Add files via upload

Author: NaeRong

Tutorials/Model Script/alexnet.py

@@ -0,0 +1,222 @@
+# -*- coding: utf-8 -*-
+"""AlexNet.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1ABqe0qMluk3sfqmwdxABpyUl93efb4Al
+"""
+
+from google.colab import drive
+drive.mount('/content/drive')
+
+pip install cnn_finetune
+
+import skimage
+import pandas
+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
+from torchvision import transforms, utils
+from PIL import Image
+import pandas as pd
+# Ignore warnings
+import warnings
+warnings.filterwarnings("ignore")
+from torch.utils.data.sampler import SubsetRandomSampler
+from torch.utils.data import DataLoader
+
+import torch.nn as nn
+import torch.nn.functional as F
+import argparse
+import torch
+import torchvision
+import torchvision.transforms as transforms
+from torch.autograd import Variable
+import torch.nn as nn
+import torch.optim as optim
+
+from cnn_finetune import make_model
+
+parser = argparse.ArgumentParser(description='cnn_finetune')
+parser.add_argument('-f')
+parser.add_argument('--batch-size', type=int, default=16, metavar='N',
+                    help='input batch size for training (default: 4)')
+parser.add_argument('--epochs', type=int, default=30, metavar='N',
+                    help='number of epochs to train (default: 30)')
+parser.add_argument('--lr', type=float, default=0.001, metavar='LR',
+                    help='learning rate (default: 0.001)')
+parser.add_argument('--momentum', type=float, default=0.9, metavar='M',
+                    help='SGD momentum (default: 0.9)')
+parser.add_argument('--no-cuda', action='store_true', default=False,
+                    help='disables CUDA training')
+parser.add_argument('--model-name', type=str, default='alexnet', metavar='M',
+                    help='model name (default: alexnet)')
+
+args = parser.parse_args()
+use_cuda = not args.no_cuda and torch.cuda.is_available()
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+class FloodTinyDataset(Dataset):
+
+    def __init__(self, df, transform = None):
+       
+        self.flood_tiny_data = df
+        ''' Change self.root_dir to load images '''
+        # self.root_dir = f"/content/drive/My Drive/ladi/Images/flood_tiny/"
+        self.transform = transform
+
+    def __len__(self):
+        return len(self.flood_tiny_data)
+
+    def __getitem__(self, idx):
+        if torch.is_tensor(idx):
+            idx = idx.tolist()
+            
+        # pos = self.flood_tiny_data.iloc[idx, 9].rfind('/')+1
+        # img_name = os.path.join(self.root_dir, self.flood_tiny_data.iloc[idx, 9][pos:])  
+        img_name = self.flood_tiny_data.iloc[idx, 10]
+
+        image = Image.fromarray(io.imread(img_name))
+        uuid = self.flood_tiny_data.iloc[idx, 1]
+        timestamp = self.flood_tiny_data.iloc[idx, 2]
+        gps_lat = self.flood_tiny_data.iloc[idx, 3]
+        gps_lon = self.flood_tiny_data.iloc[idx, 4]
+        gps_alt = self.flood_tiny_data.iloc[idx, 5]
+        file_size = self.flood_tiny_data.iloc[idx, 6]
+        width = self.flood_tiny_data.iloc[idx, 7]
+        height = self.flood_tiny_data.iloc[idx, 8]
+        ### Labels should be numerical, not bool for training ###
+        if self.flood_tiny_data.iloc[idx, -1] == True:
+            label = 1
+        else:
+            label = 0
+        
+        if self.transform:
+            image = self.transform(image)
+
+        sample = {'image': image, 'image_name': img_name, 'label': label, 'uuid': uuid, 'timestamp': timestamp, 'gps_lat': gps_lat, 'gps_lon': gps_lon, 'gps_alt': gps_alt, 'orig_file_size': file_size, 'orig_width': width, 'orig_height': height}
+
+        return sample
+
+csv_file = '/content/drive/My Drive/DS440_Model/flood_tiny_metadata_L.csv'
+label_csv = '/content/drive/My Drive/DS440_Model/flood_tiny_label_L.csv'
+
+metadata = pd.read_csv(csv_file)
+label = pd.read_csv(label_csv)
+all_data = pd.merge(metadata, label, on="s3_path")
