I am not sure , whether this question follow any logic as per the design of Tensorflow . Here is the Code
import numpy as np
import tensorflow as tf
np.random.seed(0)
tf.set_random_seed(0)
class Sample():
def __init__(self, hidden_dim = 50 , input_dim = 784):
self.hidden_dim = hidden_dim
self.input_dim = input_dim
self.x = tf.placeholder(tf.float32, [None, self.input_dim])
self._create_network()
self.__minimize()
self.sess = tf.InteractiveSession()
init = tf.initialize_all_variables()
self.sess.run(init)
def _create_network(self):
self.W1 = tf.Variable(tf.random_normal([self.input_dim, self.hidden_dim]))
self.W2 = tf.Variable(tf.random_normal([self.hidden_dim, self.input_dim]))
def __minimize(self):
h1 = tf.matmul(self.x , self.W1)
h2 = tf.matmul(h1, self.W2)
reconstruction = tf.nn.sigmoid(h2)
self.loss = tf.reduce_mean(tf.squared_difference(self.x , reconstruction))
self.optimizer = \
tf.train.AdamOptimizer(learning_rate=0.01).minimize(self.loss)
def partial_fit(self, X):
cost , _ = self.sess.run([self.loss, self.optimizer] , feed_dict = {self.x: X})
return cost
import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
n_samples = mnist.train.num_examples
ex_1 = mnist.train.next_batch(1)[0]
model = Sample()
for i in xrange(11):
c = model.partial_fit(ex_1)
print c
The result is as follows :
0.498799
0.469001
0.449659
0.436665
0.424995
0.414473
0.404129
0.394458
0.39165
0.38483
0.380042
This result is achieved with seed 0 and it is same when I restart the kernel . But suppose , if I ran 10 iteration and then , if I have to start it from the scratch , how will i do it in Ipython . Because , if run after 10 or so iterations , the model continues to start from the remaining values .
I used tf.reset_default_graph() , but that has not make any change to the behavior .
Don't use an InterativeSession but use a normal Session.
Create a new Session each time with the same seed and you will get the same results.
graph = tf.Graph()
with graph.as_default():
model = Sample()
with Session(graph=graph) as sess:
np.random.seed(0)
tf.set_random_seed(0)
for i in xrange(11):
c = model.partial_fit(ex_1)
print c
Related
I am learning neural network modeling and its uses in time series prediction.
First, thank you for reading this post and for your help :)
On this page there are various NN models (LSTM, CNN etc.) for predicting "traffic volume":
https://michael-fuchs-python.netlify.app/2020/11/01/time-series-analysis-neural-networks-for-forecasting-univariate-variables/#train-validation-split
I got inspired and decided to use/shorten/adapt the code in there for a problem of my own: predicting the bitcoin price.
I have the bitcoin daily prices starting 1.1.2017
in total 2024 daily prices
I use the first 85% of the data for the training data, and the rest as the validation (except the last 10 observation, which I would like to use as test data to see how good my model is)
I would like to use a Feedforward model
My goal is merely having a code that runs.
I have managed so far to have most of my code run. However, I get a strange format for my test forecast results: It should be simply an array of 10 numbers (i.e. predicted prices corresponding to the 10 day at the end of my data). To my surprise what is printed out is a long list of numbers. I need help to find out what changes I need to make to make to the code to make it run.
