update website (#1912)

keras-team · Mar 20, 2024 · 346df97 · 346df97
1 parent 5549d89
commit 346df97
Show file tree

Hide file tree

Showing 8 changed files with 79 additions and 68 deletions.
diff --git a/docs/ipynb/export.ipynb b/docs/ipynb/export.ipynb
@@ -61,13 +61,12 @@
     "\n",
     "print(type(model))  # <class 'tensorflow.python.keras.engine.training.Model'>\n",
     "\n",
-    "try:\n",
-    "    model.save(\"model_autokeras\", save_format=\"tf\")\n",
-    "except Exception:\n",
-    "    model.save(\"model_autokeras.h5\")\n",
+    "model.save(\"model_autokeras.keras\")\n",
     "\n",
     "\n",
-    "loaded_model = load_model(\"model_autokeras\", custom_objects=ak.CUSTOM_OBJECTS)\n",
+    "loaded_model = load_model(\n",
+    "    \"model_autokeras.keras\", custom_objects=ak.CUSTOM_OBJECTS\n",
+    ")\n",
     "\n",
     "predicted_y = loaded_model.predict(np.expand_dims(x_test, -1))\n",
     "print(predicted_y)"

diff --git a/docs/ipynb/image_classification.ipynb b/docs/ipynb/image_classification.ipynb
@@ -46,6 +46,10 @@
    "outputs": [],
    "source": [
     "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
+    "x_train = x_train[:100]\n",
+    "y_train = y_train[:100]\n",
+    "x_test = x_test[:100]\n",
+    "y_test = y_test[:100]\n",
     "print(x_train.shape)  # (60000, 28, 28)\n",
     "print(y_train.shape)  # (60000,)\n",
     "print(y_train[:3])  # array([7, 2, 1], dtype=uint8)"
@@ -75,7 +79,7 @@
     "# Initialize the image classifier.\n",
     "clf = ak.ImageClassifier(overwrite=True, max_trials=1)\n",
     "# Feed the image classifier with training data.\n",
-    "clf.fit(x_train, y_train, epochs=10)\n",
+    "clf.fit(x_train, y_train, epochs=1)\n",
     "\n",
     "\n",
     "# Predict with the best model.\n",
@@ -112,7 +116,7 @@
     "    y_train,\n",
     "    # Split the training data and use the last 15% as validation data.\n",
     "    validation_split=0.15,\n",
-    "    epochs=10,\n",
+    "    epochs=1,\n",
     ")"
    ]
   },
@@ -144,7 +148,7 @@
     "    y_train,\n",
     "    # Use your own validation set.\n",
     "    validation_data=(x_val, y_val),\n",
-    "    epochs=10,\n",
+    "    epochs=1,\n",
     ")"
    ]
   },
@@ -185,7 +189,7 @@
     "clf = ak.AutoModel(\n",
     "    inputs=input_node, outputs=output_node, overwrite=True, max_trials=1\n",
     ")\n",
-    "clf.fit(x_train, y_train, epochs=10)"
+    "clf.fit(x_train, y_train, epochs=1)"
    ]
   },
   {
@@ -219,7 +223,7 @@
     "clf = ak.AutoModel(\n",
     "    inputs=input_node, outputs=output_node, overwrite=True, max_trials=1\n",
     ")\n",
-    "clf.fit(x_train, y_train, epochs=10)"
+    "clf.fit(x_train, y_train, epochs=1)"
    ]
   },
   {
@@ -294,7 +298,7 @@
     "\n",
     "clf = ak.ImageClassifier(overwrite=True, max_trials=1)\n",
     "# Feed the tensorflow Dataset to the classifier.\n",
-    "clf.fit(train_set, epochs=10)\n",
+    "clf.fit(train_set, epochs=1)\n",
     "# Predict with the best model.\n",
     "predicted_y = clf.predict(test_set)\n",
     "# Evaluate the best model with testing data.\n",

