Tensorflow Interpreter throwing error for "data count" iOS - ios

Question

I am using TensorFlowLiteSwift and the model I'm working with is responsible for flattening an image when the image is cropped in a trapezoidal shape.
Now, Tensorflow does not provide much of a documentation. So, I have been trying to implement things from their example projects.
But here is the catch, it throws error saying "Provided data count must match the required count" and the required count is 4. I backtracked the byteCount in Interpreter.swift but could not find the actual setter.
So, is the .tflite model responsible for the "required count?" And if no, then how does this get set?
Here is a chunk of code I think would help understanding my problem:
/// Performs image preprocessing, invokes the `Interpreter`, and processes the inference results.
func runModel(on item: ImageProcessInfo) -> UIImage? {
let rgbData = item.resizedImage.scaledData(with: CGSize(width: 1000, height: 900),
byteCount: inputWidth * inputHeight
* batchSize,
isQuantized: false)
var corner = item.corners.map { $0.map { p -> (Float, Float) in
return (Float(p.x), Float(p.y))
} }
var item = item
guard let height = NSMutableData(capacity: 0) else { return nil }
height.append(&item.originalHeight, length: 4)
guard let width = NSMutableData(capacity: 0) else { return nil }
width.append(&item.originalWidth, length: 4)
guard let corners = NSMutableData(capacity: 0) else { return nil }
corners.append(&corner, length: 4)
do {
try interpreter.copy(rgbData!, toInputAt: 0)
try interpreter.copy(height as Data, toInputAt: 1)
try interpreter.copy(width as Data, toInputAt: 2)
try interpreter.copy(corners as Data, toInputAt: 3)
try interpreter.invoke()
let outputTensor1 = try self.interpreter.output(at: 0)
guard let cgImage = postprocessImageData(data: outputTensor1.data, size: CGSize(width: 1000, height: 900)) else {
return nil
}
let outputImage = UIImage(cgImage: cgImage)
return outputImage
} catch {
dump(error)
return nil
}
}
extension UIImage {
func scaledData(with size: CGSize, byteCount: Int, isQuantized: Bool) -> Data? {
guard let cgImage = self.cgImage, cgImage.width > 0, cgImage.height > 0 else { return nil }
guard let imageData = imageData(from: cgImage, with: size) else { return nil }
var scaledBytes = [UInt8](repeating: 0, count: byteCount)
var index = 0
for component in imageData.enumerated() {
let offset = component.offset
let isAlphaComponent = (offset % 4)
== 3
guard !isAlphaComponent else { continue }
scaledBytes[index] = component.element
index += 1
}
if isQuantized { return Data(scaledBytes) }
let scaledFloats = scaledBytes.map { (Float32($0) - 127.5) / 127.5 }
return Data(copyingBufferOf: scaledFloats)
}
private func imageData(from cgImage: CGImage, with size: CGSize) -> Data? {
let bitmapInfo = CGBitmapInfo(
rawValue: CGBitmapInfo.byteOrder32Big.rawValue | CGImageAlphaInfo.premultipliedLast.rawValue
)
let width = Int(size.width)
let scaledBytesPerRow = (cgImage.bytesPerRow / cgImage.width) * width
guard let context = CGContext(
data: nil,
width: width,
height: Int(size.height),
bitsPerComponent: cgImage.bitsPerComponent,
bytesPerRow: scaledBytesPerRow,
space: CGColorSpaceCreateDeviceRGB(),
bitmapInfo: bitmapInfo.rawValue)
else {
return nil
}
context.draw(cgImage, in: CGRect(origin: .zero, size: size))
return context.makeImage()?.dataProvider?.data as Data?
}
}
#discardableResult
public func copy(_ data: Data, toInputAt index: Int) throws -> Tensor {
let maxIndex = inputTensorCount - 1
guard case 0...maxIndex = index else {
throw InterpreterError.invalidTensorIndex(index: index, maxIndex: maxIndex)
}
guard let cTensor = TfLiteInterpreterGetInputTensor(cInterpreter, Int32(index)) else {
throw InterpreterError.allocateTensorsRequired
}
/* Error here */
let byteCount = TfLiteTensorByteSize(cTensor)
guard data.count == byteCount else {
throw InterpreterError.invalidTensorDataCount(provided: data.count, required: byteCount)
}
#if swift(>=5.0)
let status = data.withUnsafeBytes {
TfLiteTensorCopyFromBuffer(cTensor, $0.baseAddress, data.count)
}
#else
let status = data.withUnsafeBytes { TfLiteTensorCopyFromBuffer(cTensor, $0, data.count) }
#endif // swift(>=5.0)
guard status == kTfLiteOk else { throw InterpreterError.failedToCopyDataToInputTensor }
return try input(at: index)
}

Answer 1

What are the input shapes? Can you identify which one is complaining about the size?
At the first glance, corners.append(&corner, length: 4) seems weird - does corners contain only 1 Float (byte size 4)?
The byteCount for a tensor is filled by underlying C API, and simply returns tensor->bytes for underlying TfLiteTensor struct that is filled in the model loading stage.