Thank you for helping me :)
The code is pasted down there, followed by the error:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import preprocessing #import MinMaxScaler
from sklearn import metrics #import mean_squared_error
import seaborn as sns
sns.set()
import tensorflow as tf
from tensorflow import keras
from keras.layers import Input, Dense, Flatten
from keras.optimizers import Adam
from keras.models import Sequential
from keras.callbacks import EarlyStopping
tf.__version__
df = pd.read_csv('/content/BTC-USD.csv')
def mean_absolute_percentage_error_func(y_true, y_pred):
y_true, y_pred = np.array(y_true), np.array(y_pred)
return np.mean(np.abs((y_true - y_pred) / y_true)) * 100
def timeseries_evaluation_metrics_func(y_true, y_pred):
print('Evaluation metric results: ')
print(f'MSE is : {metrics.mean_squared_error(y_true, y_pred)}')
print(f'MAE is : {metrics.mean_absolute_error(y_true, y_pred)}')
print(f'RMSE is : {np.sqrt(metrics.mean_squared_error(y_true, y_pred))}')
print(f'MAPE is : {mean_absolute_percentage_error_func(y_true, y_pred)}')
print(f'R2 is : {metrics.r2_score(y_true, y_pred)}',end='\n\n')
def univariate_data_prep_func(dataset, start, end, window, horizon):
X = []
y = []
start = start + window
if end is None:
end = len(dataset) - horizon
for i in range(start, end):
indicesx = range(i-window, i)
X.append(np.reshape(dataset[indicesx], (window, 1)))
indicesy = range(i,i+horizon)
y.append(dataset[indicesy])
return np.array(X), np.array(y)
# Generating the test set
test_data = df['close'].tail(10)
df = df.drop(df['close'].tail(10).index)
df.shape
# Defining the target variable
uni_data = df['close']
uni_data.index = df['formatted_date']
uni_data.head()
#scaling
from sklearn import preprocessing
uni_data = uni_data.values
scaler_x = preprocessing.MinMaxScaler()
x_scaled = scaler_x.fit_transform(uni_data.reshape(-1, 1))
# Single Step Style (sss) modeling
univar_hist_window_sss = 50
horizon_sss = 1
# 2014 observations in total
# 2014*0.85=1710 should be part of the training (304 validation)
train_split_sss = 1710
x_train_uni_sss, y_train_uni_sss = univariate_data_prep_func(x_scaled, 0, train_split_sss,
univar_hist_window_sss, horizon_sss)
x_val_uni_sss, y_val_uni_sss = univariate_data_prep_func(x_scaled, train_split_sss, None,
univar_hist_window_sss, horizon_sss)
print ('Length of first Single Window:')
print (len(x_train_uni_sss[0]))
print()
print ('Target horizon:')
print (y_train_uni_sss[0])
BATCH_SIZE_sss = 32
BUFFER_SIZE_sss = 150
train_univariate_sss = tf.data.Dataset.from_tensor_slices((x_train_uni_sss, y_train_uni_sss))
train_univariate_sss = train_univariate_sss.cache().shuffle(BUFFER_SIZE_sss).batch(BATCH_SIZE_sss).repeat()
validation_univariate_sss = tf.data.Dataset.from_tensor_slices((x_val_uni_sss, y_val_uni_sss))
validation_univariate_sss = validation_univariate_sss.batch(BATCH_SIZE_sss).repeat()
n_steps_per_epoch = 55
n_validation_steps = 10
n_epochs = 100
#FFNN architecture
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(8, input_shape=x_train_uni_sss.shape[-2:]),
tf.keras.layers.Dense(units=horizon_sss)])
model.compile(loss='mse',
optimizer='adam')
#fit the model
model_path = '/content/FFNN_model_sss.h5'
keras_callbacks = [tf.keras.callbacks.EarlyStopping(monitor='val_loss',
min_delta=0, patience=10,
verbose=1, mode='min'),
tf.keras.callbacks.ModelCheckpoint(model_path,monitor='val_loss',
save_best_only=True,
mode='min', verbose=0)]
history = model.fit(train_univariate_sss, epochs=n_epochs, steps_per_epoch=n_steps_per_epoch,
validation_data=validation_univariate_sss, validation_steps=n_validation_steps, verbose =1,
callbacks = keras_callbacks)
#validation
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(loss) + 1)
plt.plot(epochs, loss, 'r', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()
# Testing our model
trained_ffnn_model_sss = tf.keras.models.load_model(model_path)
df_temp = df['close']
test_horizon = df_temp.tail(univar_hist_window_sss)
test_history = test_horizon.values
result = []
# Define Forecast length here
window_len = len(test_data)
test_scaled = scaler_x.fit_transform(test_history.reshape(-1, 1))
for i in range(1, window_len+1):
test_scaled = test_scaled.reshape((1, test_scaled.shape[0], 1))
# Inserting the model
predicted_results = trained_ffnn_model_sss.predict(test_scaled)
print(f'predicted : {predicted_results}')
result.append(predicted_results[0])
test_scaled = np.append(test_scaled[:,1:],[[predicted_results]])
result_inv_trans = scaler_x.inverse_transform(result)
result_inv_trans
I believe the problem might have to do with the shapes of data. How exactly I do not yet know.
