I am new to pytorch. The following is the basic example of using nn module to train a simple one-layer model with some random data (from here)
import torch
N, D_in, H, D_out = 64, 1000, 100, 10
x = torch.randn(N, D_in)
y = torch.randn(N, D_out)
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
torch.nn.ReLU(),
torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
for t in range(500):
y_pred = model(x)
loss = loss_fn(y_pred, y)
print(t, loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()
As far as I understand, the batch size is equal to 1 in the example, in other words, a single point (out of 64) is used to calculate gradients and update parameters. My question is: how to modify this example to train the model with the batch size greater than one?
In fact N is the batch size. So you just need to modify N currently its set to 64. So you have in every training batch 64 vectors with size / dim D_in.
I checked the link you posted, you can also take a look at the comments - there is some explanation too :)
# -*- coding: utf-8 -*-
import numpy as np
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random input and output data
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)
# Randomly initialize weights
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)
learning_rate = 1e-6
for t in range(500):
# Forward pass: compute predicted y
h = x.dot(w1)
h_relu = np.maximum(h, 0)
y_pred = h_relu.dot(w2)
# Compute and print loss
loss = np.square(y_pred - y).sum()
print(t, loss)
# Backprop to compute gradients of w1 and w2 with respect to loss
grad_y_pred = 2.0 * (y_pred - y)
grad_w2 = h_relu.T.dot(grad_y_pred)
grad_h_relu = grad_y_pred.dot(w2.T)
grad_h = grad_h_relu.copy()
grad_h[h < 0] = 0
grad_w1 = x.T.dot(grad_h)
# Update weights
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
To include batch size in PyTorch basic examples, the easiest and cleanest way is to use PyTorch torch.utils.data.DataLoader and torch.utils.data.TensorDataset.
Dataset stores the samples and their corresponding labels, and DataLoader wraps an iterable around the Dataset to enable easy access to the samples.
DataLoader will take care of creating batches for you.
Building on your question, there is a complete code snippet, where we iterate over a dataset of 10000 examples for 2 epochs with a batch size of 64:
import torch
from torch.utils.data import DataLoader, TensorDataset
# Create the dataset with N_SAMPLES samples
N_SAMPLES, D_in, H, D_out = 10000, 1000, 100, 10
x = torch.randn(N_SAMPLES, D_in)
y = torch.randn(N_SAMPLES, D_out)
# Define the batch size and the number of epochs
BATCH_SIZE = 64
N_EPOCHS = 2
# Use torch.utils.data to create a DataLoader
# that will take care of creating batches
dataset = TensorDataset(x, y)
dataloader = DataLoader(dataset, batch_size=BATCH_SIZE, shuffle=True)
# Define model, loss and optimizer
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
torch.nn.ReLU(),
torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
# Get the dataset size for printing (it is equal to N_SAMPLES)
dataset_size = len(dataloader.dataset)
# Loop over epochs
for epoch in range(N_EPOCHS):
print(f"Epoch {epoch + 1}\n-------------------------------")
# Loop over batches in an epoch using DataLoader
for id_batch, (x_batch, y_batch) in enumerate(dataloader):
y_batch_pred = model(x_batch)
loss = loss_fn(y_batch_pred, y_batch)
optimizer.zero_grad()
loss.backward()
optimizer.step()
# Every 100 batches, print the loss for this batch
# as well as the number of examples processed so far
if id_batch % 100 == 0:
loss, current = loss.item(), (id_batch + 1)* len(x_batch)
print(f"loss: {loss:>7f} [{current:>5d}/{dataset_size:>5d}]")
The output should be something like:
Epoch 1
-------------------------------
loss: 643.433716 [ 64/10000]
loss: 648.195435 [ 6464/10000]
Epoch 2
-------------------------------
loss: 613.619873 [ 64/10000]
loss: 625.018555 [ 6464/10000]
Related
I have created a simple pytorch classification model with sample datasets generated using sklearns make_classification. Even after training for thousands of epochs the accuracy of the model hovers between 30 and 40 percentage. During training itself the loss value is fluctuating very far and wide. I am wondering why this model is not learning, whether it's due to some logical error in the code.