+
+class_zero = all_data[all_data['label']==False]
+class_one = all_data[all_data['label']==True]
+flood_tiny_data = pd.concat([class_zero, class_one]).sample(frac=1).reset_index(drop=True)
+
+flood_tiny_dataset = FloodTinyDataset(df=flood_tiny_data)
+
+transformed_dataset = FloodTinyDataset(df=flood_tiny_data, transform=transforms.Compose([transforms.Resize(256),
+transforms.RandomRotation(10),
+transforms.RandomCrop(256),
+transforms.RandomHorizontalFlip(), 
+transforms.ToTensor()]))
+
+batch_size=args.batch_size
+test_split_ratio = .2
+shuffle_dataset = True
+random_seed= 42
+# Creating data indices for training and validation splits:
+dataset_size = len(transformed_dataset)
+indices = list(range(dataset_size))
+split = int(np.floor(test_split_ratio * dataset_size))
+if shuffle_dataset :
+    np.random.seed(random_seed)
+    np.random.shuffle(indices)
+train_indices, test_indices = indices[split:], indices[:split]
+
+train_sampler = SubsetRandomSampler(train_indices)
+test_sampler = SubsetRandomSampler(test_indices)
+
+train_loader = torch.utils.data.DataLoader(transformed_dataset, batch_size=batch_size,
+                                           sampler=train_sampler)
+test_loader = torch.utils.data.DataLoader(transformed_dataset, batch_size=batch_size,
+                                                sampler=test_sampler)
+
+def train(model, epoch, optimizer, train_loader, criterion=nn.CrossEntropyLoss()):
+    running_loss = 0
+    total_size = 0
+    model.train()
+    for i, data in enumerate(train_loader, 0):
+
+        # get the inputs; data is a list of [inputs, labels]
+        inputs = data['image']
+        labels = data['label']
+        inputs = inputs.to(device)
+        labels = labels.to(device)
+        # casting int to long for loss calculation#
+        labels = labels.long()
+
+        # zero the parameter gradients
+        optimizer.zero_grad()
+
+        # forward + backward + optimize
+        outputs = model(inputs)
+        loss = criterion(outputs, labels)
+
+        running_loss += loss.item()
+        total_size += inputs.size(0)
+        loss.backward()
+        optimizer.step()
+
+        if i % 20 == 19:   
+            print('[%d, %3d] loss: %.3f' %
+                  (epoch + 1, i + 1, running_loss / 20))
+            running_loss = 0.0
+
+print('Finished Training')
+
+def test(model, test_loader, criterion=nn.CrossEntropyLoss()):
+    model.eval()
+    correct = 0
+    total = 0
+    with torch.no_grad():
+        for data in test_loader:
+            inputs = data['image']
+            labels = data['label']
+            inputs = inputs.to(device)
+            labels = labels.to(device)
+            
+            outputs = model(inputs)
+            
+            _, predicted = torch.max(outputs.data, 1)
+            #test_loss += criterion(output, target).item()
+            total += labels.size(0)
+            correct += (predicted == labels).sum().item()
+
+            #correct += pred.eq(target.data.view_as(pred)).long().cpu().sum().item()
+    accuracy = 100 * (correct / total)
+    print('Accuracy of the network on test images: %d %%' % (accuracy))
+    state = {'epoch': epoch, 'state_dict': model.state_dict(),
+             'optimizer_state_dict': optimizer.state_dict()}
+    model_name = 'Alexnet_%d_%d.pth' % (epoch, accuracy)
+    PATH = f"/content/drive/My Drive/{model_name}"
+    torch.save(state, PATH)
+
+model_name = args.model_name
+
+# classes = ('0','1') 
+model = make_model(
+        model_name,
+        pretrained=True,
+        num_classes=2,
+        input_size= (256,256),
+    )
+model = model.to(device)
+optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum= args.momentum)
+scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)
+for epoch in range(0, args.epochs):
+  scheduler.step(epoch)
+  train(model, epoch, optimizer, train_loader)
+  test(model, test_loader)