File size: 9,916 Bytes
520f98d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | <!doctype html>
<meta charset="utf-8" />
<title>MangaOCR WebGPU comparison harness</title>
<style>
body { background: #111; color: #eee; font: 14px/1.45 ui-monospace, monospace; margin: 24px; }
pre { white-space: pre-wrap; }
</style>
<h1>MangaOCR WebGPU comparison harness</h1>
<pre id="log">Starting…</pre>
<script type="module">
import * as ort from "./.cache/ort/ort.webgpu.min.mjs";
const parameters = new URLSearchParams(location.search);
const output = document.querySelector("#log");
const lines = [];
const log = (message) => {
lines.push(`${new Date().toISOString()} ${message}`);
output.textContent = lines.join("\n");
console.log(message);
};
const timed = async (operation) => {
const started = performance.now();
const value = await operation();
return [value, performance.now() - started];
};
window.addEventListener("error", (event) => log(`FAIL ${event.error?.stack ?? event.message}`));
window.addEventListener("unhandledrejection", (event) => log(`FAIL ${event.reason?.stack ?? event.reason}`));
if (!navigator.gpu) throw new Error("WebGPU is unavailable");
log(`navigator.gpu=true secure=${window.isSecureContext}`);
const session = async (path) => {
const bytes = new Uint8Array(await (await fetch(path)).arrayBuffer());
return ort.InferenceSession.create(bytes, {
executionProviders: ["webgpu"],
logSeverityLevel: 3,
});
};
let value;
let elapsed;
[value, elapsed] = await timed(() => session("./.cache/mangaocr/encoder_model.onnx"));
const encoder = value;
log(`PASS encoder session creation (${elapsed.toFixed(1)} ms)`);
[value, elapsed] = await timed(() => session("./.cache/mangaocr/decoder_model.onnx"));
const decoder = value;
log(`PASS decoder session creation (${elapsed.toFixed(1)} ms)`);
const vocab = (await (await fetch("./.cache/mangaocr/vocab.txt")).text()).split(/\r?\n/g);
log(`models ready vocab=${vocab.length}`);
const loadImage = (source) => new Promise((resolve, reject) => {
const image = new Image();
image.onload = () => resolve(image);
image.onerror = reject;
image.src = source;
});
const parseCrop = (image) => {
const raw = parameters.get("crop");
if (!raw) return [0, 0, image.naturalWidth, image.naturalHeight];
return raw.split(",").map(Number);
};
const cropImageData = (image) => {
const [x, y, width, height] = parseCrop(image);
const canvas = document.createElement("canvas");
canvas.width = width;
canvas.height = height;
const context = canvas.getContext("2d", { willReadFrequently: true });
context.drawImage(image, x, y, width, height, 0, 0, width, height);
return context.getImageData(0, 0, width, height);
};
const clampByte = (number) => Math.max(0, Math.min(255, number));
const grayscale = (image) => {
const result = new Uint8ClampedArray(image.width * image.height);
for (let source = 0, pixel = 0; source < image.data.length; source += 4, pixel += 1) {
const r = image.data[source] ?? 0;
const g = image.data[source + 1] ?? 0;
const b = image.data[source + 2] ?? 0;
result[pixel] = ((b * 19595 + g * 38470 + r * 7471 + 0x8000) >> 16) & 0xff;
}
return result;
};
const coefficients = (inputSize, outputSize) => {
const scale = inputSize / outputSize;
const support = scale >= 1 ? scale : 1;
const maximum = Math.ceil(support) * 2 + 1;
const result = [];
for (let outputIndex = 0; outputIndex < outputSize; outputIndex += 1) {
const center = (outputIndex + 0.5) * scale;
const inverse = scale >= 1 ? 1 / scale : 1;
const start = Math.max(0, Math.min(inputSize, Math.trunc(center - support + 0.5)));
const end = Math.min(Math.trunc(center + support + 0.5), inputSize);
const size = Math.max(0, Math.min(maximum, end - start));
const weights = [];
let total = 0;
for (let index = 0; index < size; index += 1) {
const weight = Math.max(0, 1 - Math.abs((index + start - center + 0.5) * inverse));
weights.push(weight);
total += weight;
}
result.push({
start,
size,
weights: weights.map((weight) => Math.trunc(0.5 + weight / total * 2 ** 22)),
});
}
return result;
};
const preprocess = (image) => {
const source = grayscale(image);
const horizontal = coefficients(image.width, 224);
const vertical = coefficients(image.height, 224);
const temporary = new Uint8ClampedArray(image.height * 224);
for (let y = 0; y < image.height; y += 1) {
for (let x = 0; x < 224; x += 1) {
const item = horizontal[x];
let sum = 1 << 21;
for (let index = 0; index < item.size; index += 1) {
sum += (source[y * image.width + item.start + index] ?? 0) * (item.weights[index] ?? 0);
}
temporary[y * 224 + x] = clampByte(Math.trunc(sum / 2 ** 22));
}
}
const resized = new Uint8ClampedArray(224 * 224);
for (let y = 0; y < 224; y += 1) {
const item = vertical[y];
for (let x = 0; x < 224; x += 1) {
let sum = 1 << 21;