import torch
from torch.utils.data import Dataset, DataLoader
import torch.nn as nn
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
X,y = make_classification(n_features=15,n_classes=5,n_informative=4)
DEVICE = torch.device('cuda')
epochs = 5000
class CustomDataset(Dataset):
def __init__(self,X,y):
self.X = torch.from_numpy(X)
self.y = torch.from_numpy(y)
def __len__(self):
return len(self.X)
def __getitem__(self, index):
X = self.X[index]
y = self.y[index]
return (X,y)
class Model(nn.Module):
def __init__(self):
super().__init__()
self.l1 = nn.Linear(15,10)
self.l2 = nn.Linear(10,5)
self.relu = nn.ReLU()
def forward(self,x):
x = self.l1(x)
x = self.relu(x)
x = self.l2(x)
x = self.relu(x)
return x
model = Model().double().to(DEVICE)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
loss_function = nn.CrossEntropyLoss()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
train_data = CustomDataset(X_train,y_train)
test_data = CustomDataset(X_test,y_test)
trainloader = DataLoader(train_data, batch_size=32, shuffle=True)
testloader = DataLoader(test_data, batch_size=32, shuffle=True)
for i in range(epochs):
for (x,y) in trainloader:
x = x.to(DEVICE)
y = y.to(DEVICE)
optimizer.zero_grad()
output = model(x)
loss = loss_function(output,y)
loss.backward()
optimizer.step()
if i%200==0:
print("epoch: ",i," Loss: ",loss.item())
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for x, y in testloader:
# calculate outputs by running x through the network
outputs = model(x.to(DEVICE)).to(DEVICE)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += y.size(0)
correct += (predicted == y.to(DEVICE)).sum().item()
print(f'Accuracy of the network on the test data: {100 * correct // total} %')
EDIT
I tried to over-fit my model with only 10 samples (batch_size=5) X,y = make_classification(n_samples=10,n_features=15,n_classes=5,n_informative=4) but now the accuracy decreased to 15-20%. I then normalize the input data between the values 0 and 1 which pushed the accuracy a bit higher but not over 50 percentage. Any idea why this might be happening?
You should not be using ReLU activation on your output layer. Usually softmax activation is used for multi class classification on the final layer, or the logits are fed to the loss function directly without explicitly adding a softmax activation layer.
Try removing the ReLU activation from the final layer.
I am attempting to train EEG data through a transformer network. The input dimensions are 50x16684x60 (seq x batch x features) and the output is 16684x2. Right now I am simply trying to run a basic transformer, and I keep getting an error telling me
RuntimeError: the feature number of src and tgt must be equal to d_model
Why would the source and target feature number ever be equal? Is it possible to run such a dataset through a transformer?
Here is my basic model:
input_size = 60 # seq x batch x features
hidden_size = 32
num_classes = 2
learning_rate = 0.001
batch_size = 64
num_epochs = 2
sequence_length = 50
num_layers = 2
dropout = 0.5
class Transformer(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, num_classes):
super(Transformer, self).__init__()
self.hidden_size = hidden_size
self.num_layers = num_layers
self.transformer = nn.Transformer(60, 2)
self.fc = nn.Linear(hidden_size * sequence_length, num_classes)
def forward(self, x, y):
# Forward Propogation
out, _ = self.transformer(x,y)
out = out.reshape(out.shape[0], -1)
out = self.fc(out)
return out
model = Transformer(input_size, hidden_size, num_layers, num_classes)
criterion = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)
for epoch in range(num_epochs):
for index in tqdm(range(16684)):
X, y = (X_train[index], Y_train[index])
print(X.shape, y.shape)
output = model(X, y)
loss = criterion(output, y)
model.zero_grad()
loss.backward()
optimizer.step()
if index % 500 == 0:
print(f"Epoch {epoch}, Batch: {index}, Loss: {loss}")
You train the model to find some features by feeding it the input sequence and desired sequence. The backprop trains the net by computing the loss as a "difference" between src and target features.
If the features sizes aren't the same - the backprop can't find the accordance to some desired feature and the model can't be trained.
I was tackling the Fashion MNIST data-set problem on Udacity. However my implementation of code is giving drastically different loss as compared to the solution shared by the Udacity team. I believe the only difference in my answer is the definition of the Neural Network and apart from that everything is the same. I am not able to figure out the reason for such a drastic difference in Loss.
