請在程式碼中計算此尺寸。
請在程式碼中計算此尺寸。
```python Python
import math
def count_image_tokens(width: int, height: int) -> int:
"""Visual tokens consumed by an image: one token per 28x28 pixel patch."""
return math.ceil(width / 28) * math.ceil(height / 28)
def resized_size(
width: int,
height: int,
max_edge: int = 1568,
max_tokens: int = 1568,
) -> tuple[int, int]:
"""The size Claude resizes an image to before padding.
Defaults are for the standard resolution tier. For high-resolution-tier
models, use max_edge=2576 and max_tokens=4784. Returns (width, height).
Images that already fit within the limits are returned unchanged.
"""
def fits(w: int, h: int) -> bool:
return (
math.ceil(w / 28) * 28 <= max_edge
and math.ceil(h / 28) * 28 <= max_edge
and count_image_tokens(w, h) <= max_tokens
)
if fits(width, height):
return (width, height)
if height > width:
resized_h, resized_w = resized_size(height, width, max_edge, max_tokens)
return (resized_w, resized_h)
# 沿長邊進行二分搜尋，找出保持長寬比且能容納的
# 最大尺寸。
aspect_ratio = width / height
lo, hi = 1, width # lo always fits; hi never fits
while lo + 1 < hi:
mid = (lo + hi) // 2
if fits(mid, max(round(mid / aspect_ratio), 1)):
lo = mid
else:
hi = mid
return (lo, max(round(lo / aspect_ratio), 1))
# 「Claude 如何調整大小並填補影像」中的 A4 範例：
print(resized_size(1075, 1520)) # (924, 1307)
# 若要套用調整大小，請使用您的影像函式庫，例如 Pillow：
# image.resize(resized_size(*image.size))
```
```typescript TypeScript
/** Visual tokens consumed by an image: one token per 28x28 pixel patch. */
function countImageTokens(width: number, height: number): number {
return Math.ceil(width / 28) * Math.ceil(height / 28);
}
/**
* Round half to even (banker's rounding), matching Python's round(). The
* live API resolves exact .5 ties toward the even neighbor, so Math.round
* (which rounds halves up) would compute a different size for some images.
*/
function roundTiesToEven(value: number): number {
const floor = Math.floor(value);
if (value - floor !== 0.5) {
return Math.round(value);
}
return floor % 2 === 0 ? floor : floor + 1;
}
/**
* The size Claude resizes an image to before padding.
*
* Defaults are for the standard resolution tier. For high-resolution-tier
* models, use maxEdge = 2576 and maxTokens = 4784. Returns [width, height].
* Images that already fit within the limits are returned unchanged.
*/
function resizedSize(
width: number,
height: number,
maxEdge = 1568,
maxTokens = 1568
): [number, number] {
const fits = (w: number, h: number): boolean =>
Math.ceil(w / 28) * 28 <= maxEdge &&
Math.ceil(h / 28) * 28 <= maxEdge &&
countImageTokens(w, h) <= maxTokens;
if (fits(width, height)) {
return [width, height];
}
if (height > width) {
const [resizedH, resizedW] = resizedSize(height, width, maxEdge, maxTokens);
return [resizedW, resizedH];
}
// 沿長邊進行二分搜尋，找出保持長寬比且能容納的
// 最大尺寸。
const aspectRatio = width / height;
let lo = 1; // lo always fits
let hi = width; // hi never fits
while (lo + 1 < hi) {
const mid = Math.floor((lo + hi) / 2);
if (fits(mid, Math.max(roundTiesToEven(mid / aspectRatio), 1))) {
lo = mid;
} else {
hi = mid;
}
}
return [lo, Math.max(roundTiesToEven(lo / aspectRatio), 1)];
}
// 「Claude 如何調整大小與填補影像」中的 A4 範例：
console.log(resizedSize(1075, 1520)); // [ 924, 1307 ]
// 若要套用調整大小，請使用您的影像程式庫，例如 sharp：
// await sharp(input).resize(width, height).toBuffer()
```
```csharp C#
// 影像消耗的視覺 token 數：每個 28x28 像素區塊對應一個 token。
static int CountImageTokens(int width, int height)
{
return (width + 27) / 28 * ((height + 27) / 28); // ceil(w/28) * ceil(h/28)
}
// Claude 在填補前將影像調整到的大小。預設值適用於
// 標準解析度層級；若為高解析度層級模型，請傳入
// maxEdge: 2576, maxTokens: 4784。已符合限制的影像
// 會原樣回傳。
static (int Width, int Height) ResizedSize(
int width, int height, int maxEdge = 1568, int maxTokens = 1568)
{
bool Fits(int w, int h) =>
(w + 27) / 28 * 28 <= maxEdge
&& (h + 27) / 28 * 28 <= maxEdge
&& CountImageTokens(w, h) <= maxTokens;
if (Fits(width, height))
{
return (width, height);
}
if (height > width)
{