Data:
click here
Traceback:
click here
I am getting an error when i run the below code. The error says
MisconfigurationException: No training_step() method defined. Lightning Trainer expects as minimum a training_step(), train_dataloader() and configure_optimizers() to be defined.
Can someone please let me know what is the issue here? I am very new to Pytorch. I am trying to simulate Sin wave using MLP
import numpy as np ## using again numpy library for Sin function
import torch ## using pytorch
import matplotlib.pyplot as plt
import pytorch_lightning as pl
import torch.optim as optim
from torch import nn
from pytorch_lightning import Trainer
from sklearn.model_selection import train_test_split
import pandas as pd
from torch.utils.data import DataLoader
N=1000 ## 1000 samples to be generated
L=1000 ## length of each sample
T=20 ## width of wave
x = np.random.randn(1000)
y = np.sin(x)
df = pd.DataFrame({'x':x, 'y':y})
train, test = train_test_split(df, test_size=0.2, random_state=42, shuffle=True)
target_fields=['y']
train_features, train_targets = train.drop(target_fields, axis=1), train[target_fields]
test_features, test_targets = test.drop(target_fields, axis=1), test[target_fields]
class MLP(pl.LightningModule):
def __init__(self):
super(MLP,self).__init__()
self.fc1 = nn.Linear(1, 10)
self.fc2 = nn.Linear(10, 1)
def forward(self, x):
x = torch.Relu(self.fc1(x))
x = self.fc2(x)
return x
l_rate = 0.2
mse_loss = nn.MSELoss(reduction = 'mean')
def train_dataloader(self):
train_dataset = TensorDataset(torch.tensor(train_features.values).float(), torch.tensor(train_targets[['cnt']].values).float())
train_loader = DataLoader(dataset = train_dataset, batch_size = 128)
return train_loader
def test_dataloader(self):
test_dataset = TensorDataset(torch.tensor(test_features.values).float(), torch.tensor(test_targets[['cnt']].values).float())
test_loader = DataLoader(dataset = test_dataset, batch_size = 128)
return test_loader
def configure_optimizers(self):
return optim.SGD(self.parameters(), lr=l_rate)
def training_step(self, batch, batch_idx):
x, y = batch
logits = self.forward(x)
loss = mse_loss(logits, y)
# Add logging
logs = {'loss': loss}
return {'loss': loss, 'log': logs}
def test_step(self, batch, batch_idx):
x, y = batch
logits = self.forward(x)
loss = mse_loss(logits, y)
correct = torch.sum(logits == y.data)
predictions_pred.append(logits)
predictions_actual.append(y.data)
return {'test_loss': loss, 'test_correct': correct, 'logits': logits}
def test_epoch_end(self, outputs):
avg_loss = torch.stack([x['test_loss'] for x in outputs]).mean()
logs = {'test_loss': avg_loss}
return {'avg_test_loss': avg_loss, 'log': logs, 'progress_bar': logs }
model = MLP()
trainer = Trainer(max_epochs = 50)
trainer.fit(model)
Error
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
---------------------------------------------------------------------------
MisconfigurationException Traceback (most recent call last)
<ipython-input-9-7bdf5ac9771f> in <module>()
1 model = MLP()
2 trainer = Trainer(max_epochs = 50)
----> 3 trainer.fit(model)
3 frames
/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/configuration_validator.py in __verify_train_loop_configuration(self, model)
50 if not has_training_step:
51 raise MisconfigurationException(
---> 52 "No `training_step()` method defined. Lightning `Trainer` expects as minimum a"
53 " `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined."
54 )
MisconfigurationException: No `training_step()` method defined. Lightning `Trainer` expects as minimum a `training_step()`, `train_dataloader()` and `configure_optimizers()` to be defined.
You are missing 2 parameters in your trainer.fit() call. See the documentation
I want to train a model in distributed system. I have found a code in github for distributed training where the worker node send gradient to the parameter server and the parameter server sends the average gradient to the workers. But in client/worker side code, i couldn't understand where the received gradient updates the weights and biases.
