Model gives ten outputs for a single input image

My model has several issues, but the one I’m focusing on here is a problem I get when using the onnx file in a C# program. When I run the model on a single image, it gives me the probability for the first value, then it gives me 9 other values that are all identical and don’t make sense (they’re like 8 when I’m expecting a probability between 0 and 1)
Here is my C# program:

using System;
using System.IO;
using System.Linq;
using System.Drawing;
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using static System.Net.Mime.MediaTypeNames;

class Program
{
    static void Main(string[] args)
    {
        // Load the ONNX model
        string modelPath = "C:/Users/Tdezeeuw/source/repos/Copper_Plate_Pytorch/Copper_Plate_Pytorch/saved_model.onnx";
        var session = new InferenceSession(modelPath);

        // Load the image
        string imagePath = "D:/Cropped Copper Plates/Edge Strips/Testing/Testing_ND/NCam1 - 202212170723 - EdgestripOvergrowth - LowerGrade - 1.bmp";//This image is in the testing set, so its likely to work
        Bitmap image = (Bitmap)System.Drawing.Image.FromFile(imagePath);

        // Convert the image to a float tensor
        var tensor = new DenseTensor<float>(new[] { 10, 3, 446, 2048 });
        for (int x = 0; x < 446; x++)
        {
            for (int y = 0; y < 2048; y++)
            {
                var color = image.GetPixel(x, y);
                tensor[0, 0, x, y] = (float)color.R;
                tensor[0, 1, x, y] = (float)color.G;
                tensor[0, 2, x, y] = (float)color.B;
            }
        }

        // Run the inference
        var inputs = new[] { session.InputMetadata.Keys.First() };
        var outputs = session.OutputMetadata.Keys.ToArray();
        //var results = session.Run(inputs, new[] { tensor });
        var inputValues = new List<NamedOnnxValue>
        {
            NamedOnnxValue.CreateFromTensor(session.InputMetadata.Keys.First(), tensor)
        };
        var results = session.Run(inputValues);


        // Print the results
        foreach (var output in outputs)
        {
            var tensorResult = results.First().AsTensor<float>();
            var prediction = tensorResult.ToArray().ToList();
            Console.WriteLine($"Prediction for {output}: {string.Join(",", prediction)}");
        }
    }
}

And here is my python program to train the model:

import os
import torch
import torch.nn as nn
import torchvision
from torchvision import datasets, transforms
from torchvision.transforms import transforms
from torch.utils.data import DataLoader
from torch.optim import Adam
import matplotlib.pyplot as plt
import numpy as np
import torch.nn.functional as F
import onnx

os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:64"
torch.cuda.empty_cache()

# Loading and normalizing the data.
# Define transformations for the training and test sets
transformations = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

batch_size = 10
number_of_labels = 2

data_dir = "D:/Cropped Copper Plates/Edge Strips"

# Load training data
train_dir = os.path.join(data_dir, "Training")
train_set = datasets.ImageFolder(train_dir, transform=transformations)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=True, num_workers=0)

# Load testing data
test_dir = os.path.join(data_dir, "Testing")
test_set = datasets.ImageFolder(test_dir, transform=transformations)
test_loader = torch.utils.data.DataLoader(test_set, batch_size=batch_size, shuffle=False, num_workers=0)

print("The number of images in a training set is: ", len(train_loader)*batch_size)
print("The number of images in a test set is: ", len(test_loader)*batch_size)

print("The number of batches per epoch is: ", len(train_loader))
classes = ('Defect', 'No_Defect')


class Network(nn.Module):
    def __init__(self):
        super(Network, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(16)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=3)
        self.drop = nn.Dropout2d()
        self.bn2 = nn.BatchNorm2d(32)
        self.fc1 = nn.Linear(7187840, 2)

    def forward(self, x):

        x = F.relu(self.bn1(self.conv1(x)))
        x = self.pool(x)
        x = F.relu(self.bn2(self.drop(self.conv2(x))))
        x = self.drop(x)
        x = torch.flatten(x, 1)
        #x = x.view(x.size(0), -1)
        #print(x.shape)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training = self.training)
        #x = self.fc2(x)
        return x