diff --git a/docs/ipynb/image_regression.ipynb b/docs/ipynb/image_regression.ipynb
@@ -52,6 +52,8 @@
     "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
     "x_train = x_train[:100]\n",
     "y_train = y_train[:100]\n",
+    "x_test = x_test[:100]\n",
+    "y_test = y_test[:100]\n",
     "print(x_train.shape)  # (60000, 28, 28)\n",
     "print(y_train.shape)  # (60000,)\n",
     "print(y_train[:3])  # array([7, 2, 1], dtype=uint8)"
@@ -65,7 +67,7 @@
    "source": [
     "The second step is to run the ImageRegressor.  It is recommended have more\n",
     "trials for more complicated datasets.  This is just a quick demo of MNIST, so\n",
-    "we set max_trials to 1.  For the same reason, we set epochs to 2.  You can also\n",
+    "we set max_trials to 1.  For the same reason, we set epochs to 1.  You can also\n",
     "leave the epochs unspecified for an adaptive number of epochs.\n"
    ]
   },
@@ -80,7 +82,7 @@
     "# Initialize the image regressor.\n",
     "reg = ak.ImageRegressor(overwrite=True, max_trials=1)\n",
     "# Feed the image regressor with training data.\n",
-    "reg.fit(x_train, y_train, epochs=2)\n",
+    "reg.fit(x_train, y_train, epochs=1)\n",
     "\n",
     "\n",
     "# Predict with the best model.\n",
@@ -117,7 +119,7 @@
     "    y_train,\n",
     "    # Split the training data and use the last 15% as validation data.\n",
     "    validation_split=0.15,\n",
-    "    epochs=2,\n",
+    "    epochs=1,\n",
     ")"
    ]
   },
@@ -190,7 +192,7 @@
     "reg = ak.AutoModel(\n",
     "    inputs=input_node, outputs=output_node, overwrite=True, max_trials=1\n",
     ")\n",
-    "reg.fit(x_train, y_train, epochs=2)"
+    "reg.fit(x_train, y_train, epochs=1)"
    ]
   },
   {
@@ -224,7 +226,7 @@
     "reg = ak.AutoModel(\n",
     "    inputs=input_node, outputs=output_node, overwrite=True, max_trials=1\n",
     ")\n",
-    "reg.fit(x_train, y_train, epochs=2)"
+    "reg.fit(x_train, y_train, epochs=1)"
    ]
   },
   {
@@ -258,6 +260,10 @@
    "outputs": [],
    "source": [
     "(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
+    "x_train = x_train[:100]\n",
+    "y_train = y_train[:100]\n",
+    "x_test = x_test[:100]\n",
+    "y_test = y_test[:100]\n",
     "\n",
     "# Reshape the images to have the channel dimension.\n",
     "x_train = x_train.reshape(x_train.shape + (1,))\n",
@@ -273,7 +279,7 @@
     "\n",
     "reg = ak.ImageRegressor(overwrite=True, max_trials=1)\n",
     "# Feed the tensorflow Dataset to the regressor.\n",
-    "reg.fit(train_set, epochs=2)\n",
+    "reg.fit(train_set, epochs=1)\n",
     "# Predict with the best model.\n",
     "predicted_y = reg.predict(test_set)\n",
     "# Evaluate the best model with testing data.\n",