Here is client/worker side the code, it receives initial gradients from the parameter server and then calculates loss, gradients and sends the gradient value to the server again.
from __future__ import division
from __future__ import print_function
import numpy as np
import sys
import pickle as pickle
import socket
from datetime import datetime
import time
import tensorflow as tf
import cifar10
TCP_IP = 'some IP'
TCP_PORT = 5014
port = 0
port_main = 0
s = 0
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string('train_dir', '/home/ubuntu/cifar10_train',
"""Directory where to write event logs """
"""and checkpoint.""")
tf.app.flags.DEFINE_integer('max_steps', 5000,
"""Number of batches to run.""")
tf.app.flags.DEFINE_boolean('log_device_placement', False,
"""Whether to log device placement.""")
tf.app.flags.DEFINE_integer('log_frequency', 10,
"""How often to log results to the console.""")
#gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.30)
def safe_recv(size, server_socket):
data = ""
temp = ""
data = bytearray()
recv_size = 0
while 1:
try:
temp = server_socket.recv(size-len(data))
data.extend(temp)
recv_size = len(data)
if recv_size >= size:
break
except:
print("Error")
data = bytes(data)
return data
def train():
"""Train CIFAR-10 for a number of steps."""
g1 = tf.Graph()
with g1.as_default():
global_step = tf.Variable(-1, name='global_step',
trainable=False, dtype=tf.int32)
increment_global_step_op = tf.assign(global_step, global_step+1)
# Get images and labels for CIFAR-10.
images, labels = cifar10.distorted_inputs()
# Build a Graph that computes the logits predictions from the
# inference model.
logits = cifar10.inference(images)
# Calculate loss.
loss = cifar10.loss(logits, labels)
grads = cifar10.train_part1(loss, global_step)
only_gradients = [g for g, _ in grads]
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
return tf.train.SessionRunArgs(loss) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % FLAGS.log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
self._start_time = current_time
loss_value = run_values.results
examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
sec_per_batch = float(duration / FLAGS.log_frequency)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
with tf.train.MonitoredTrainingSession(
checkpoint_dir=FLAGS.train_dir,
hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
tf.train.NanTensorHook(loss),
_LoggerHook()],
config=tf.ConfigProto(
# log_device_placement=FLAGS.log_device_placement, gpu_options=gpu_options)) as mon_sess:
log_device_placement=FLAGS.log_device_placement)) as mon_sess:
global port
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect((TCP_IP, port_main))
recv_size = safe_recv(17, s)
recv_size = pickle.loads(recv_size)
recv_data = safe_recv(recv_size, s)
var_vals = pickle.loads(recv_data)
s.close()
feed_dict = {}
i = 0
for v in tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES):
feed_dict[v] = var_vals[i]
i = i+1
print("Received variable values from ps")
# Opening the socket and connecting to server
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.connect((TCP_IP, port))
while not mon_sess.should_stop():
gradients, step_val = mon_sess.run(
[only_gradients, increment_global_step_op], feed_dict=feed_dict)
# sending the gradients
send_data = pickle.dumps(gradients, pickle.HIGHEST_PROTOCOL)
to_send_size = len(send_data)
send_size = pickle.dumps(to_send_size, pickle.HIGHEST_PROTOCOL)
s.sendall(send_size)
s.sendall(send_data)
# receiving the variable values
recv_size = safe_recv(17, s)
recv_size = pickle.loads(recv_size)
recv_data = safe_recv(recv_size, s)
var_vals = pickle.loads(recv_data)
feed_dict = {}
i = 0
for v in tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES):
feed_dict[v] = var_vals[i]
i = i+1
s.close()
def main(argv=None): # pylint: disable=unused-argument
global port
global port_main
global s
if(len(sys.argv) != 3):
print("<port> <worker-id> required")
sys.exit()
port = int(sys.argv[1]) + int(sys.argv[2])
port_main = int(sys.argv[1])
print("Connecting to port ", port)
cifar10.maybe_download_and_extract()
if tf.gfile.Exists(FLAGS.train_dir):
tf.gfile.DeleteRecursively(FLAGS.train_dir)
tf.gfile.MakeDirs(FLAGS.train_dir)
total_start_time = time.time()
train()
print("--- %s seconds ---" % (time.time() - total_start_time))
if __name__ == '__main__':
tf.app.run()
EDIT:
Here is the train_part1() code:
def train_part1(total_loss, global_step):
"""Train CIFAR-10 model.
