[Web] How to free webgpu gpu mem in onnxruntime web #21574

/**
 *
 * @param model don't pass session but pass model path and create session in infer inner. In this way, after infer finish, it will auto free gpu mem to prevent mem overflow
 * @param inputTensor
 */
export async function infer2(model: string, inputTensor: Tensor) {
  const session = await newSession(model)
  const feeds: any = {};
  const inputNames = session.inputNames;
  feeds[inputNames[0]] = inputTensor;
  const results = await session.run(feeds);
  const tensor = results[session.outputNames[0]]
  // await session.release() // free gpu mem
  await session.release() // free gpu mem
  return tensor;
}

/**
 * Load the ONNX model and perform inference
 * @param model don't pass session but pass model path and create session in infer inner. In this way, after infer finish, it will auto free gpu mem to prevent mem overflow
 * @param {onnxruntime.Tensor} inputTensor - Input tensor
 * @param {number[]} inputShape - Input tensor shape
 * @returns {Promise<Float32Array>} - Output tensor data
 */
export const infer = async (model: string, input: Ndarray) => {
  let inputTensor = ndarrayToTensor(input)
  const outTensor = await infer2(model, inputTensor);
  let na = new Ndarray(Array.from(outTensor.data as Float32Array) as number[], outTensor.dims as number[])
  inputTensor.dispose()
  outTensor.dispose()
  return na
  // const {data: out, dims: outShape} = results[session.outputNames[0]]
  // return {out: out as Float32Array, outShape: outShape as number[]}
};

  let input = await imgToNdarray(t);
  let out = await infer(model, input)
  let imgDataUrl = outToImgDataUrl(out)
  testReact(<img src={imgDataUrl}/>)