diff --git a/docs/ipynb/load.ipynb b/docs/ipynb/load.ipynb
@@ -94,7 +94,7 @@
    },
    "outputs": [],
    "source": [
-    "batch_size = 32\n",
+    "batch_size = 2\n",
     "img_height = 180\n",
     "img_width = 180\n",
     "\n",
@@ -137,8 +137,8 @@
    "outputs": [],
    "source": [
     "clf = ak.ImageClassifier(overwrite=True, max_trials=1)\n",
-    "clf.fit(train_data, epochs=1)\n",
-    "print(clf.evaluate(test_data))"
+    "clf.fit(train_data.take(100), epochs=1)\n",
+    "print(clf.evaluate(test_data.take(2)))"
    ]
   },
   {
@@ -203,8 +203,8 @@
     ")\n",
     "\n",
     "clf = ak.TextClassifier(overwrite=True, max_trials=1)\n",
-    "clf.fit(train_data, epochs=2)\n",
-    "print(clf.evaluate(test_data))"
+    "clf.fit(train_data.take(2), epochs=1)\n",
+    "print(clf.evaluate(test_data.take(2)))"
    ]
   },
   {
@@ -225,8 +225,8 @@
    },
    "outputs": [],
    "source": [
-    "N_BATCHES = 30\n",
-    "BATCH_SIZE = 100\n",
+    "N_BATCHES = 2\n",
+    "BATCH_SIZE = 10\n",
     "\n",
     "\n",
     "def get_data_generator(n_batches, batch_size):\n",
@@ -247,7 +247,7 @@
     "    output_shapes=((32, 32, 3), tuple()),\n",
     ").batch(BATCH_SIZE)\n",
     "\n",
-    "clf = ak.ImageDataClassifier(overwrite=True, max_trials=1, seed=5)\n",
+    "clf = ak.ImageClassifier(overwrite=True, max_trials=1, seed=5)\n",
     "clf.fit(x=dataset, validation_data=dataset, batch_size=BATCH_SIZE)\n",
     "print(clf.evaluate(dataset))"
    ]

diff --git a/docs/ipynb/multi.ipynb b/docs/ipynb/multi.ipynb
@@ -78,7 +78,7 @@
    },
    "outputs": [],
    "source": [
-    "num_instances = 100\n",
+    "num_instances = 10\n",
     "# Generate image data.\n",
     "image_data = np.random.rand(num_instances, 32, 32, 3).astype(np.float32)\n",
     "# Generate numerical data.\n",
@@ -144,7 +144,8 @@
     "model.fit(\n",
     "    [image_data, numerical_data],\n",
     "    [regression_target, classification_target],\n",
-    "    epochs=3,\n",
+    "    epochs=1,\n",
+    "    batch_size=3,\n",
     ")"
    ]
   },
@@ -173,7 +174,8 @@
     "    [regression_target, classification_target],\n",
     "    # Split the training data and use the last 15% as validation data.\n",
     "    validation_split=0.15,\n",
-    "    epochs=2,\n",
+    "    epochs=1,\n",
+    "    batch_size=3,\n",
     ")"
    ]
   },
@@ -195,7 +197,7 @@
    },
    "outputs": [],
    "source": [
-    "split = 20\n",
+    "split = 5\n",
     "\n",
     "image_val = image_data[split:]\n",
     "numerical_val = numerical_data[split:]\n",
@@ -215,7 +217,8 @@
     "        [image_val, numerical_val],\n",
     "        [regression_val, classification_val],\n",
     "    ),\n",
-    "    epochs=2,\n",
+    "    epochs=1,\n",
+    "    batch_size=3,\n",
     ")"
    ]
   },
@@ -261,7 +264,7 @@
     "output_node1 = ak.Merge()([output_node1, output_node2])\n",
     "\n",
     "input_node2 = ak.Input()\n",
-    "output_node2 = ak.DenseBlock()(output_node)\n",
+    "output_node2 = ak.DenseBlock()(input_node2)\n",
     "\n",
     "output_node = ak.Merge()([output_node1, output_node2])\n",
     "output_node1 = ak.ClassificationHead()(output_node)\n",
@@ -282,8 +285,8 @@
     "auto_model.fit(\n",
     "    [image_data, numerical_data],\n",
     "    [classification_target, regression_target],\n",
-    "    batch_size=32,\n",
-    "    epochs=3,\n",
+    "    batch_size=3,\n",
+    "    epochs=1,\n",
     ")"
    ]
   },