Create an optimizer and apply to all trainable variables. Add moving
average for all trainable variables.
Args:
total_loss: Total loss from loss().
global_step: Integer Variable counting the number of training steps
processed.
Returns:
train_op: op for training.
"""
# Variables that affect learning rate.
num_batches_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size
decay_steps = int(num_batches_per_epoch * NUM_EPOCHS_PER_DECAY)
# Decay the learning rate exponentially based on the number of steps.
lr = tf.train.exponential_decay(INITIAL_LEARNING_RATE,
global_step,
decay_steps,
LEARNING_RATE_DECAY_FACTOR,
staircase=True)
tf.summary.scalar('learning_rate', lr)
# Generate moving averages of all losses and associated summaries.
loss_averages_op = _add_loss_summaries(total_loss)
# Compute gradients.
with tf.control_dependencies([loss_averages_op]):
opt = tf.train.GradientDescentOptimizer(lr)
grads = opt.compute_gradients(total_loss)
return grads
To me it seems that line
gradients, step_val = mon_sess.run(
[only_gradients, increment_global_step_op], feed_dict=feed_dict)
receieves new values for variables in feed_dict, assign these values to variables, and makes a training step, during which it only calculates and returns the gradients, that are later sent to the parameter server. I would expect cifar10.train_part1 (the one that returns only_gradients) to depend on variable values and define the update.
Update: I looked into the code and changed my mind. Had to google and found next answer that shed some light on what is happening.
Gradients are actually not applied in this code anywhere implicitly. Instead, gradients are sent to the parameter server, parameter server averages gradients and applies them to weights, it returns the weights to the local worker, * recieved weights are used instead of local weights during session run through feed_dict* i.e. local weights are never actually updated and do not actually matter at all. The key, is that feed_dict allows to rewrite any tensor output of the session run and this code rewrites variables.
I want use keras Lstm to get the time series features, then use the features to Kmeans. But now I can not get the layers output values. How can I get the layers output values?
This is my lstm network
Layer (type) Output Shape Param #
lstm_66 (LSTM) (None, None, 50) 10400
lstm_67 (LSTM) (None, 100) 60400
dense_19 (Dense) (None, 1) 101
activation_19 (Activation) (None, 1) 0
I want to get the lstm_67 output values,my code is:
import keras.backend as K
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
import numpy as np
statesAll=[]
layers = model.layers
print layers[1].output,type(layers[1].output[1]),sess.run(layers[1].output)
and the result is:
Tensor("lstm_61/TensorArrayReadV3:0", shape=(?, 100), dtype=float32)
So, how can I get the layers output value?
Thanks!
But it not work,my code is:
def load_data(file_name, sequence_length=10, split=0.8):
df = pd.read_csv(file_name, sep=',', usecols=[1])
data_all = np.array(df).astype(float)
scaler = MinMaxScaler()
data_all = scaler.fit_transform(data_all)
data = []
print len(data_all)
for i in range(len(data_all) - sequence_length - 1):
data.append(data_all[i: i + sequence_length + 1])
reshaped_data = np.array(data).astype('float64')
np.random.shuffle(reshaped_data)
x = reshaped_data[:, :-1]
y = reshaped_data[:, -1]
split_boundary = int(reshaped_data.shape[0] * split)
train_x = x[: split_boundary]
test_x = x[split_boundary:]
train_y = y[: split_boundary]
test_y = y[split_boundary:]
return train_x, train_y, test_x, test_y, scaler
def build_model(n_samples, time_steps, input_dim):
model = Sequential()
model.add(LSTM(input_dim=1, output_dim=50,return_sequences=True))
model.add(LSTM(100, return_sequences=False))
model.add(Dense(output_dim=1))
model.add(Activation('linear'))
model.compile(loss='mse', optimizer='rmsprop')
print(model.layers)
return model
def train_model(train_x, train_y, test_x, test_y):
model = build_model()
model.fit(train_x, train_y, batch_size=128, nb_epoch=30,validation_split=0.1)
return model
train_x, train_y, test_x, test_y, scaler = load_data(file path)
train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
test_x = np.reshape(test_x, (test_x.shape[0], test_x.shape[1], 1))
model = train_model(train_x, train_y, test_x, test_y)
from keras import backend as K
layers = model.layers
K.eval(layers[1].output)
In TensorFlow 2.x, you can do like this:
from tensorflow.python.keras import backend as K
model = build_model()