(int resizedH, int resizedW) = ResizedSize(height, width, maxEdge, maxTokens);
return (resizedW, resizedH);
}
// 沿長邊進行二分搜尋，找出能容納且保持長寬比的
// 最大尺寸。短邊採四捨五入至偶數，與即時 API 在
// 恰為 .5 時的行為一致（MidpointRounding.ToEven，即 Math.Round 預設）。
double aspectRatio = (double)width / height;
int lo = 1; // lo always fits
int hi = width; // hi never fits
while (lo + 1 < hi)
{
int mid = (lo + hi) / 2;
if (Fits(mid, ShortEdge(mid)))
{
lo = mid;
}
else
{
hi = mid;
}
}
return (lo, ShortEdge(lo));
int ShortEdge(int longEdge) =>
Math.Max((int)Math.Round(longEdge / aspectRatio, MidpointRounding.ToEven), 1);
}
// 「Claude 如何調整影像大小與填補」中的 A4 範例：
Console.WriteLine(ResizedSize(1075, 1520)); // (924, 1307)
```
```go Go
// countImageTokens 是一張圖片消耗的視覺 token 數：每個
// 28x28 像素區塊對應一個 token。
func countImageTokens(width, height int) int {
return ((width + 27) / 28) * ((height + 27) / 28) // ceil(w/28) * ceil(h/28)
}
// resizedSize 是 Claude 在填充前將圖片調整到的尺寸，以
// (width, height) 表示。標準解析度層級請傳入 maxEdge 1568 與 maxTokens 1568，
// 高解析度層級則傳入 2576 與 4784。已符合
// 限制的圖片會原樣回傳。
// 「Claude 如何調整圖片大小與填充」中的 A4 範例：
// resizedSize(1075, 1520, 1568, 1568) 回傳 (924, 1307)。
func resizedSize(width, height, maxEdge, maxTokens int) (int, int) {
fits := func(w, h int) bool {
return ((w+27)/28)*28 <= maxEdge &&
((h+27)/28)*28 <= maxEdge &&
countImageTokens(w, h) <= maxTokens
}
if fits(width, height) {
return width, height
}
if height > width {
resizedH, resizedW := resizedSize(height, width, maxEdge, maxTokens)
return resizedW, resizedH
}
// 沿長邊進行二分搜尋，找出保持長寬比且能容納的
// 最大尺寸。短邊採四捨六入五成雙（math.RoundToEven），
// 與即時 API 在恰好 .5 時的行為一致；math.Round 則會進位。
aspectRatio := float64(width) / float64(height)
lo, hi := 1, width // lo always fits; hi never fits
for lo+1 < hi {
mid := (lo + hi) / 2
short := max(int(math.RoundToEven(float64(mid)/aspectRatio)), 1)
if fits(mid, short) {
lo = mid
} else {
hi = mid
}
}
return lo, max(int(math.RoundToEven(float64(lo)/aspectRatio)), 1)
}
```
```java Java
/** A resized image size, as returned by resizedSize. */
record Size(int width, int height) {}
/** Visual tokens consumed by an image: one token per 28x28 pixel patch. */
static int countImageTokens(int width, int height) {
return Math.ceilDiv(width, 28) * Math.ceilDiv(height, 28);
}
/**
* The size Claude resizes an image to before padding.
*
* Pass maxEdge 1568 and maxTokens 1568 for the standard resolution tier,
* or 2576 and 4784 for the high-resolution tier. Images that already fit
* within the limits are returned unchanged.
*
*
The A4 example from "How Claude resizes and pads images":
* resizedSize(1075, 1520, 1568, 1568) returns new Size(924, 1307).
*/
static Size resizedSize(int width, int height, int maxEdge, int maxTokens) {
if (fits(width, height, maxEdge, maxTokens)) {
return new Size(width, height);
}
if (height > width) {
Size rotated = resizedSize(height, width, maxEdge, maxTokens);
return new Size(rotated.height(), rotated.width());
}
// 沿長邊進行二分搜尋，找出能容納且保持長寬比的
// 最大尺寸。短邊採用四捨六入五成雙（Math.rint），
// 與即時 API 在恰好 .5 時的行為一致；Math.round 則會向上取整。
double aspectRatio = (double) width / height;
int lo = 1; // lo always fits
int hi = width; // hi never fits
while (lo + 1 < hi) {
int mid = (lo + hi) / 2;
if (fits(mid, shortEdge(mid, aspectRatio), maxEdge, maxTokens)) {
lo = mid;
} else {
hi = mid;
}
}
return new Size(lo, shortEdge(lo, aspectRatio));
}
private static boolean fits(int width, int height, int maxEdge, int maxTokens) {
return Math.ceilDiv(width, 28) * 28 <= maxEdge
&& Math.ceilDiv(height, 28) * 28 <= maxEdge
&& countImageTokens(width, height) <= maxTokens;
}
private static int shortEdge(int longEdge, double aspectRatio) {
return Math.max((int) Math.rint(longEdge / aspectRatio), 1);
}
```
```php PHP
// 影像消耗的視覺 token 數：每個 28x28 像素區塊對應一個 token。
function countImageTokens(int $width, int $height): int
{
return intdiv($width + 27, 28) * intdiv($height + 27, 28);
}
/**
* The size Claude resizes an image to before padding, as [width, height].
