mirror of
https://github.com/clearml/clearml
synced 2025-01-31 17:17:00 +00:00
300 lines
83 KiB
Plaintext
300 lines
83 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Trains - Example of integrating plots and training on jupyter notebook. \n",
|
|
"# In this example, simple graphs are shown, then an MNIST classifier is trained using Keras. \n",
|
|
"!pip install -U pip\n",
|
|
"!pip install -U trains\n",
|
|
"!pip install -U numpy==1.18.0\n",
|
|
"!pip install -U tensorflow==2.0.0\n",
|
|
"!pip install -U tensorboard==2.0.0\n",
|
|
"!pip install -U matplotlib==3.1.2"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from tensorflow.keras.callbacks import TensorBoard, ModelCheckpoint\n",
|
|
"from tensorflow.keras.datasets import mnist\n",
|
|
"from tensorflow.keras.models import Sequential\n",
|
|
"from tensorflow.keras.layers import Dense, Dropout, Activation\n",
|
|
"from tensorflow.keras.optimizers import SGD, Adam, RMSprop\n",
|
|
"from tensorflow.keras.utils import to_categorical\n",
|
|
"\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"TRAINS Task: created new task id=83ebee675e9f4b50af88da70be6a30d6\n",
|
|
"2020-01-05 17:51:21,909 - trains.Task - INFO - No repository found, storing script code instead\n",
|
|
"TRAINS results page: https://demoapp.trains.allegro.ai/projects/087f765c846c4c76a7e9f3d035667d82/experiments/83ebee675e9f4b50af88da70be6a30d6/output/log\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Connecting TRAINS\n",
|
|
"from trains import Task\n",
|
|
"task = Task.init(project_name = 'examples', task_name = 'notebook example')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"TRAINS Monitor: GPU monitoring failed getting GPU reading, switching off GPU monitoring\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Set script parameters\n",
|
|
"task_params = {'num_scatter_samples': 60, 'sin_max_value': 20, 'sin_steps': 30}\n",
|
|
"task_params = task.connect(task_params)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"image/png": "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\n",
|
|
"text/plain": [
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
]
|
|
},
|
|
"metadata": {
|
|
"needs_background": "light"
|
|
},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"%matplotlib inline\n",
|
|
"N = task_params['num_scatter_samples']\n",
|
|
"x = np.random.rand(N)\n",
|
|
"y = np.random.rand(N)\n",
|
|
"colors = np.random.rand(N)\n",
|
|
"area = (50 * np.random.rand(N))**2 # 0 to 15 point radii\n",
|
|
"plt.scatter(x, y, s=area, c=colors, alpha=0.5)\n",
|
|
"plt.title('Nice Circles')\n",
|
|
"plt.show()\n",
|
|
"\n",
|
|
"x = np.linspace(0, task_params['sin_max_value'], task_params['sin_steps'])\n",
|
|
"y = np.sin(x)\n",
|
|
"plt.plot(x, y, 'o', color='black')\n",
|
|
"plt.title('Sinus Dots')\n",
|
|
"plt.show()\n",
|
|
"\n",
|
|
"m = np.eye(32, 32, dtype=np.uint8)\n",
|
|
"plt.imshow(m)\n",
|
|
"plt.title('sample output')\n",
|
|
"plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Notice, Updating task_params is traced and updated in TRAINS\n",
|
|
"task_params['batch_size'] = 128\n",
|
|
"task_params['nb_classes'] = 10\n",
|
|
"task_params['nb_epoch'] = 6\n",
|
|
"task_params['hidden_dim'] = 512\n",
|
|
"batch_size = task_params['batch_size']\n",
|
|
"nb_classes = task_params['nb_classes']\n",
|
|
"nb_epoch = task_params['nb_epoch']"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"60000 train samples\n",
|
|
"10000 test samples\n",
|
|
"Model: \"sequential\"\n",
|
|
"_________________________________________________________________\n",
|
|
"Layer (type) Output Shape Param # \n",
|
|
"=================================================================\n",
|
|
"dense (Dense) (None, 512) 401920 \n",
|
|
"_________________________________________________________________\n",
|
|
"activation (Activation) (None, 512) 0 \n",
|
|
"_________________________________________________________________\n",
|
|
"dense_1 (Dense) (None, 512) 262656 \n",
|
|
"_________________________________________________________________\n",
|
|
"activation_1 (Activation) (None, 512) 0 \n",
|
|
"_________________________________________________________________\n",
|
|
"dense_2 (Dense) (None, 10) 5130 \n",
|
|
"_________________________________________________________________\n",
|
|
"activation_2 (Activation) (None, 10) 0 \n",
|
|
"=================================================================\n",
|
|
"Total params: 669,706\n",
|
|
"Trainable params: 669,706\n",
|
|
"Non-trainable params: 0\n",
|
|
"_________________________________________________________________\n",
|
|