# lstm_67 is the second layer.
lstm = K.function([model.layers[0].input], [model.layers[1].output])
lstm_output = lstm([test_x])[0]
keras.backend.eval() should do.
Look at the documentation here and here
First of all, this is a tensor, you need to use the tf. Print () method to see the specific value. If you use Spyder, you will not see this information in the console. You need to execute this program in the command line.
I'm trying to use the chainer package for a large project I'm working on. I have read through the tutorial on their website which gives an example of applying it to the MNIST dataset, but it doesn't seem to scale easily to other examples, and there's simply not enough documentation otherwise.
Their example code is as follows:
class MLP(Chain):
def __init__(self, n_units, n_out):
super(MLP, self).__init__(
# the size of the inputs to each layer will be inferred
l1=L.Linear(None, n_units), # n_in -> n_units
l2=L.Linear(None, n_units), # n_units -> n_units
l3=L.Linear(None, n_out), # n_units -> n_out
)
def __call__(self, x):
h1 = F.relu(self.l1(x))
h2 = F.relu(self.l2(h1))
y = self.l3(h2)
return y
train, test = datasets.get_mnist()
train_iter = iterators.SerialIterator(train, batch_size=5, shuffle=True)
test_iter = iterators.SerialIterator(test, batch_size=2, repeat=False, shuffle=False)
model = L.Classifier(MLP(100, 10)) # the input size, 784, is inferred
optimizer = optimizers.SGD()
optimizer.setup(model)
updater = training.StandardUpdater(train_iter, optimizer)
trainer = training.Trainer(updater, (4, 'epoch'), out='result')
trainer.extend(extensions.Evaluator(test_iter, model))
trainer.extend(extensions.LogReport())
trainer.extend(extensions.PrintReport(['epoch', 'main/accuracy', 'validation/main/accuracy']))
trainer.extend(extensions.ProgressBar())
trainer.run()
Could someone point me in the direction of how to simple fit a straight line to a few data points in 2D? If I can understand a simple fit such as this I should be able to scale appropriately.
Thanks for the help!
I pasted simple regression modeling here.
You can use original train data and test data as tuple.
train = (data, label)
Here, data.shape = (Number of data, Number of data dimesion)
And, label.shape = (Number of data,)
Both of their data type should be numpy.float32.
import chainer
from chainer.functions import *
from chainer.links import *
from chainer.optimizers import *
from chainer import training
from chainer.training import extensions
from chainer import reporter
from chainer import datasets
import numpy
class MyNet(chainer.Chain):
def __init__(self):
super(MyNet, self).__init__(
l0=Linear(None, 30, nobias=True),
l1=Linear(None, 1, nobias=True),
)
def __call__(self, x, t):
l0 = self.l0(x)
f0 = relu(l0)
l1 = self.l1(f0)
f1 = flatten(l1)
self.loss = mean_squared_error(f1, t)
reporter.report({'loss': self.loss}, self)
return self.loss
def get_optimizer():
return Adam()
def training_main():
model = MyNet()
optimizer = get_optimizer()
optimizer.setup(model)
train, test = datasets.get_mnist(label_dtype=numpy.float32)
train_iter = chainer.iterators.SerialIterator(train, 50)
test_iter = chainer.iterators.SerialIterator(test, 50,
repeat=False,
shuffle=False)
updater = training.StandardUpdater(train_iter, optimizer)
trainer = training.Trainer(updater, (10, 'epoch'))
trainer.extend(extensions.ProgressBar())
trainer.extend(extensions.Evaluator(test_iter, model))
trainer.extend(
extensions.PlotReport(['main/loss', 'validation/main/loss'],
'epoch'))
trainer.run()
if __name__ == '__main__':
training_main()