diff --git a/notebooks/wut-train-cluster-fn.ipynb b/notebooks/wut-train-cluster-fn.ipynb index 4b187d9..8e5fe61 100644 --- a/notebooks/wut-train-cluster-fn.ipynb +++ b/notebooks/wut-train-cluster-fn.ipynb @@ -126,16 +126,6 @@ "options = tf.data.Options()" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#from tensorflow.python.framework.ops import disable_eager_execution\n", - "#disable_eager_execution()" - ] - }, { "cell_type": "code", "execution_count": null, @@ -143,18 +133,7 @@ "outputs": [], "source": [ "strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy(\n", - " tf.distribute.experimental.CollectiveCommunication.RING)\n", - "#\n", - "# MultiWorkerMirroredStrategy needs TF_CONFIG\n", - "#multiworker_strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy()\n", - "# Central Storage Strategy\n", - "#central_storage_strategy = tf.distribute.experimental.CentralStorageStrategy()\n", - "# ParameterServerStrategy needs TF_CONFIG\n", - "#ps_strategy = tf.distribute.experimental.ParameterServerStrategy()\n", - "# OneDeviceStrategy No cluster\n", - "#strategy = tf.distribute.OneDeviceStrategy(device=\"/CPU:0\")\n", - "# Mirrored Strategy\n", - "#mirrored_strategy = tf.distribute.MirroredStrategy()" + " tf.distribute.experimental.CollectiveCommunication.RING)" ] }, { @@ -260,8 +239,8 @@ " plt.tight_layout()\n", " plt.show()\n", " \n", - "#plotImages(sample_train_images[0:3])\n", - "#plotImages(sample_val_images[0:3])" + "plotImages(sample_train_images[0:3])\n", + "plotImages(sample_val_images[0:3])" ] }, { @@ -276,7 +255,7 @@ "log_dir=\"clusterlogs\"\n", "#tensorboard_callback = tensorflow.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)\n", "tensorboard_callback = tensorflow.keras.callbacks.TensorBoard(log_dir=log_dir)\n", - "#%tensorboard --logdir clusterlogs --port 6006" + "%tensorboard --logdir clusterlogs --port 6006" ] }, { @@ -358,15 +337,6 @@ " return model" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#model = get_compiled_model()" - ] - }, { "cell_type": "code", "execution_count": null, @@ -407,50 +377,6 @@ "#return model" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#with strategy.scope():\n", - "# get_uncompiled_model()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#with strategy.scope():\n", - "# get_compiled_model()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#with strategy.scope():\n", - "# get_fit_model()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#multi_worker_model = get_compiled_model()\n", - "#multi_worker_model.fit(\n", - "# x=train_data_gen,\n", - "# epochs=epochs,\n", - "# steps_per_epoch=total_train // batch_size\n", - "# )" - ] - }, { "cell_type": "code", "execution_count": null, @@ -469,21 +395,6 @@ " )" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "#with strategy.scope():\n", - "# multi_worker_model = get_compiled_model()\n", - "# multi_worker_model.fit(\n", - "# x=train_data_gen,\n", - "# epochs=epochs,\n", - "# steps_per_epoch=total_train // batch_size\n", - "# )" - ] - }, { "cell_type": "code", "execution_count": null,