diff --git a/docs/ipynb/text_classification.ipynb b/docs/ipynb/text_classification.ipynb
@@ -66,10 +66,10 @@
     "    os.path.join(IMDB_DATADIR, \"test\"), shuffle=False, categories=classes\n",
     ")\n",
     "\n",
-    "x_train = np.array(train_data.data)\n",
-    "y_train = np.array(train_data.target)\n",
-    "x_test = np.array(test_data.data)\n",
-    "y_test = np.array(test_data.target)\n",
+    "x_train = np.array(train_data.data)[:100]\n",
+    "y_train = np.array(train_data.target)[:100]\n",
+    "x_test = np.array(test_data.data)[:100]\n",
+    "y_test = np.array(test_data.target)[:100]\n",
     "\n",
     "print(x_train.shape)  # (25000,)\n",
     "print(y_train.shape)  # (25000, 1)\n",
@@ -100,7 +100,7 @@
     "    overwrite=True, max_trials=1\n",
     ")  # It only tries 1 model as a quick demo.\n",
     "# Feed the text classifier with training data.\n",
-    "clf.fit(x_train, y_train, epochs=2)\n",
+    "clf.fit(x_train, y_train, epochs=1, batch_size=2)\n",
     "# Predict with the best model.\n",
     "predicted_y = clf.predict(x_test)\n",
     "# Evaluate the best model with testing data.\n",
@@ -132,6 +132,8 @@
     "    y_train,\n",
     "    # Split the training data and use the last 15% as validation data.\n",
     "    validation_split=0.15,\n",
+    "    epochs=1,\n",
+    "    batch_size=2,\n",
     ")"
    ]
   },
@@ -153,17 +155,18 @@
    },
    "outputs": [],
    "source": [
-    "split = 5000\n",
+    "split = 5\n",
     "x_val = x_train[split:]\n",
     "y_val = y_train[split:]\n",
     "x_train = x_train[:split]\n",
     "y_train = y_train[:split]\n",
     "clf.fit(\n",
     "    x_train,\n",
     "    y_train,\n",
-    "    epochs=2,\n",
+    "    epochs=1,\n",
     "    # Use your own validation set.\n",
     "    validation_data=(x_val, y_val),\n",
+    "    batch_size=2,\n",
     ")"
    ]
   },
@@ -196,7 +199,7 @@
     "clf = ak.AutoModel(\n",
     "    inputs=input_node, outputs=output_node, overwrite=True, max_trials=1\n",
     ")\n",
-    "clf.fit(x_train, y_train, epochs=2)"
+    "clf.fit(x_train, y_train, epochs=1, batch_size=2)"
    ]
   },
   {
@@ -226,17 +229,17 @@
    "outputs": [],
    "source": [
     "train_set = tf.data.Dataset.from_tensor_slices(((x_train,), (y_train,))).batch(\n",
-    "    32\n",
+    "    2\n",
     ")\n",
-    "test_set = tf.data.Dataset.from_tensor_slices(((x_test,), (y_test,))).batch(32)\n",
+    "test_set = tf.data.Dataset.from_tensor_slices(((x_test,), (y_test,))).batch(2)\n",
     "\n",
-    "clf = ak.TextClassifier(overwrite=True, max_trials=2)\n",
+    "clf = ak.TextClassifier(overwrite=True, max_trials=1)\n",
     "# Feed the tensorflow Dataset to the classifier.\n",
-    "clf.fit(train_set, epochs=2)\n",
+    "clf.fit(train_set.take(2), epochs=1)\n",
     "# Predict with the best model.\n",
-    "predicted_y = clf.predict(test_set)\n",
+    "predicted_y = clf.predict(test_set.take(2))\n",
     "# Evaluate the best model with testing data.\n",
-    "print(clf.evaluate(test_set))"
+    "print(clf.evaluate(test_set.take(2)))"
    ]
   },
   {