server_model.py

import io
from fastapi.responses import JSONResponse
import torch
from fastapi import FastAPI, UploadFile, File
from PIL import Image

# ...
import torchvision.transforms as transforms
import torch.nn as nn


def conv3x3(in_planes, out_planes, stride=1):
    return nn.Conv2d(
        in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False
    )


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AvgPool2d(4, stride=1)
        self.fc = nn.Linear(512 * block.expansion * 1 * 1, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(
                    self.inplanes,
                    planes * block.expansion,
                    kernel_size=1,
                    stride=stride,
                    bias=False,
                ),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x


app = FastAPI()

# Implement transforms
pipeline_transforms = transforms.Compose(
    [
        transforms.Resize((32, 32)),
        transforms.ToTensor(),
        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
    ]
)
classes = ("0", "1", "2", "3", "4", "5", "6", "7", "8", "9")


@app.get("/")
def root():
    return {"message": "CNN model is up!"}


@app.post("/predict")
async def predict(file: UploadFile = File()):
    input_tensor = None
    try:
        model = ResNet(BasicBlock, [2, 2, 2, 2], num_classes=10)
        model.load_state_dict(
            torch.load("resnet18_svhn.pth", weights_only=True, map_location="cpu")
        )
        model.eval()
        # get data payload
        image_bytes = await file.read()
        # encode data as uint8 RGB image from payload
        image = Image.open(io.BytesIO(image_bytes)).convert("RGB")

        # Create input tensor
        # ...
        input_tensor = pipeline_transforms(image)
        input_tensor = input_tensor.unsqueeze(0)

        # Implement inference step
        with torch.no_grad():
            outputs = model(input_tensor)
            _, predicted_idx = torch.max(outputs.data, 1)
        predicted_class = classes[predicted_idx.item()]
        ...

        return JSONResponse(content={"prediction": predicted_class})
    except Exception as e:
        return JSONResponse(
            status_code=400, content={"error": str(e) + str(input_tensor.shape)}
        )