devpatelio

pragma solidity ^0.5.1;


contract ERC20Token {
    string public name; 
    mapping(address => uint256) public balances;
    
    constructor(string memory _token_name) public{
        name = _token_name;
    }

devpatelio

## in the command-line, type 'kaggle datasets download -d sovitrath/diabetic-retinopathy-224x224-gaussian-filtered'

from __future__ import print_function, division
import os
import torch
import pandas as pd
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader

devpatelio

trainer_names_csv = pd.read_csv('/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/train.csv')

n = 3662
img_names = trainer_names_csv.iloc[:n, 0]
label = trainer_names_csv.iloc[:n, 1]

def showimages(img):
    plt.imshow(img)
    
showimages(io.imread('/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/gaussian_filtered_images/gaussian_filtered_images/' + img_names[0] + '.png'))

devpatelio

from torch.utils.data import Dataset
import pandas as pd
import os
from PIL import Image
import torch

class DRDataset(Dataset):
    def __init__ (self, csv_file, root_dir, transform=None):
        """
        csv_file = labels

devpatelio

image_dataset = DRDataset(csv_file='/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/train.csv', root_dir='/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/gaussian_filtered_images/gaussian_filtered_images/')
transformed_dataset = DRDataset(csv_file='/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/train.csv', root_dir='/Users/devpatelio/Downloads/Coding/Python/pyTorch/diabetic-retinopathy-224x224-gaussian-filtered/gaussian_filtered_images/gaussian_filtered_images/', 
                               transform=transforms.Compose([transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]))

"""
created 2 datasets -> 
transformed_dataset = transformed using the Normalize function and to a tensor dtype
image_dataset = dataset that is used to preview images

"""

devpatelio

from tqdm import tqdm
import random

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
   
])

num_epochs = 10

devpatelio

class Net(nn.Module):
    def __init__ (self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 8, 5) ## nn.Conv2d(input channels (image), output channels (no. of kernels), kernel size)
        self.pool = nn.MaxPool2d(2, 2) ##maxpool with kernel size 2, stride 2
        self.conv2 = nn.Conv2d(8, 8, 5) ## second conv layer
        self.conv3 = nn.Conv2d(8, 16, 5) ## third conv layer

        self.fc1 = nn.Linear(9216, 2000) #to find the first parameter of fc1, you can uncomment the print(x.shape) in the forward pass and take the value returned by it and paste it in
        self.fc2 = nn.Linear(2000, 120)

devpatelio

import torch.optim as optim  
criterion = nn.CrossEntropyLoss() 
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)

devpatelio

for epoch in range(num_epochs):
    running_loss = 0.0 
    for i, data in enumerate(train_loader, 0): #starting from i=0, we iterate over the train_loader
        inputs, labels = data #assign image and corresp. label to data variable
        labels = labels.type(torch.LongTensor) #turn label into longtensor just in case error is thrown
        optimizer.zero_grad() #zero the gradients before training begins after each epoch
        outputs = net(inputs) #input the given values into the model 'net'
#         print(labels.data)
#         print(outputs.data)
        loss = criterion(outputs, labels) #calculates the loss between the outputs and the given labels

devpatelio

class Net(nn.Module):
 def __init__ (self):
 super(Net, self).__init__()
 self.conv1 = nn.Conv2d(3, 8, 5) 
 self.pool = nn.MaxPool2d(2, 2)
 self.conv2 = nn.Conv2d(8, 8, 5)
 self.pool = nn.MaxPool2d(2, 2)
 self.conv3 = nn.Conv2d(8, 20, 5) ## note change here in 16 to 20
 self.pool = nn.MaxPool2d(2, 2)
 self.fc1 = nn.Linear(11520, 2000) ## note change here in 9216 to 11520