From 9bb95d7c36f7ac38bfd64b5462c0e92a82c64c8e Mon Sep 17 00:00:00 2001
From: Shreyash Gupta <31446588+shreyashguptas@users.noreply.github.com>
Date: Sun, 23 Jun 2024 15:01:11 +0000
Subject: [PATCH] chore: Update dataset paths in code files

---
 CAPTCHA Images/.gitignore |  2 --
 combined_code.txt         | 20 +++++++++++++++++---
 dataset.py                |  2 +-
 predict.py                |  2 +-
 split_train_val_test.py   |  2 +-
 train.py                  |  6 +++---
 6 files changed, 23 insertions(+), 11 deletions(-)
 delete mode 100644 CAPTCHA Images/.gitignore

diff --git a/CAPTCHA Images/.gitignore b/CAPTCHA Images/.gitignore
deleted file mode 100644
index a3a0c8b..0000000
--- a/CAPTCHA Images/.gitignore	
+++ /dev/null
@@ -1,2 +0,0 @@
-*
-!.gitignore
\ No newline at end of file
diff --git a/combined_code.txt b/combined_code.txt
index 83c3dad..a4f124c 100644
--- a/combined_code.txt
+++ b/combined_code.txt
@@ -19,15 +19,25 @@ def split_image(image):
     return output
 
 
+# class CaptchaImagesDataset(Dataset):
+#     def __init__(self, root, augment=False):
+#         super(CaptchaImagesDataset, self).__init__()
+#         self.root = root
+#         self.augment = augment
+
+#         self.image_list = []
+#         for ext in ('*.png', '*.jpg'):
+#             self.image_list.extend(glob.glob(os.path.join(root, ext)))
+
 class CaptchaImagesDataset(Dataset):
     def __init__(self, root, augment=False):
         super(CaptchaImagesDataset, self).__init__()
         self.root = root
         self.augment = augment
-
         self.image_list = []
         for ext in ('*.png', '*.jpg'):
             self.image_list.extend(glob.glob(os.path.join(root, ext)))
+        print(f"Found {len(self.image_list)} images in {root}")
 
     def __len__(self):
         return len(self.image_list)
@@ -54,8 +64,13 @@ class CaptchaImagesDataset(Dataset):
 def get_loader(root, batch_size):
     train_dataset = CaptchaImagesDataset(root + '/train', augment=True)
     val_dataset = CaptchaImagesDataset(root + '/val', augment=False)
+    
+    print(f"Number of training samples: {len(train_dataset)}")
+    print(f"Number of validation samples: {len(val_dataset)}")
+    
     train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, drop_last=True)
     val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=True, drop_last=True)
+    
     return train_loader, val_loader
 
 
@@ -384,5 +399,4 @@ if __name__ == '__main__':
         if ground_truth == decoded_text:
             correct += 1
 
-    print('accuracy =', correct/len(image_list))
-
+    print('accuracy =', correct/len(image_list))
\ No newline at end of file
diff --git a/dataset.py b/dataset.py
index 90a641e..5d06b6d 100644
--- a/dataset.py
+++ b/dataset.py
@@ -74,7 +74,7 @@ def get_loader(root, batch_size):
 
 
 if __name__ == '__main__':
-    train, val = get_loader('data/CAPTCHA Images/', batch_size=2)
+    train, val = get_loader('/home/dev/dev_work_shrey/playing_around/data/CAPTCHA Images/', batch_size=2)
     for image, labels in train:
         print()
     print()
diff --git a/predict.py b/predict.py
index 84e7945..ade2082 100644
--- a/predict.py
+++ b/predict.py
@@ -24,7 +24,7 @@
     model.eval()
 
     correct = 0.0
-    image_list = glob.glob('/app/data/CAPTCHA Images/test/*')
+    image_list = glob.glob('/home/dev/dev_work_shrey/playing_around/data/CAPTCHA Images/test/*')
     for image in tqdm(image_list):
         ground_truth = image.split('/')[-1].split('.')[0]
         image = Image.open(image).convert('RGB')
diff --git a/split_train_val_test.py b/split_train_val_test.py
index b2dd4a7..42ba03d 100644
--- a/split_train_val_test.py
+++ b/split_train_val_test.py
@@ -35,6 +35,6 @@ def split_train_val_test(root):
 
 
 if __name__ == '__main__':
-    split_train_val_test('data/CAPTCHA Images')
+    split_train_val_test('/home/dev/dev_work_shrey/playing_around/data/CAPTCHA Images')
 
     print()
diff --git a/train.py b/train.py
index 26c76f4..ab2ce24 100644
--- a/train.py
+++ b/train.py
@@ -64,7 +64,7 @@ def train():
     model = CRNN(vocab_size=vocab_size).to(device)
     # model.load_state_dict(torch.load('output/weight.pth', map_location=device))
 
-    train_loader, val_loader = get_loader('/app/data/CAPTCHA Images', batch_size=batch_size)
+    train_loader, val_loader = get_loader('/home/dev/dev_work_shrey/playing_around/data/CAPTCHA Images', batch_size=batch_size)
 
     optimizer = optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9, nesterov=True)
     scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min')
@@ -77,7 +77,7 @@ def train():
         print('-----------------------------------------')
 
         if epoch == 0 or val_epoch_loss <= np.min(val_losses):
-            torch.save(model.state_dict(), '/app/output/weight.pth')
+            torch.save(model.state_dict(), '/home/dev/dev_work_shrey/playing_around/output/weight.pth')
 
         train_losses.append(train_epoch_loss)
         val_losses.append(val_epoch_loss)
@@ -90,4 +90,4 @@ def train():
 
 
 if __name__ == "__main__":
-    train()
+    train()
\ No newline at end of file