for (let index = 0; index < item.size; index += 1) {
sum += (temporary[(item.start + index) * 224 + x] ?? 0) * (item.weights[index] ?? 0);
}
resized[y * 224 + x] = clampByte(Math.trunc(sum / 2 ** 22));
}
}
const plane = 224 * 224;
const result = new Float32Array(3 * plane);
for (let pixel = 0; pixel < plane; pixel += 1) {
const normalized = Math.fround(Math.fround(Math.fround(resized[pixel]) / Math.fround(255)) * Math.fround(2) - Math.fround(1));
result[pixel] = normalized;
result[plane + pixel] = normalized;
result[2 * plane + pixel] = normalized;
}
return result;
};
const logSoftmax = (values) => {
let maximum = Number.NEGATIVE_INFINITY;
for (const item of values) maximum = Math.max(maximum, item);
let sum = 0;
for (const item of values) sum += Math.exp(item - maximum);
const logZ = Math.log(sum) + maximum;
return Float32Array.from(values, (item) => item - logZ);
};
const noRepeat = (ids, scores) => {
if (ids.length < 2) return;
const prefix = ids.slice(-2);
for (let index = 0; index <= ids.length - 3; index += 1) {
if (prefix.every((id, offset) => id === ids[index + offset])) scores[ids[index + 2]] = Number.NEGATIVE_INFINITY;
}
};
const top = (items, item, count) => {
if (items.length < count || item.score > (items.at(-1)?.score ?? Number.NEGATIVE_INFINITY)) {
items.push(item);
items.sort((a, b) => b.score - a.score);
if (items.length > count) items.pop();
}
};
const normalizedScore = (beam) => beam.score / Math.pow(Math.max(1, beam.ended ? beam.ids.length - 1 : beam.ids.length), 2);
const decodeText = (ids) => ids.filter((id) => id >= 15).map((id) => vocab[id] ?? "").map((token) => token.replace(/^##/, "")).join("").replace(/\s+/g, "").replaceAll("…", "...").replace(/[・.]{2,}/g, (match) => ".".repeat(match.length)).replace(/[\u0021-\u007e]/g, (character) => String.fromCharCode(character.charCodeAt(0) + 0xfee0));
const recognize = async (image) => {
const pixels = preprocess(cropImageData(image));
let result;
let encoderMs;
[result, encoderMs] = await timed(() => encoder.run({ pixel_values: new ort.Tensor("float32", pixels, [1, 3, 224, 224]) }));
const hiddenTensor = result.last_hidden_state ?? Object.values(result)[0];
log(`encoder output=${hiddenTensor.location} ${JSON.stringify(hiddenTensor.dims)}`);
const hidden = hiddenTensor.data;
const [, seqLen, hiddenDim] = hiddenTensor.dims;
let active = [{ ids: [2], score: 0, ended: false }];
const completed = [];
const decoderStarted = performance.now();
for (let step = 1; step < 96; step += 1) {
if (!active.length || completed.length >= 4) break;
const tokenLength = active[0].ids.length;
const inputIds = new BigInt64Array(active.length * tokenLength);
const repeatedHidden = new Float32Array(active.length * seqLen * hiddenDim);
active.forEach((beam, beamIndex) => {
beam.ids.forEach((id, idIndex) => inputIds[beamIndex * tokenLength + idIndex] = BigInt(id));
repeatedHidden.set(hidden, beamIndex * seqLen * hiddenDim);
});
const decoderResult = await decoder.run({
input_ids: new ort.Tensor("int64", inputIds, [active.length, tokenLength]),
encoder_hidden_states: new ort.Tensor("float32", repeatedHidden, [active.length, seqLen, hiddenDim]),
});
const tensor = decoderResult.logits ?? Object.values(decoderResult)[0];
const candidates = [];
active.forEach((beam, beamIndex) => {
const rowOffset = beamIndex * tokenLength * 6144 + (tokenLength - 1) * 6144;
const scores = logSoftmax(tensor.data.subarray(rowOffset, rowOffset + 6144));
noRepeat(beam.ids, scores);
for (let token = 0; token < scores.length; token += 1) top(candidates, { beam, token, score: beam.score + scores[token] }, 8);
});
const next = [];
for (let rank = 0; rank < candidates.length && next.length < 4; rank += 1) {
const candidate = candidates[rank];
if (candidate.token === 3) {
if (rank < 4) completed.push({ ids: [...candidate.beam.ids, 3], score: candidate.score, ended: true });
} else next.push({ ids: [...candidate.beam.ids, candidate.token], score: candidate.score, ended: false });
}
active = next;
}
const decoderMs = performance.now() - decoderStarted;
const candidates = (completed.length >= 4 ? completed : [...completed, ...active]).sort((a, b) => normalizedScore(b) - normalizedScore(a));
const text = decodeText(candidates[0]?.ids.filter((id) => id !== 2 && id !== 3) ?? []);
hiddenTensor.dispose();
return { encoderMs, decoderMs, totalMs: encoderMs + decoderMs, text };
};
const image = await loadImage(parameters.get("image") ?? "/.cache/demo/daf0244b038a-20260706.png");
const runs = Number(parameters.get("runs") ?? 4);
for (let run = 1; run <= runs; run += 1) {
const result = await recognize(image);
log(`RUN ${run}/${runs} encoder=${result.encoderMs.toFixed(1)} decoder=${result.decoderMs.toFixed(1)} total=${result.totalMs.toFixed(1)} ms`);
log(`TEXT ${result.text}`);
}
</script>
|