Code 1: My solution:
import torch.nn as nn
from torch import optim
images, labels = next(iter(trainloader))
model = nn.Sequential(nn.Linear(784,256),
nn.ReLU(),
nn.Linear(256,128),
nn.ReLU(),
nn.Linear(128,64),
nn.ReLU(),
nn.Linear(64,10),
nn.LogSoftmax(dim=1))
# Flatten images
optimizer = optim.Adam(model.parameters(),lr=0.003)
criterion = nn.NLLLoss()
for i in range(10):
running_loss = 0
for images,labels in trainloader:
images = images.view(images.shape[0], -1)
output = model.forward(images)
loss = criterion(output,labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
else:
print(f"Training loss: {running_loss}")
# Loss is coming around 4000
Code 2: Official Solution:
from torch import nn, optim
import torch.nn.functional as F
class Classifier(nn.Module):
def __init__(self):
super().__init__()
self.fc1 = nn.Linear(784, 256)
self.fc2 = nn.Linear(256, 128)
self.fc3 = nn.Linear(128, 64)
self.fc4 = nn.Linear(64, 10)
def forward(self, x):
# make sure input tensor is flattened
x = x.view(x.shape[0], -1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = F.relu(self.fc3(x))
x = F.log_softmax(self.fc4(x), dim=1)
return x
model = Classifier()
criterion = nn.NLLLoss()
optimizer = optim.Adam(model.parameters(), lr=0.003)
epochs = 5
for e in range(epochs):
running_loss = 0
for images, labels in trainloader:
log_ps = model(images)
loss = criterion(log_ps, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
running_loss += loss.item()
else:
print(f"Training loss: {running_loss}")
# Loss is coming around 200
Is there any explanation for the vast difference in loss ?
You forgot to zero out/clear the gradients in your implementation. That is you are missing :
optimizer.zero_grad()
In other words simply do:
for i in range(10):
running_loss = 0
for images,labels in trainloader:
images = images.view(images.shape[0], -1)
output = model.forward(images)
loss = criterion(output,labels)
# missed this!
optimizer.zero_grad()
loss.backward()
optimizer.step()
running_loss += loss.item()
else:
print(f"Training loss: {running_loss}")
and you are good to go!
I am doing making simple NN using MXnet , but having some problem in step() method
x1.shape=(64, 1, 1000)
y1.shape=(64, 1, 10)
net =nm.Sequential()
net.add(nn.Dense(H,activation='relu'),nn.Dense(90,activation='relu'),nn.Dense(D_out))
for t in range(500):
#y_pred = net(x1)
#loss = loss_fn(y_pred, y)
#for i in range(len(x1)):
with autograd.record():
output=net(x1)
loss =loss_fn(output,y1)
loss.backward()
trainer.step(64)
if t % 100 == 99:
print(t, loss)
#optimizer.zero_grad()
UserWarning: Gradient of Parameter dense30_weight on context cpu(0)
has not been updated by backward since last step. This could mean a
bug in your model that made it only use a subset of the Parameters
(Blocks) for this iteration. If you are intentionally only using a
subset, call step with ignore_stale_grad=True to suppress this warning
and skip updating of Parameters with stale gradient
The error indicates that you are passing parameters in your trainer that are not in your computational graph.