*
* Defaults are for the standard resolution tier. For high-resolution-tier
* models, pass maxEdge: 2576, maxTokens: 4784. Images that already fit
* within the limits are returned unchanged.
*/
function resizedSize(int $width, int $height, int $maxEdge = 1568, int $maxTokens = 1568): array
{
$fits = fn (int $w, int $h): bool =>
intdiv($w + 27, 28) * 28 <= $maxEdge
&& intdiv($h + 27, 28) * 28 <= $maxEdge
&& countImageTokens($w, $h) <= $maxTokens;
if ($fits($width, $height)) {
return [$width, $height];
}
if ($height > $width) {
[$resizedH, $resizedW] = resizedSize($height, $width, $maxEdge, $maxTokens);
return [$resizedW, $resizedH];
}
// 沿長邊進行二分搜尋，找出能容納且保持長寬比的
// 最大尺寸。短邊採用四捨六入五成雙
// （PHP_ROUND_HALF_EVEN），與即時 API 在恰好 .5 平手時的行為一致。
$aspectRatio = $width / $height;
$lo = 1; // lo always fits
$hi = $width; // hi never fits
while ($lo + 1 < $hi) {
$mid = intdiv($lo + $hi, 2);
$short = max((int) round($mid / $aspectRatio, 0, PHP_ROUND_HALF_EVEN), 1);
if ($fits($mid, $short)) {
$lo = $mid;
} else {
$hi = $mid;
}
}
return [$lo, max((int) round($lo / $aspectRatio, 0, PHP_ROUND_HALF_EVEN), 1)];
}
// 來自「Claude 如何調整影像大小與填補」的 A4 範例：
[$resizedWidth, $resizedHeight] = resizedSize(1075, 1520);
echo "({$resizedWidth}, {$resizedHeight})\n"; // (924, 1307)
```
```ruby Ruby
# 影像消耗的視覺 token：每個 28x28 像素區塊對應一個 token。
def count_image_tokens(width, height)
width.ceildiv(28) * height.ceildiv(28)
end
# Claude 在填補前將影像調整到的尺寸，格式為 [width, height]。
#
# 預設值適用於標準解析度層級。對於高解析度層級
# 模型，請傳入 max_edge: 2576, max_tokens: 4784。已符合
# 限制的影像會原樣回傳。
def resized_size(width, height, max_edge = 1568, max_tokens = 1568)
fits = lambda do |w, h|
w.ceildiv(28) * 28 <= max_edge &&
h.ceildiv(28) * 28 <= max_edge &&
count_image_tokens(w, h) <= max_tokens
end
return [width, height] if fits.call(width, height)
if height > width
resized_h, resized_w = resized_size(height, width, max_edge, max_tokens)
return [resized_w, resized_h]
end
# 沿長邊進行二分搜尋，找出保持長寬比且能容納的
# 最大尺寸。短邊將半值捨入至偶數（round(half: :even)），
# 在恰好為 .5 的平手情況下與實際 API 一致。
aspect_ratio = width.fdiv(height)
lo = 1 # lo always fits
hi = width # hi never fits
while lo + 1 < hi
mid = (lo + hi) / 2
short = [(mid / aspect_ratio).round(half: :even), 1].max
if fits.call(mid, short)
lo = mid
else
hi = mid
end
end
[lo, [(lo / aspect_ratio).round(half: :even), 1].max]
end
# 來自「How Claude resizes and pads images」的 A4 範例：
p resized_size(1075, 1520) # => [924, 1307]
```
1. 將影像調整為調整大小輔助函式所回傳的尺寸。如果影像已符合模型的限制，輔助函式會原封不動地回傳其尺寸，無需調整大小。
2. [將調整後的影像傳送](https://platform.claude.com/docs/zh-TW/build-with-claude/vision#send-images-to-claude)至 API。請勿自行填補。Claude 會處理填補，且填補不會移動座標原點。
3. 在提示中明確要求像素座標。例如：*「以像素座標回傳 Submit 按鈕的點擊位置，格式為 `[x, y]`。」*
4. 直接將回傳的座標用於您所傳送的影像。如果您需要正規化座標，請以您所傳送影像的尺寸相除，而非原始影像的尺寸，也非填補後的尺寸。