diff --git a/10_neural_nets_with_keras.ipynb b/10_neural_nets_with_keras.ipynb index bdc15c2..074f1da 100644 --- a/10_neural_nets_with_keras.ipynb +++ b/10_neural_nets_with_keras.ipynb @@ -843,7 +843,7 @@ " keras.layers.Dense(30, activation=\"relu\", input_shape=X_train.shape[1:]),\n", " keras.layers.Dense(1)\n", "])\n", - "model.compile(loss=\"mean_squared_error\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mean_squared_error\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "history = model.fit(X_train, y_train, epochs=20, validation_data=(X_valid, y_valid))\n", "mse_test = model.evaluate(X_test, y_test)\n", "X_new = X_test[:3]\n", @@ -924,7 +924,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mean_squared_error\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mean_squared_error\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "history = model.fit(X_train, y_train, epochs=20,\n", " validation_data=(X_valid, y_valid))\n", "mse_test = model.evaluate(X_test, y_test)\n", @@ -969,7 +969,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "\n", "X_train_A, X_train_B = X_train[:, :5], X_train[:, 2:]\n", "X_valid_A, X_valid_B = X_valid[:, :5], X_valid[:, 2:]\n", @@ -1022,7 +1022,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=[\"mse\", \"mse\"], loss_weights=[0.9, 0.1], optimizer=keras.optimizers.SGD(lr=1e-3))" + "model.compile(loss=[\"mse\", \"mse\"], loss_weights=[0.9, 0.1], optimizer=keras.optimizers.SGD(learning_rate=1e-3))" ] }, { @@ -1085,7 +1085,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", loss_weights=[0.9, 0.1], optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mse\", loss_weights=[0.9, 0.1], optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "history = model.fit((X_train_A, X_train_B), (y_train, y_train), epochs=10,\n", " validation_data=((X_valid_A, X_valid_B), (y_valid, y_valid)))\n", "total_loss, main_loss, aux_loss = model.evaluate((X_test_A, X_test_B), (y_test, y_test))\n", @@ -1128,7 +1128,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "history = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))\n", "mse_test = model.evaluate(X_test, y_test)" ] @@ -1215,7 +1215,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "checkpoint_cb = keras.callbacks.ModelCheckpoint(\"my_keras_model.h5\", save_best_only=True)\n", "history = model.fit(X_train, y_train, epochs=10,\n", " validation_data=(X_valid, y_valid),\n", @@ -1230,7 +1230,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))\n", + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))\n", "early_stopping_cb = keras.callbacks.EarlyStopping(patience=10,\n", " restore_best_weights=True)\n", "history = model.fit(X_train, y_train, epochs=100,\n", @@ -1315,7 +1315,7 @@ " keras.layers.Dense(30, activation=\"relu\"),\n", " keras.layers.Dense(1)\n", "]) \n", - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))" + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))" ] }, { @@ -1387,7 +1387,7 @@ " keras.layers.Dense(30, activation=\"relu\"),\n", " keras.layers.Dense(1)\n", "]) \n", - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=0.05))" + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=0.05))" ] }, { @@ -1455,7 +1455,7 @@ " for layer in range(n_hidden):\n", " model.add(keras.layers.Dense(n_neurons, activation=\"relu\"))\n", " model.add(keras.layers.Dense(1))\n", - " optimizer = keras.optimizers.SGD(lr=learning_rate)\n", + " optimizer = keras.optimizers.SGD(learning_rate=learning_rate)\n", " model.compile(loss=\"mse\", optimizer=optimizer)\n", " return model" ] @@ -1802,9 +1802,9 @@ " self.rates = []\n", " self.losses = []\n", " def on_batch_end(self, batch, logs):\n", - " self.rates.append(K.get_value(self.model.optimizer.lr))\n", + " self.rates.append(K.get_value(self.model.optimizer.learning_rate))\n", " self.losses.append(logs[\"loss\"])\n", - " K.set_value(self.model.optimizer.lr, self.model.optimizer.lr * self.factor)" + " K.set_value(self.model.optimizer.learning_rate, self.model.optimizer.learning_rate * self.factor)" ] }, { @@ -1846,7 +1846,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])\n", "expon_lr = ExponentialLearningRate(factor=1.005)" ] @@ -1930,7 +1930,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=3e-1),\n", + " optimizer=keras.optimizers.SGD(learning_rate=3e-1),\n", " metrics=[\"accuracy\"])" ] }, diff --git a/11_training_deep_neural_networks.ipynb b/11_training_deep_neural_networks.ipynb index b424baa..747d64e 100644 --- a/11_training_deep_neural_networks.ipynb +++ b/11_training_deep_neural_networks.ipynb @@ -283,7 +283,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -332,7 +332,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -534,7 +534,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -606,7 +606,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -686,7 +686,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -733,7 +733,7 @@ "outputs": [], "source": [ "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -893,7 +893,7 @@ "outputs": [], "source": [ "model_A.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -936,7 +936,7 @@ "outputs": [], "source": [ "model_B.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -990,7 +990,7 @@ " layer.trainable = False\n", "\n", "model_B_on_A.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -1007,7 +1007,7 @@ " layer.trainable = True\n", "\n", "model_B_on_A.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])\n", "history = model_B_on_A.fit(X_train_B, y_train_B, epochs=16,\n", " validation_data=(X_valid_B, y_valid_B))" @@ -1074,7 +1074,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.SGD(lr=0.001, momentum=0.9)" + "optimizer = keras.optimizers.SGD(learning_rate=0.001, momentum=0.9)" ] }, { @@ -1090,7 +1090,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.SGD(lr=0.001, momentum=0.9, nesterov=True)" + "optimizer = keras.optimizers.SGD(learning_rate=0.001, momentum=0.9, nesterov=True)" ] }, { @@ -1106,7 +1106,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Adagrad(lr=0.001)" + "optimizer = keras.optimizers.Adagrad(learning_rate=0.001)" ] }, { @@ -1122,7 +1122,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.RMSprop(lr=0.001, rho=0.9)" + "optimizer = keras.optimizers.RMSprop(learning_rate=0.001, rho=0.9)" ] }, { @@ -1138,7 +1138,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999)" + "optimizer = keras.optimizers.Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999)" ] }, { @@ -1154,7 +1154,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Adamax(lr=0.001, beta_1=0.9, beta_2=0.999)" + "optimizer = keras.optimizers.Adamax(learning_rate=0.001, beta_1=0.9, beta_2=0.999)" ] }, { @@ -1170,7 +1170,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=0.001, beta_1=0.9, beta_2=0.999)" + "optimizer = keras.optimizers.Nadam(learning_rate=0.001, beta_1=0.9, beta_2=0.999)" ] }, { @@ -1201,7 +1201,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.SGD(lr=0.01, decay=1e-4)" + "optimizer = keras.optimizers.SGD(learning_rate=0.01, decay=1e-4)" ] }, { @@ -1374,12 +1374,12 @@ "\n", " def on_batch_begin(self, batch, logs=None):\n", " # Note: the `batch` argument is reset at each epoch\n", - " lr = K.get_value(self.model.optimizer.lr)\n", - " K.set_value(self.model.optimizer.lr, lr * 0.1**(1 / s))\n", + " lr = K.get_value(self.model.optimizer.learning_rate)\n", + " K.set_value(self.model.optimizer.learning_rate, lr * 0.1**(1 / s))\n", "\n", " def on_epoch_end(self, epoch, logs=None):\n", " logs = logs or {}\n", - " logs['lr'] = K.get_value(self.model.optimizer.lr)\n", + " logs['lr'] = K.get_value(self.model.optimizer.learning_rate)\n", "\n", "model = keras.models.Sequential([\n", " keras.layers.Flatten(input_shape=[28, 28]),\n", @@ -1388,7 +1388,7 @@ " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", "lr0 = 0.01\n", - "optimizer = keras.optimizers.Nadam(lr=lr0)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=lr0)\n", "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer, metrics=[\"accuracy\"])\n", "n_epochs = 25\n", "\n", @@ -1532,7 +1532,7 @@ " keras.layers.Dense(100, activation=\"selu\", kernel_initializer=\"lecun_normal\"),\n", " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", - "optimizer = keras.optimizers.SGD(lr=0.02, momentum=0.9)\n", + "optimizer = keras.optimizers.SGD(learning_rate=0.02, momentum=0.9)\n", "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer, metrics=[\"accuracy\"])\n", "n_epochs = 25\n", "history = model.fit(X_train_scaled, y_train, epochs=n_epochs,\n", @@ -1629,20 +1629,20 @@ " self.rates = []\n", " self.losses = []\n", " def on_batch_end(self, batch, logs):\n", - " self.rates.append(K.get_value(self.model.optimizer.lr))\n", + " self.rates.append(K.get_value(self.model.optimizer.learning_rate))\n", " self.losses.append(logs[\"loss\"])\n", - " K.set_value(self.model.optimizer.lr, self.model.optimizer.lr * self.factor)\n", + " K.set_value(self.model.optimizer.learning_rate, self.model.optimizer.learning_rate * self.factor)\n", "\n", "def find_learning_rate(model, X, y, epochs=1, batch_size=32, min_rate=10**-5, max_rate=10):\n", " init_weights = model.get_weights()\n", " iterations = math.ceil(len(X) / batch_size) * epochs\n", " factor = np.exp(np.log(max_rate / min_rate) / iterations)\n", - " init_lr = K.get_value(model.optimizer.lr)\n", - " K.set_value(model.optimizer.lr, min_rate)\n", + " init_lr = K.get_value(model.optimizer.learning_rate)\n", + " K.set_value(model.optimizer.learning_rate, min_rate)\n", " exp_lr = ExponentialLearningRate(factor)\n", " history = model.fit(X, y, epochs=epochs, batch_size=batch_size,\n", " callbacks=[exp_lr])\n", - " K.set_value(model.optimizer.lr, init_lr)\n", + " K.set_value(model.optimizer.learning_rate, init_lr)\n", " model.set_weights(init_weights)\n", " return exp_lr.rates, exp_lr.losses\n", "\n", @@ -1672,9 +1672,9 @@ " def on_batch_end(self, batch, logs=None):\n", " batch_loss = logs[\"loss\"] * (batch + 1) - self.prev_loss * batch\n", " self.prev_loss = logs[\"loss\"]\n", - " self.rates.append(K.get_value(self.model.optimizer.lr))\n", + " self.rates.append(K.get_value(self.model.optimizer.learning_rate))\n", " self.losses.append(batch_loss)\n", - " K.set_value(self.model.optimizer.lr, self.model.optimizer.lr * self.factor)\n", + " K.set_value(self.model.optimizer.learning_rate, self.model.optimizer.learning_rate * self.factor)\n", "```" ] }, @@ -1694,7 +1694,7 @@ " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])" ] }, @@ -1738,7 +1738,7 @@ " rate = self._interpolate(2 * self.half_iteration, self.iterations,\n", " self.start_rate, self.last_rate)\n", " self.iteration += 1\n", - " K.set_value(self.model.optimizer.lr, rate)" + " K.set_value(self.model.optimizer.learning_rate, rate)" ] }, { @@ -1889,7 +1889,7 @@ " keras.layers.AlphaDropout(rate=0.2),\n", " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", - "optimizer = keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True)\n", + "optimizer = keras.optimizers.SGD(learning_rate=0.01, momentum=0.9, nesterov=True)\n", "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer, metrics=[\"accuracy\"])\n", "n_epochs = 20\n", "history = model.fit(X_train_scaled, y_train, epochs=n_epochs,\n", @@ -2060,7 +2060,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.SGD(lr=0.01, momentum=0.9, nesterov=True)\n", + "optimizer = keras.optimizers.SGD(learning_rate=0.01, momentum=0.9, nesterov=True)\n", "mc_model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer, metrics=[\"accuracy\"])" ] }, @@ -2219,7 +2219,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=5e-5)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=5e-5)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])" @@ -2342,7 +2342,7 @@ " model.add(keras.layers.Activation(\"elu\"))\n", "model.add(keras.layers.Dense(10, activation=\"softmax\"))\n", "\n", - "optimizer = keras.optimizers.Nadam(lr=5e-4)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=5e-4)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])\n", @@ -2399,7 +2399,7 @@ " activation=\"selu\"))\n", "model.add(keras.layers.Dense(10, activation=\"softmax\"))\n", "\n", - "optimizer = keras.optimizers.Nadam(lr=7e-4)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=7e-4)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])\n", @@ -2470,7 +2470,7 @@ "model.add(keras.layers.AlphaDropout(rate=0.1))\n", "model.add(keras.layers.Dense(10, activation=\"softmax\"))\n", "\n", - "optimizer = keras.optimizers.Nadam(lr=5e-4)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=5e-4)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])\n", @@ -2621,7 +2621,7 @@ "model.add(keras.layers.AlphaDropout(rate=0.1))\n", "model.add(keras.layers.Dense(10, activation=\"softmax\"))\n", "\n", - "optimizer = keras.optimizers.SGD(lr=1e-3)\n", + "optimizer = keras.optimizers.SGD(learning_rate=1e-3)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])" @@ -2659,7 +2659,7 @@ "model.add(keras.layers.AlphaDropout(rate=0.1))\n", "model.add(keras.layers.Dense(10, activation=\"softmax\"))\n", "\n", - "optimizer = keras.optimizers.SGD(lr=1e-2)\n", + "optimizer = keras.optimizers.SGD(learning_rate=1e-2)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\"])" diff --git a/12_custom_models_and_training_with_tensorflow.ipynb b/12_custom_models_and_training_with_tensorflow.ipynb index bdd8aa5..6f6d6e8 100644 --- a/12_custom_models_and_training_with_tensorflow.ipynb +++ b/12_custom_models_and_training_with_tensorflow.ipynb @@ -2717,7 +2717,7 @@ "n_epochs = 5\n", "batch_size = 32\n", "n_steps = len(X_train) // batch_size\n", - "optimizer = keras.optimizers.Nadam(lr=0.01)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n", "loss_fn = keras.losses.mean_squared_error\n", "mean_loss = keras.metrics.Mean()\n", "metrics = [keras.metrics.MeanAbsoluteError()]" @@ -3828,7 +3828,7 @@ "n_epochs = 5\n", "batch_size = 32\n", "n_steps = len(X_train) // batch_size\n", - "optimizer = keras.optimizers.Nadam(lr=0.01)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n", "loss_fn = keras.losses.sparse_categorical_crossentropy\n", "mean_loss = keras.metrics.Mean()\n", "metrics = [keras.metrics.SparseCategoricalAccuracy()]" @@ -3913,8 +3913,8 @@ "metadata": {}, "outputs": [], "source": [ - "lower_optimizer = keras.optimizers.SGD(lr=1e-4)\n", - "upper_optimizer = keras.optimizers.Nadam(lr=1e-3)" + "lower_optimizer = keras.optimizers.SGD(learning_rate=1e-4)\n", + "upper_optimizer = keras.optimizers.Nadam(learning_rate=1e-3)" ] }, { diff --git a/13_loading_and_preprocessing_data.ipynb b/13_loading_and_preprocessing_data.ipynb index 65b7b3b..02ab9bb 100644 --- a/13_loading_and_preprocessing_data.ipynb +++ b/13_loading_and_preprocessing_data.ipynb @@ -559,7 +559,7 @@ "metadata": {}, "outputs": [], "source": [ - "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1e-3))" + "model.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1e-3))" ] }, { @@ -601,7 +601,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=0.01)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n", "loss_fn = keras.losses.mean_squared_error\n", "\n", "n_epochs = 5\n", @@ -637,7 +637,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=0.01)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n", "loss_fn = keras.losses.mean_squared_error\n", "\n", "@tf.function\n", @@ -674,7 +674,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=0.01)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.01)\n", "loss_fn = keras.losses.mean_squared_error\n", "\n", "@tf.function\n", @@ -1687,7 +1687,7 @@ " keras.layers.Dense(1)\n", "])\n", "model.compile(loss=\"mse\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])\n", "model.fit(dataset, steps_per_epoch=len(X_train) // batch_size, epochs=5)" ] @@ -1824,7 +1824,7 @@ " keras.layers.Lambda(lambda images: tf.cast(images, tf.float32)),\n", " keras.layers.Dense(10, activation=\"softmax\")])\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-3),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n", " metrics=[\"accuracy\"])\n", "model.fit(mnist_train, steps_per_epoch=60000 // 32, epochs=5)" ] diff --git a/14_deep_computer_vision_with_cnns.ipynb b/14_deep_computer_vision_with_cnns.ipynb index 6148c69..ed7ea3b 100644 --- a/14_deep_computer_vision_with_cnns.ipynb +++ b/14_deep_computer_vision_with_cnns.ipynb @@ -1092,7 +1092,7 @@ "for layer in base_model.layers:\n", " layer.trainable = False\n", "\n", - "optimizer = keras.optimizers.SGD(lr=0.2, momentum=0.9, decay=0.01)\n", + "optimizer = keras.optimizers.SGD(learning_rate=0.2, momentum=0.9, decay=0.01)\n", "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer,\n", " metrics=[\"accuracy\"])\n", "history = model.fit(train_set,\n", diff --git a/15_processing_sequences_using_rnns_and_cnns.ipynb b/15_processing_sequences_using_rnns_and_cnns.ipynb index 70fd374..1d63131 100644 --- a/15_processing_sequences_using_rnns_and_cnns.ipynb +++ b/15_processing_sequences_using_rnns_and_cnns.ipynb @@ -305,7 +305,7 @@ " keras.layers.SimpleRNN(1, input_shape=[None, 1])\n", "])\n", "\n", - "optimizer = keras.optimizers.Adam(lr=0.005)\n", + "optimizer = keras.optimizers.Adam(learning_rate=0.005)\n", "model.compile(loss=\"mse\", optimizer=optimizer)\n", "history = model.fit(X_train, y_train, epochs=20,\n", " validation_data=(X_valid, y_valid))" @@ -711,7 +711,7 @@ "def last_time_step_mse(Y_true, Y_pred):\n", " return keras.metrics.mean_squared_error(Y_true[:, -1], Y_pred[:, -1])\n", "\n", - "model.compile(loss=\"mse\", optimizer=keras.optimizers.Adam(lr=0.01), metrics=[last_time_step_mse])\n", + "model.compile(loss=\"mse\", optimizer=keras.optimizers.Adam(learning_rate=0.01), metrics=[last_time_step_mse])\n", "history = model.fit(X_train, Y_train, epochs=20,\n", " validation_data=(X_valid, Y_valid))" ] @@ -1478,7 +1478,7 @@ " keras.layers.LSTM(128),\n", " keras.layers.Dense(len(class_names), activation=\"softmax\")\n", "])\n", - "optimizer = keras.optimizers.SGD(lr=1e-2, clipnorm=1.)\n", + "optimizer = keras.optimizers.SGD(learning_rate=1e-2, clipnorm=1.)\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", " optimizer=optimizer,\n", " metrics=[\"accuracy\", \"sparse_top_k_categorical_accuracy\"])\n", @@ -1818,7 +1818,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=1e-3)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=1e-3)\n", "model.compile(loss=\"sparse_categorical_crossentropy\", optimizer=optimizer,\n", " metrics=[\"accuracy\"])\n", "model.fit(train_set, epochs=20, validation_data=valid_set)" diff --git a/16_nlp_with_rnns_and_attention.ipynb b/16_nlp_with_rnns_and_attention.ipynb index 57d4da3..3c03bc3 100644 --- a/16_nlp_with_rnns_and_attention.ipynb +++ b/16_nlp_with_rnns_and_attention.ipynb @@ -1531,7 +1531,7 @@ " keras.layers.GRU(30),\n", " keras.layers.Dense(1, activation=\"sigmoid\")\n", "])\n", - "optimizer = keras.optimizers.SGD(lr=0.02, momentum = 0.95, nesterov=True)\n", + "optimizer = keras.optimizers.SGD(learning_rate=0.02, momentum = 0.95, nesterov=True)\n", "model.compile(loss=\"binary_crossentropy\", optimizer=optimizer, metrics=[\"accuracy\"])\n", "history = model.fit(X_train, y_train, epochs=20, validation_data=(X_valid, y_valid))" ] diff --git a/17_autoencoders_and_gans.ipynb b/17_autoencoders_and_gans.ipynb index 44bd0ac..2af152d 100644 --- a/17_autoencoders_and_gans.ipynb +++ b/17_autoencoders_and_gans.ipynb @@ -174,7 +174,7 @@ "decoder = keras.models.Sequential([keras.layers.Dense(3, input_shape=[2])])\n", "autoencoder = keras.models.Sequential([encoder, decoder])\n", "\n", - "autoencoder.