You need to initialize the parameters of your model and define the trainer. Unlike Pytorch, you don't need to call zero_grad in MXNet because by default new gradients are written in and not accumulated. Following code shows a simple neural network implemented using MXNet's Gluon API:
# Define model
net = gluon.nn.Dense(1)
net.collect_params().initialize(mx.init.Normal(sigma=1.), ctx=model_ctx)
square_loss = gluon.loss.L2Loss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.0001})
# Create random input and labels
def real_fn(X):
return 2 * X[:, 0] - 3.4 * X[:, 1] + 4.2
X = nd.random_normal(shape=(num_examples, num_inputs))
noise = 0.01 * nd.random_normal(shape=(num_examples,))
y = real_fn(X) + noise
# Define Dataloader
batch_size = 4
train_data = gluon.data.DataLoader(gluon.data.ArrayDataset(X, y), batch_size=batch_size, shuffle=True)
num_batches = num_examples / batch_size
for e in range(10):
# Iterate over training batches
for i, (data, label) in enumerate(train_data):
# Load data on the CPU
data = data.as_in_context(mx.cpu())
label = label.as_in_context(mx.cpu())
with autograd.record():
output = net(data)
loss = square_loss(output, label)
# Backpropagation
loss.backward()
trainer.step(batch_size)
cumulative_loss += nd.mean(loss).asscalar()
print("Epoch %s, loss: %s" % (e, cumulative_loss / num_examples))
I was reading the original paper on BN and the stack overflow question on How could I use Batch Normalization in TensorFlow? which provides a very useful piece of code to insert a batch normalization block to a Neural Network but does not provides enough guidance on how to actually use it during training, inference and when evaluating models.
For example, I would like to track the train error during training and test error to make sure I don't overfit. Its clear that the batch normalization block should be off during test, but when evaluating the error on the training set, should the batch normalization block be turned off too? My main questions are:
During inference and error evaluation, should the batch normalization block be turned off regardless of the data set?
Does that mean that the batch normalization block should only be on during the training step then?
To make it very clear, I will provide an extract (of simplified) code I have been using to run batch normalization with Tensor flow according to what is my understanding of what is the right thing to do:
## TRAIN
if phase_train is not None:
#DO BN
feed_dict_train = {x:X_train, y_:Y_train, phase_train: False}
feed_dict_cv = {x:X_cv, y_:Y_cv, phase_train: False}
feed_dict_test = {x:X_test, y_:Y_test, phase_train: False}
else:
#Don't do BN
feed_dict_train = {x:X_train, y_:Y_train}
feed_dict_cv = {x:X_cv, y_:Y_cv}
feed_dict_test = {x:X_test, y_:Y_test}
def get_batch_feed(X, Y, M, phase_train):
mini_batch_indices = np.random.randint(M,size=M)
Xminibatch = X[mini_batch_indices,:] # ( M x D^(0) )
Yminibatch = Y[mini_batch_indices,:] # ( M x D^(L) )
if phase_train is not None:
#DO BN
feed_dict = {x: Xminibatch, y_: Yminibatch, phase_train: True}
else:
#Don't do BN
feed_dict = {x: Xminibatch, y_: Yminibatch}
return feed_dict
with tf.Session() as sess:
sess.run( tf.initialize_all_variables() )
for iter_step in xrange(steps):
feed_dict_batch = get_batch_feed(X_train, Y_train, M, phase_train)
# Collect model statistics
if iter_step%report_error_freq == 0:
train_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_train)
cv_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_cv)
test_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_test)
do_stuff_with_errors(train_error, cv_error, test_error)
# Run Train Step
sess.run(fetches=train_step, feed_dict=feed_dict_batch)
and the code I am using to produce batch normalization blocks is:
def standard_batch_norm(l, x, n_out, phase_train, scope='BN'):
"""
Batch normalization on feedforward maps.
Args:
x: Vector
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope+l):
#beta = tf.Variable(tf.constant(0.0, shape=[n_out], dtype=tf.float64 ), name='beta', trainable=True, dtype=tf.float64 )
#gamma = tf.Variable(tf.constant(1.0, shape=[n_out],dtype=tf.float64 ), name='gamma', trainable=True, dtype=tf.float64 )
init_beta = tf.constant(0.0, shape=[n_out], dtype=tf.float64)
init_gamma = tf.constant(1.0, shape=[n_out],dtype=tf.float64)
beta = tf.get_variable(name='beta'+l, dtype=tf.float64, initializer=init_beta, regularizer=None, trainable=True)
gamma = tf.get_variable(name='gamma'+l, dtype=tf.float64, initializer=init_gamma, regularizer=None, trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train, mean_var_with_update, lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
I found that there is 'official' batch_norm layer in tensorflow. Try it out:
https://github.com/tensorflow/tensorflow/blob/b826b79718e3e93148c3545e7aa3f90891744cc0/tensorflow/contrib/layers/python/layers/layers.py#L100
Most likely it is not mentioned in docs since it included in some RC or 'beta' version only.