"Train on 60000 samples, validate on 10000 samples\n",
|
|
"Epoch 1/6\n",
|
|
"59264/60000 [============================>.] - ETA: 0s - loss: 0.2217 - accuracy: 0.93122020-01-05 17:51:43,884 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:43,906 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:43,909 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 6s 99us/sample - loss: 0.2206 - accuracy: 0.9316 - val_loss: 0.1300 - val_accuracy: 0.9586\n",
|
|
"Epoch 2/6\n",
|
|
"59264/60000 [============================>.] - ETA: 0s - loss: 0.0808 - accuracy: 0.97512020-01-05 17:51:49,017 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:49,039 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:49,043 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 5s 84us/sample - loss: 0.0804 - accuracy: 0.9752 - val_loss: 0.0794 - val_accuracy: 0.9765\n",
|
|
"Epoch 3/6\n",
|
|
"59648/60000 [============================>.] - ETA: 0s - loss: 0.0542 - accuracy: 0.98342020-01-05 17:51:54,222 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:54,245 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:54,248 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 5s 87us/sample - loss: 0.0540 - accuracy: 0.9834 - val_loss: 0.0758 - val_accuracy: 0.9782\n",
|
|
"Epoch 4/6\n",
|
|
"59392/60000 [============================>.] - ETA: 0s - loss: 0.0388 - accuracy: 0.98762020-01-05 17:51:59,298 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:59,320 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:51:59,324 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 5s 84us/sample - loss: 0.0387 - accuracy: 0.9876 - val_loss: 0.0836 - val_accuracy: 0.9777\n",
|
|
"Epoch 5/6\n",
|
|
"59520/60000 [============================>.] - ETA: 0s - loss: 0.0282 - accuracy: 0.99142020-01-05 17:52:04,410 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:52:04,433 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:52:04,436 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 5s 85us/sample - loss: 0.0280 - accuracy: 0.9915 - val_loss: 0.0754 - val_accuracy: 0.9811\n",
|
|
"Epoch 6/6\n",
|
|
"59520/60000 [============================>.] - ETA: 0s - loss: 0.0242 - accuracy: 0.99252020-01-05 17:52:09,482 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:52:09,504 - trains - WARNING - too many indices for array\n",
|
|
"2020-01-05 17:52:09,507 - trains - WARNING - too many indices for array\n",
|
|
"60000/60000 [==============================] - 5s 85us/sample - loss: 0.0243 - accuracy: 0.9924 - val_loss: 0.0769 - val_accuracy: 0.9824\n",
|
|
"Test score: 0.07691321085649504\n",
|
|
"Test accuracy: 0.9824\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# the data, shuffled and split between train and test sets\n",
|
|
"(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
|
|
"\n",
|
|
"X_train = X_train.reshape(60000, 784)\n",
|
|
"X_test = X_test.reshape(10000, 784)\n",
|
|
"X_train = X_train.astype('float32')\n",
|
|
"X_test = X_test.astype('float32')\n",
|
|
"X_train /= 255.\n",
|
|
"X_test /= 255.\n",
|
|
"print(X_train.shape[0], 'train samples')\n",
|
|
"print(X_test.shape[0], 'test samples')\n",
|
|
"\n",
|
|
"# convert class vectors to binary class matrices\n",
|
|
"Y_train = to_categorical(y_train, nb_classes)\n",
|
|
"Y_test = to_categorical(y_test, nb_classes)\n",
|
|
"\n",
|
|
"hidden_dim = task_params['hidden_dim']\n",
|
|
"model = Sequential()\n",
|
|
"model.add(Dense(hidden_dim, input_shape=(784,)))\n",
|
|
"model.add(Activation('relu'))\n",
|
|
"# model.add(Dropout(0.2))\n",
|
|
"model.add(Dense(hidden_dim))\n",
|
|
"model.add(Activation('relu'))\n",
|
|
"# model.add(Dropout(0.2))\n",
|
|
"model.add(Dense(10))\n",
|
|
"model.add(Activation('softmax'))\n",
|
|
"\n",
|
|
"model.summary()\n",
|
|
"\n",
|
|
"model.compile(loss='categorical_crossentropy',\n",
|
|
" optimizer=RMSprop(),\n",
|
|
" metrics=['accuracy'])\n",
|
|
"\n",
|
|
"board = TensorBoard(histogram_freq=1, log_dir='/tmp/histogram_example')\n",
|
|
"model_store = ModelCheckpoint(filepath='/tmp/weight.{epoch}.hdf5')\n",
|
|
"\n",
|
|
"model.fit(X_train, Y_train,\n",
|
|
" batch_size=batch_size, epochs=nb_epoch,\n",
|
|
" callbacks=[board, model_store],\n",
|
|
" verbose=1, validation_data=(X_test, Y_test))\n",
|
|
"score = model.evaluate(X_test, Y_test, verbose=0)\n",
|
|
"print('Test score:', score[0])\n",
|
|
"print('Test accuracy:', score[1])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "conda_python3",
|
|
"language": "python",
|
|
"name": "conda_python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.6.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|