Update trainer.py

trainer.py

@@ -9,7 +9,8 @@ import matplotlib.pyplot as plt
 import cv2
 import tensorflow as tf
 from tqdm import tqdm
-sac=os.getenv('accesstoken')
+
+sac = os.getenv('accesstoken')
 sn.set(font_scale=1.4)
 
 class_names = ['buildings', 'forest', 'glacier', 'mountain', 'sea', 'street']
@@ -52,41 +53,48 @@ def load_data():
 train_images, train_labels = shuffle(train_images, train_labels, random_state=25)
 print("Train: ", train_images.shape, train_labels.shape)
 print("Test: ", test_images.shape, test_labels.shape)
-
-model = tf.keras.models.Sequential([
+#
+# model = tf.keras.models.Sequential([
+#     tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),
+#     tf.keras.layers.MaxPooling2D(2, 2),
+#     tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
+#     tf.keras.layers.MaxPooling2D(2, 2),
+#     tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
+#     tf.keras.layers.MaxPooling2D(2, 2),
+#     tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
+#     tf.keras.layers.MaxPooling2D(2, 2),
+#     tf.keras.layers.Flatten(),
+#     tf.keras.layers.Dense(512, activation='relu'),
+#     tf.keras.layers.Dense(6, activation='softmax')
+# ])
+model = tf.keras.Sequential([
     tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),
     tf.keras.layers.MaxPooling2D(2, 2),
-    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
-    tf.keras.layers.MaxPooling2D(2, 2),
-    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
-    tf.keras.layers.MaxPooling2D(2, 2),
-    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
+    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
     tf.keras.layers.MaxPooling2D(2, 2),
     tf.keras.layers.Flatten(),
-    tf.keras.layers.Dense(512, activation='relu'),
-    tf.keras.layers.Dense(6, activation='softmax')
+    tf.keras.layers.Dense(128, activation=tf.nn.relu),
+    tf.keras.layers.Dense(6, activation=tf.nn.softmax)
 ])
 
 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
-model.fit(train_images, train_labels, epochs=10, validation_split=0.1)
+model.fit(train_images, train_labels, epochs=6, validation_split=0.2)
 
 # Evaluate the model
 model.evaluate(test_images, test_labels)
 
 # save the model
 model.save("model.keras")
-#from transformers import push_to_hub_keras
+# from transformers import push_to_hub_keras
 
 # Save the model
-#model.save("model.keras")
+# model.save("model.keras")
 
 # Upload the model to your Hugging Face space repository
 push_to_hub_keras(
     model,
-    repo_id="okeowo1014/imgclassifiertrainingsample",
+    repo_id="okeowo1014/imgclassifiertraining",
     commit_message="Optional commit message",
     tags=["image-classifier", "some_other_tag"],
-    include_optimizer=True,token=sac
+    include_optimizer=True, token=sac
 )
-
-