通过本地主机将火炬张量或图像作为 JSON 发送到另一个应用程序

Question

我有一个加载了生成器模型的基本 Flask 服务器。我正在通过 JSON 发送一个输入向量，它正在命中生成器，生成器吐出一个预测。这行得通。然后我想将此图像（我愿意将其作为我可以在另一端重建的任何类型的数据发送）发送到同一台机器上的另一个应用程序运行。据我所知，最好将图像编码为 base64，但我的所有尝试都失败了。任何指导表示赞赏。

@app.route("/json", methods=['GET', 'POST', 'PUT'])
def getjsondata():

if request.method=='POST':
    print("received POST")

    data = request.get_json()

    #print(format(data['z']))
    jzf = [float(i) for i in data['z']]
    jzft = torch.FloatTensor(jzf)
    jzftr = jzft.reshape([1, 512])

    z = jzftr.cuda()
    c = None                   # class labels (not used in this example)
    trunc = 1
    img = G(z, c, trunc)
    img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)

    # now what?

Answer 1

我设法解决了。 Python Flask 服务器看起来像这样并期望接收一个 JSON 对象，其中包含一个由 512 个浮点数组成的 Z 数组和一个浮点数的截断。

from flask import Flask, jsonify, request, send_file # initialize our Flask application
import json
from flask_cors import CORS
import base64
from torchvision import transforms
import dnnlib
import torch
import PIL.Image
from io import BytesIO
from datetime import datetime
import legacy

device = torch.device('cuda')
with dnnlib.util.open_url("snapshot.pkl") as f:
    G = legacy.load_network_pkl(f)['G_ema'].to(device) # type: ignore

app = Flask(__name__)
CORS(app)

@app.route("/test", methods=['GET', 'POST', 'PUT'])
def test():
    return "OK"

@app.route("/query", methods=['GET', 'POST', 'PUT'])
def getjsondata():

    if request.method=='POST':
        # print("received POST")

        data = request.get_json()

        #print(format(data['z']))
        jzf = [float(i) for i in data['z']]
        jzft = torch.FloatTensor(jzf)
        jzftr = jzft.reshape([1, 512])

        z = jzftr.cuda()
        c = None                   # class labels (not used in this example)
        trunc = data['truncation']
        img = G(z, c, trunc)

        #img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
        img = (img * 127.5 + 128).clamp(0, 255).to(torch.uint8)

        # turn into PIL image
        pil_img = transforms.ToPILImage()(img[0]).convert("RGB")
        #pil_img = PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB')

        # SAVING...
        #fn = datetime.today().strftime('%Y-%m-%d-%H:%M:%S')
        #pil_img.save('saved_images/' + fn + '.jpg')

        response = serve_pil_image64(pil_img)
        response.headers.add('Access-Control-Allow-Origin', '*')
        # response.headers.add('Content-Transfer-Encoding', 'base64')
        return response


    return 'OK'

def serve_pil_image64(pil_img):
    img_io = BytesIO()
    pil_img.save(img_io, 'JPEG', quality=70)
    img_str = base64.b64encode(img_io.getvalue()).decode("utf-8")
    return jsonify({'status': True, 'image': img_str})


if __name__ == '__main__':
    app.run(host='localhost', port=9000, debug=True)

就目前而言，我正在从一个简单的 JavaScript/HTML 站点发送上述 JSON 数组。然后它会监听响应，也是 JSON.

// construct an HTTP request
var xhr = new XMLHttpRequest();

// upon successful completion of request...
xhr.onreadystatechange = function() {
    if (xhr.readyState == XMLHttpRequest.DONE) {
        var json = JSON.parse(xhr.responseText);
        // console.log(json);
        document.getElementById("image_output").src = "data:image/jpeg;base64," + json.image;

    }
}


xhr.open("POST", "http://localhost:9000/json");
xhr.setRequestHeader('Content-Type', 'application/json; charset=UTF-8');

通过本地主机将火炬张量或图像作为 JSON 发送到另一个应用程序

send torch tensor or image via localhost as JSON to another app

python

python-imaging-library

flask

torch

pytorch