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(lr=1.5))" + "autoencoder.compile(loss=\"mse\", optimizer=keras.optimizers.SGD(learning_rate=1.5))" ] }, { @@ -282,7 +282,7 @@ "])\n", "stacked_ae = keras.models.Sequential([stacked_encoder, stacked_decoder])\n", "stacked_ae.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1.5), metrics=[rounded_accuracy])\n", + " optimizer=keras.optimizers.SGD(learning_rate=1.5), metrics=[rounded_accuracy])\n", "history = stacked_ae.fit(X_train, X_train, epochs=20,\n", " validation_data=(X_valid, X_valid))" ] @@ -448,7 +448,7 @@ "tied_ae = keras.models.Sequential([tied_encoder, tied_decoder])\n", "\n", "tied_ae.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1.5), metrics=[rounded_accuracy])\n", + " optimizer=keras.optimizers.SGD(learning_rate=1.5), metrics=[rounded_accuracy])\n", "history = tied_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" ] @@ -508,10 +508,10 @@ "X_valid_flat = K.batch_flatten(X_valid)\n", "enc1, dec1, X_train_enc1, X_valid_enc1 = train_autoencoder(\n", " 100, X_train_flat, X_valid_flat, \"binary_crossentropy\",\n", - " keras.optimizers.SGD(lr=1.5), output_activation=\"sigmoid\",\n", + " keras.optimizers.SGD(learning_rate=1.5), output_activation=\"sigmoid\",\n", " metrics=[rounded_accuracy])\n", "enc2, dec2, _, _ = train_autoencoder(\n", - " 30, X_train_enc1, X_valid_enc1, \"mse\", keras.optimizers.SGD(lr=0.05),\n", + " 30, X_train_enc1, X_valid_enc1, \"mse\", keras.optimizers.SGD(learning_rate=0.05),\n", " output_activation=\"selu\")" ] }, @@ -545,7 +545,7 @@ "outputs": [], "source": [ "stacked_ae_1_by_1.compile(loss=\"binary_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=0.1), metrics=[rounded_accuracy])\n", + " optimizer=keras.optimizers.SGD(learning_rate=0.1), metrics=[rounded_accuracy])\n", "history = stacked_ae_1_by_1.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" ] @@ -601,7 +601,7 @@ "])\n", "conv_ae = keras.models.Sequential([conv_encoder, conv_decoder])\n", "\n", - "conv_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.0),\n", + "conv_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.0),\n", " metrics=[rounded_accuracy])\n", "history = conv_ae.fit(X_train, X_train, epochs=5,\n", " validation_data=(X_valid, X_valid))" @@ -708,7 +708,7 @@ " keras.layers.Reshape([28, 28])\n", "])\n", "denoising_ae = keras.models.Sequential([denoising_encoder, denoising_decoder])\n", - "denoising_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.0),\n", + "denoising_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.0),\n", " metrics=[rounded_accuracy])\n", "history = denoising_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" @@ -756,7 +756,7 @@ " keras.layers.Reshape([28, 28])\n", "])\n", "dropout_ae = keras.models.Sequential([dropout_encoder, dropout_decoder])\n", - "dropout_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.0),\n", + "dropout_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.0),\n", " metrics=[rounded_accuracy])\n", "history = dropout_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" @@ -810,7 +810,7 @@ " keras.layers.Reshape([28, 28])\n", "])\n", "simple_ae = keras.models.Sequential([simple_encoder, simple_decoder])\n", - "simple_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.),\n", + "simple_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.),\n", " metrics=[rounded_accuracy])\n", "history = simple_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" @@ -923,7 +923,7 @@ " keras.layers.Reshape([28, 28])\n", "])\n", "sparse_l1_ae = keras.models.Sequential([sparse_l1_encoder, sparse_l1_decoder])\n", - "sparse_l1_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.0),\n", + "sparse_l1_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.0),\n", " metrics=[rounded_accuracy])\n", "history = sparse_l1_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" @@ -1019,7 +1019,7 @@ " keras.layers.Reshape([28, 28])\n", "])\n", "sparse_kl_ae = keras.models.Sequential([sparse_kl_encoder, sparse_kl_decoder])\n", - "sparse_kl_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(lr=1.0),\n", + "sparse_kl_ae.compile(loss=\"binary_crossentropy\", optimizer=keras.optimizers.SGD(learning_rate=1.0),\n", " metrics=[rounded_accuracy])\n", "history = sparse_kl_ae.fit(X_train, X_train, epochs=10,\n", " validation_data=(X_valid, X_valid))" diff --git a/18_reinforcement_learning.ipynb b/18_reinforcement_learning.ipynb index 9ace933..4d36515 100644 --- a/18_reinforcement_learning.ipynb +++ b/18_reinforcement_learning.ipynb @@ -871,7 +871,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Adam(lr=0.01)\n", + "optimizer = keras.optimizers.Adam(learning_rate=0.01)\n", "loss_fn = keras.losses.binary_crossentropy" ] }, @@ -1389,7 +1389,7 @@ "source": [ "batch_size = 32\n", "discount_rate = 0.95\n", - "optimizer = keras.optimizers.Adam(lr=1e-2)\n", + "optimizer = keras.optimizers.Adam(learning_rate=1e-2)\n", "loss_fn = keras.losses.mean_squared_error\n", "\n", "def training_step(batch_size):\n", @@ -1534,7 +1534,7 @@ "source": [ "batch_size = 32\n", "discount_rate = 0.95\n", - "optimizer = keras.optimizers.Adam(lr=6e-3)\n", + "optimizer = keras.optimizers.Adam(learning_rate=6e-3)\n", "loss_fn = keras.losses.Huber()\n", "\n", "def training_step(batch_size):\n", @@ -1682,7 +1682,7 @@ "source": [ "batch_size = 32\n", "discount_rate = 0.95\n", - "optimizer = keras.optimizers.Adam(lr=7.5e-3)\n", + "optimizer = keras.optimizers.Adam(learning_rate=7.5e-3)\n", "loss_fn = keras.losses.Huber()\n", "\n", "def training_step(batch_size):\n", @@ -2207,7 +2207,7 @@ "\n", "train_step = tf.Variable(0)\n", "update_period = 4 # run a training step every 4 collect steps\n", - "optimizer = keras.optimizers.RMSprop(lr=2.5e-4, rho=0.95, momentum=0.0,\n", + "optimizer = keras.optimizers.RMSprop(learning_rate=2.5e-4, rho=0.95, momentum=0.0,\n", " epsilon=0.00001, centered=True)\n", "epsilon_fn = keras.optimizers.schedules.PolynomialDecay(\n", " initial_learning_rate=1.0, # initial ε\n", @@ -3032,7 +3032,7 @@ "metadata": {}, "outputs": [], "source": [ - "optimizer = keras.optimizers.Nadam(lr=0.005)\n", + "optimizer = keras.optimizers.Nadam(learning_rate=0.005)\n", "loss_fn = keras.losses.sparse_categorical_crossentropy" ] }, diff --git a/19_training_and_deploying_at_scale.ipynb b/19_training_and_deploying_at_scale.ipynb index ccffc56..526c725 100644 --- a/19_training_and_deploying_at_scale.ipynb +++ b/19_training_and_deploying_at_scale.ipynb @@ -146,7 +146,7 @@ " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-2),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-2),\n", " metrics=[\"accuracy\"])\n", "model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))" ] @@ -535,7 +535,7 @@ " keras.layers.Dense(10, activation=\"softmax\")\n", "])\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-2),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-2),\n", " metrics=[\"accuracy\"])\n", "history = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))" ] @@ -783,7 +783,7 @@ "batch_size = 100\n", "model = create_model()\n", "model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-2),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-2),\n", " metrics=[\"accuracy\"])\n", "model.fit(X_train, y_train, epochs=10,\n", " validation_data=(X_valid, y_valid), batch_size=batch_size)" @@ -823,7 +823,7 @@ "with distribution.scope():\n", " model = create_model()\n", " model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-2),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-2),\n", " metrics=[\"accuracy\"])" ] }, @@ -1075,7 +1075,7 @@ " keras.layers.Dense(units=10, activation='softmax'),\n", " ])\n", " model.compile(loss=\"sparse_categorical_crossentropy\",\n", - " optimizer=keras.optimizers.SGD(lr=1e-2),\n", + " optimizer=keras.optimizers.SGD(learning_rate=1e-2),\n", " metrics=[\"accuracy\"])\n", "\n", "model.fit(X_train, y_train, validation_data=(X_valid, y_valid),\n",