Update app.py

app.py

@@ -2,13 +2,21 @@ import gradio as gr
 import matplotlib.pyplot as plt
 import numpy as np
 import os
+import PIL
 import tensorflow as tf
-from tensorflow.keras import layers, Sequential
-from tensorflow.keras.models import load_model
+
+from tensorflow import keras
+from tensorflow.keras import layers
+from tensorflow.keras.models import Sequential
+
+
+from PIL import Image
 import gdown
 import zipfile
+
 import pathlib
 
+
 # Define the Google Drive shareable link
 gdrive_url = 'https://drive.google.com/file/d/1HjHYlQyRz5oWt8kehkt1TiOGRRlKFsv8/view?usp=drive_link'
 
@@ -37,37 +45,63 @@ except zipfile.BadZipFile:
 os.remove(local_zip_file)
 
 # Convert the extracted directory path to a pathlib.Path object
-data_dir = pathlib.Path(extracted_path) / 'Pest_Dataset'
+data_dir = pathlib.Path(extracted_path)
+
+# Print the directory structure to debug
+for root, dirs, files in os.walk(extracted_path):
+    level = root.replace(extracted_path, '').count(os.sep)
+    indent = ' ' * 4 * (level)
+    print(f"{indent}{os.path.basename(root)}/")
+    subindent = ' ' * 4 * (level + 1)
+    for f in files:
+        print(f"{subindent}{f}")
+
+
+# Path to the dataset directory
+data_dir = pathlib.Path('extracted_files/Pest_Dataset')
+data_dir = pathlib.Path(data_dir)
+
+
+bees = list(data_dir.glob('bees/*'))
+print(bees[0])
+PIL.Image.open(str(bees[0]))
+
+
+bees = list(data_dir.glob('bees/*'))
+print(bees[0])
+PIL.Image.open(str(bees[0]))
+
 
-# Verify if the path exists
-assert data_dir.exists(), f"Path {data_dir} does not exist."
 
-# Load the dataset
-img_height, img_width = 180, 180
 batch_size = 32
+img_height = 180
+img_width = 180
 
-train_ds = tf.keras.preprocessing.image_dataset_from_directory(
+
+train_ds = tf.keras.utils.image_dataset_from_directory(
   data_dir,
   validation_split=0.2,
   subset="training",
   seed=123,
   image_size=(img_height, img_width),
-  batch_size=batch_size
-)
+  batch_size=batch_size)
 
-val_ds = tf.keras.preprocessing.image_dataset_from_directory(
+
+val_ds = tf.keras.utils.image_dataset_from_directory(
   data_dir,
   validation_split=0.2,
   subset="validation",
   seed=123,
   image_size=(img_height, img_width),
-  batch_size=batch_size
-)
+  batch_size=batch_size)
+
 
 class_names = train_ds.class_names
 print(class_names)
 
-# Plot some images from the training dataset
+
+import matplotlib.pyplot as plt
+
 plt.figure(figsize=(10, 10))
 for images, labels in train_ds.take(1):
   for i in range(9):
@@ -76,16 +110,57 @@ for images, labels in train_ds.take(1):
     plt.title(class_names[labels[i]])
     plt.axis("off")
 
-# Define data augmentation
-data_augmentation = Sequential(
+
+
+for image_batch, labels_batch in train_ds:
+  print(image_batch.shape)
+  print(labels_batch.shape)
+  break
+
+
+AUTOTUNE = tf.data.AUTOTUNE
+
+train_ds = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE)
+val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
+
+
+normalization_layer = layers.Rescaling(1./255)
+
+
+
+
+
+
+normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
+image_batch, labels_batch = next(iter(normalized_ds))
+first_image = image_batch[0]
+# Notice the pixel values are now in `[0,1]`.
+print(np.min(first_image), np.max(first_image))
+
+
+
+
+
+
+
+num_classes = len(class_names)
+
+
+
+
+data_augmentation = keras.Sequential(
   [
-    layers.RandomFlip("horizontal", input_shape=(img_height, img_width, 3)),
+    layers.RandomFlip("horizontal",
+                      input_shape=(img_height,
+                                  img_width,
+                                  3)),
     layers.RandomRotation(0.1),
     layers.RandomZoom(0.1),
   ]
 )
 
-# Plot augmented images
+
+
 plt.figure(figsize=(10, 10))
 for images, _ in train_ds.take(1):
   for i in range(9):
@@ -94,11 +169,12 @@ for images, _ in train_ds.take(1):
     plt.imshow(augmented_images[0].numpy().astype("uint8"))
     plt.axis("off")
 
-# Define the model
-num_classes = len(class_names)
+
+
+
 model = Sequential([
   data_augmentation,
-  layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
+  layers.Rescaling(1./255),
   layers.Conv2D(16, 3, padding='same', activation='relu'),
   layers.MaxPooling2D(),
   layers.Conv2D(32, 3, padding='same', activation='relu'),
@@ -108,16 +184,21 @@ model = Sequential([
   layers.Dropout(0.2),
   layers.Flatten(),
   layers.Dense(128, activation='relu'),
-  layers.Dense(num_classes, activation='softmax')
+  layers.Dense(num_classes, name="outputs")
 ])
 
+
+
+
 model.compile(optimizer='adam',
-              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
+              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
               metrics=['accuracy'])
 
+
 model.summary()
 
-# Train the model
+
+
 epochs = 15
 history = model.fit(
   train_ds,
@@ -125,10 +206,11 @@ history = model.fit(
   epochs=epochs
 )
 
-# Define the Gradio interface
+
+
 def predict_image(img):
     img = np.array(img)
-    img_resized = tf.image.resize(img, (img_height, img_width))
+    img_resized = tf.image.resize(img, (180, 180))
     img_4d = tf.expand_dims(img_resized, axis=0)
     prediction = model.predict(img_4d)[0]
     return {class_names[i]: float(prediction[i]) for i in range(len(class_names))}
@@ -155,3 +237,10 @@ gr.Interface(
     description="The image data set used was obtained from Kaggle and has a collection of 12 different types of agricultural pests: Ants, Bees, Beetles, Caterpillars, Earthworms, Earwigs, Grasshoppers, Moths, Slugs, Snails, Wasps, and Weevils",
     css=custom_css
 ).launch(debug=True)
+
+
+
+
+
+
+