "marimba", "mask", "match", "maypole", "maze", "measuring cup", "medicine chest", "megalith", "microphone", "microwave oven", "military uniform", "milk can", "minibus", "miniskirt", "minivan", "missile", "mitten", "mixing bowl", "mobile home", "Model T", "modem", "monastery", "monitor", "moped", "mortar", "square academic cap", "mosque", "mosquito net", "scooter", "mountain bike", "tent", "computer mouse", "mousetrap", "moving van", "muzzle", "nail", "neck brace", "necklace", "nipple", "notebook computer", "obelisk", "oboe", "ocarina", "odometer", "oil filter", "organ", "oscilloscope", "overskirt", "bullock cart", "oxygen mask", "packet", "paddle", "paddle wheel", "padlock", "paintbrush", "pajamas", "palace", "pan flute", "paper towel", "parachute", "parallel bars", "park bench", "parking meter", "passenger car", "patio", "payphone", "pedestal", "pencil case", "pencil sharpener", "perfume", "Petri dish", "photocopier", "plectrum", "Pickelhaube", "picket fence", "pickup truck", "pier", "piggy bank", "pill bottle", "pillow", "ping-pong ball", "pinwheel", "pirate ship", "pitcher", "hand plane", "planetarium", "plastic bag", "plate rack", "plow", "plunger", "Polaroid camera", "pole", "police van", "poncho", "billiard table", "soda bottle", "pot", "potter's wheel", "power drill", "prayer rug", "printer", "prison", "projectile", "projector", "hockey puck", "punching bag", "purse", "quill", "quilt", "race car", "racket", "radiator", "radio", "radio telescope", "rain barrel", "recreational vehicle", "reel", "reflex camera", "refrigerator", "remote control", "restaurant", "revolver", "rifle", "rocking chair", "rotisserie", "eraser", "rugby ball", "ruler", "running shoe", "safe", "safety pin", "salt shaker", "sandal", "sarong", "saxophone", "scabbard", "weighing scale", "school bus", "schooner", "scoreboard", "CRT screen", "screw", "screwdriver", "seat belt", "sewing machine", "shield", "shoe store", "shoji", "shopping basket", "shopping cart", "shovel", "shower cap", "shower curtain", "ski", "ski mask", "sleeping bag", "slide rule", "sliding door", "slot machine", "snorkel", "snowmobile", "snowplow", "soap dispenser", "soccer ball", "sock", "solar thermal collector", "sombrero", "soup bowl", "space bar", "space heater", "space shuttle", "spatula", "motorboat", "spider web", "spindle", "sports car", "spotlight", "stage", "steam locomotive", "through arch bridge", "steel drum", "stethoscope", "scarf", "stone wall", "stopwatch", "stove", "strainer", "tram", "stretcher", "couch", "stupa", "submarine", "suit", "sundial", "sunglass", "sunglasses", "sunscreen", "suspension bridge", "mop", "sweatshirt", "swimsuit", "swing", "switch", "syringe", "table lamp", "tank", "tape player", "teapot", "teddy bear", "television", "tennis ball", "thatched roof", "front curtain", "thimble", "threshing machine", "throne", "tile roof", "toaster", "tobacco shop", "toilet seat", "torch", "totem pole", "tow truck", "toy store", "tractor", "semi-trailer truck", "tray", "trench coat", "tricycle", "trimaran", "tripod", "triumphal arch", "trolleybus", "trombone", "tub", "turnstile", "typewriter keyboard", "umbrella", "unicycle", "upright piano", "vacuum cleaner", "vase", "vault", "velvet", "vending machine", "vestment", "viaduct", "violin", "volleyball", "waffle iron", "wall clock", "wallet", "wardrobe", "military aircraft", "sink", "washing machine", "water bottle", "water jug", "water tower", "whiskey jug", "whistle", "wig", "window screen", "window shade", "Windsor tie", "wine bottle", "wing", "wok", "wooden spoon", "wool", "split-rail fence", "shipwreck", "yawl", "yurt", "website", "comic book", "crossword", "traffic sign", "traffic light", "dust jacket", "menu", "plate", "guacamole", "consomme", "hot pot", "trifle", "ice cream", "ice pop", "baguette", "bagel", "pretzel", "cheeseburger", "hot dog", "mashed potato", "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 syrup", "dough", "meatloaf", "pizza", "pot pie", "burrito", "red wine", "espresso", "cup", "eggnog", "alp", "bubble", "cliff", "coral reef", "geyser", "lakeshore", "promontory", "shoal", "seashore", "valley", "volcano", "baseball player", "bridegroom", "scuba diver", "rapeseed", "daisy", "yellow lady's slipper", "corn", "acorn", "rose hip", "horse chestnut seed", "coral fungus", "agaric", "gyromitra", "stinkhorn mushroom", "earth star", "hen-of-the-woods", "bolete", "ear", "toilet paper"}; } -
Next, we will extract the top 10 class predictions:
internal class Prediction { public string Label { get; set; } public float Confidence { get; set; } } // Extract top 10 predicted classes IEnumerable<Prediction> top10 = softmax.Select((x, i) => new Prediction { Label = LabelMap.Labels[i], Confidence = x }) .OrderByDescending(x => x.Confidence) .Take(10); -
Next, we will print the top 10 results to the console:
Console.WriteLine("Top 10 predictions for ResNet50 v2..."); Console.WriteLine("--------------------------------------------------------------"); foreach (var t in top10) { Console.WriteLine($"Label: {t.Label}, Confidence: {t.Confidence}"); } -
Now when I give the following image, I get the following output.
Top 10 predictions for ResNet50 v2... -------------------------------------------------------------- Label: Persian cat, Confidence: 0.98284155 Label: Angora rabbit, Confidence: 0.004810248 Label: lynx, Confidence: 0.0028022456 Label: bow tie, Confidence: 0.00055058405 Label: ping-pong ball, Confidence: 0.00049295166 Label: tabby cat, Confidence: 0.000260345 Label: Arctic fox, Confidence: 0.00020933828 Label: Japanese Chin, Confidence: 0.0002078693 Label: bib, Confidence: 0.00019297554 Label: feather boa, Confidence: 0.00018571848
Summary
In this article, we have learned how to use ML.NET and ONNX Runtime to perform image recognition in .NET applications. We have seen how to load a pre-trained model, preprocess input images, and make predictions using the model. We also explored how to extract the top 10 class predictions and display them in a user-friendly format. With this knowledge, you can now integrate image recognition capabilities into your own .NET applications. The code snippets provided in this article can be used as a starting point for your own image recognition projects. You can further enhance the model's performance by fine-tuning it with your own dataset or exploring other pre-trained models available in the ONNX Model Zoo.