server.py

import os
import json
import numpy as np
from flask import Flask, request

import torch
import torch.nn as nn
import torch.nn.functional as F

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.cn1 = nn.Conv2d(1, 16, 3, 1)
        self.cn2 = nn.Conv2d(16, 32, 3, 1)
        self.dp1 = nn.Dropout2d(0.10)
        self.dp2 = nn.Dropout2d(0.25)
        self.fc1 = nn.Linear(4608, 64) # 4608 is basically 12 X 12 X 32
        self.fc2 = nn.Linear(64, 10)
 
    def forward(self, x):
        x = self.cn1(x)
        x = F.relu(x)
        x = self.cn2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dp1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dp2(x)
        x = self.fc2(x)
        op = F.log_softmax(x, dim=1)
        return op
    
model = ConvNet()
PATH_TO_MODEL = "./convnet.pth"
model.load_state_dict(torch.load(PATH_TO_MODEL, map_location="cpu"))
model.eval()

def run_model(input_tensor):
    model_input = input_tensor.unsqueeze(0)
    with torch.no_grad():
        model_output = model(model_input)[0]
    model_prediction = model_output.detach().numpy().argmax()
    return model_prediction

def post_process(output):
    return str(output)

app = Flask(__name__)

@app.route("/test", methods=["POST"])
def test():
    data = request.files['data'].read()
    md = json.load(request.files['metadata'])
    input_array = np.frombuffer(data, dtype=np.float32)
    input_image_tensor = torch.from_numpy(input_array).view(md["dims"])
    output = run_model(input_image_tensor)
    final_output = post_process(output)
    return final_output

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=8890)