# Instantiate a neural network model 
model = Network()

 
# Define the loss function with Classification Cross-Entropy loss and an optimizer with Adam optimizer
pos_weight = torch.full([10, 2], 8.5238)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
loss_fn = nn.BCEWithLogitsLoss(pos_weight=pos_weight)
loss_fn = loss_fn.to(device)
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, weight_decay=0.001)

from torch.autograd import Variable

# Function to save the model
def saveModel():
    path = "./myFirstModel.pth"
    torch.save(model.state_dict(), path)

# Function to test the model with the test dataset and print the accuracy for the test images
def testAccuracy():
    
    model.eval()
    accuracy = 0.0
    total = 0.0
    
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
            images, labels = images.to(device), labels.to(device)
            images = images.float()
            labels = labels.float()
            # run the model on the test set to predict labels
            outputs = model(images)
            # the label with the highest energy will be our prediction
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            accuracy += (predicted == labels).sum().item()
    
    # compute the accuracy over all test images
    accuracy = (100 * accuracy / total)
    return(accuracy)


# Training function. We simply have to loop over our data iterator and feed the inputs to the network and optimize.
def train(num_epochs):
    
    best_accuracy = 0.0

    # Define your execution device
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    print("The model will be running on", device, "device")
    # Convert model parameters and buffers to CPU or Cuda
    model.to(device)

    for epoch in range(num_epochs):  # loop over the dataset multiple times
        running_loss = 0.0
        running_acc = 0.0
        accum_iter = 8;
        for i, (images, labels) in enumerate(train_loader, 0):
            
            # get the inputs
            images = images.to(device)
            labels = labels.to(device)

            # predict classes using images from the training set
            outputs = model(images)
            labels = F.one_hot(labels, num_classes=2)
            labels = labels.float()
            outputs = outputs.float()
            # compute the loss based on model output and real labels
            loss = loss_fn(outputs, labels)
            loss = loss/accum_iter
            # backpropagate the loss
            loss.backward()
            if((i+1) % accum_iter == 0) or (i+1 == len(train_loader)):
                # adjust parameters based on the calculated gradients
                optimizer.step()
                # zero the parameter gradients
                optimizer.zero_grad()

            running_loss += loss.item()     # extract the loss value
            if i % 10 == 9:    
                # print every 100 (twice per epoch) 
                print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
                # zero the loss
                running_loss = 0.0

        # Compute and print the average accuracy fo this epoch when tested over all test images
        accuracy = testAccuracy()
        print('For epoch', epoch+1,'the test accuracy over the whole test set is %d %%' % (accuracy))
        
        # we want to save the model if the accuracy is the best
        if accuracy > best_accuracy:
            saveModel()
            best_accuracy = accuracy


# Function to show the images
def imageshow(img):
    img = img / 2 + 0.5     # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


# Function to test the model with a batch of images and show the labels predictions
def testBatch():
    # get batch of images from the test DataLoader  
    images, labels = next(iter(test_loader))

    # show all images as one image grid
    #imageshow(torchvision.utils.make_grid(images))
   
    # Show the real labels on the screen 
    print('Real labels: ', ' '.join('%5s' % classes[labels[j]] for j in range(batch_size)))
  
    # Let's see what if the model identifiers the  labels of those example
    outputs = model(images)
    
    # We got the probability for every 10 labels. The highest (max) probability should be correct label
    _, predicted = torch.max(outputs, 1)
    
    # Let's show the predicted labels on the screen to compare with the real ones
    print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] 
                              for j in range(batch_size)))

if __name__ == "__main__":
    
    # Let's build our model
    train(50)
    print('Finished Training')

    # Test which classes performed well
    testAccuracy()
    
    # Let's load the model we just created and test the accuracy per label
    model = Network()
    path = "myFirstModel.pth"
    model.load_state_dict(torch.load(path))

    # Test with batch of images
    testBatch()

    torch.onnx.export(model, torch.randn(10, 3, 446, 2048), "saved_model.onnx", export_params=True, opset_version=10, do_constant_folding=True, input_names = ['input'], output_names = ['output'])
    onnx_model = onnx.load("saved_model.onnx")
    onnx.checker.check_model(onnx_model)

Based on your PyTorch code you are using a static shape of [10, 3, 446, 2048] to trace and export the ONNX model without specifying dynamic_axes so this shape would be baked into your model.