I haven't inspected deep into this matter yet, but as far as I see from documentation you just use binary parameter is_training in this batch_norm layer, and set it to true only for training phase. Try it out.
UPDATE: Below is the code to load data, build a network with one hidden ReLU layer and L2 normalization and introduce batch normalization for both hidden and out layer. This runs fine and trains fine.
# These are all the modules we'll be using later. Make sure you can import them
# before proceeding further.
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
pickle_file = '/home/maxkhk/Documents/Udacity/DeepLearningCourse/SourceCode/tensorflow/examples/udacity/notMNIST.pickle'
with open(pickle_file, 'rb') as f:
save = pickle.load(f)
train_dataset = save['train_dataset']
train_labels = save['train_labels']
valid_dataset = save['valid_dataset']
valid_labels = save['valid_labels']
test_dataset = save['test_dataset']
test_labels = save['test_labels']
del save # hint to help gc free up memory
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
image_size = 28
num_labels = 10
def reformat(dataset, labels):
dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
# Map 2 to [0.0, 1.0, 0.0 ...], 3 to [0.0, 0.0, 1.0 ...]
labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
#for NeuralNetwork model code is below
#We will use SGD for training to save our time. Code is from Assignment 2
#beta is the new parameter - controls level of regularization.
#Feel free to play with it - the best one I found is 0.001
#notice, we introduce L2 for both biases and weights of all layers
batch_size = 128
beta = 0.001
#building tensorflow graph
graph = tf.Graph()
with graph.as_default():
# Input data. For the training data, we use a placeholder that will be fed
# at run time with a training minibatch.
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
#introduce batchnorm
tf_train_dataset_bn = tf.contrib.layers.batch_norm(tf_train_dataset)
#now let's build our new hidden layer
#that's how many hidden neurons we want
num_hidden_neurons = 1024
#its weights
hidden_weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_hidden_neurons]))
hidden_biases = tf.Variable(tf.zeros([num_hidden_neurons]))
#now the layer itself. It multiplies data by weights, adds biases
#and takes ReLU over result
hidden_layer = tf.nn.relu(tf.matmul(tf_train_dataset_bn, hidden_weights) + hidden_biases)
#adding the batch normalization layerhi()
hidden_layer_bn = tf.contrib.layers.batch_norm(hidden_layer)
#time to go for output linear layer
#out weights connect hidden neurons to output labels
#biases are added to output labels
out_weights = tf.Variable(
tf.truncated_normal([num_hidden_neurons, num_labels]))
out_biases = tf.Variable(tf.zeros([num_labels]))
#compute output
out_layer = tf.matmul(hidden_layer_bn,out_weights) + out_biases
#our real output is a softmax of prior result
#and we also compute its cross-entropy to get our loss
#Notice - we introduce our L2 here
loss = (tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
out_layer, tf_train_labels) +
beta*tf.nn.l2_loss(hidden_weights) +
beta*tf.nn.l2_loss(hidden_biases) +
beta*tf.nn.l2_loss(out_weights) +
beta*tf.nn.l2_loss(out_biases)))
#now we just minimize this loss to actually train the network
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#nice, now let's calculate the predictions on each dataset for evaluating the
#performance so far
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(out_layer)
valid_relu = tf.nn.relu( tf.matmul(tf_valid_dataset, hidden_weights) + hidden_biases)
valid_prediction = tf.nn.softmax( tf.matmul(valid_relu, out_weights) + out_biases)
test_relu = tf.nn.relu( tf.matmul( tf_test_dataset, hidden_weights) + hidden_biases)
test_prediction = tf.nn.softmax(tf.matmul(test_relu, out_weights) + out_biases)
#now is the actual training on the ANN we built
#we will run it for some number of steps and evaluate the progress after
#every 500 steps
#number of steps we will train our ANN
num_steps = 3001
#actual training
with tf.Session(graph=graph) as session:
tf.initialize_all_variables().run()
print("Initialized")
for step in range(num_steps):
# Pick an offset within the training data, which has been randomized.
# Note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
# Generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :]
batch_labels = train_labels[offset:(offset + batch_size), :]
# Prepare a dictionary telling the session where to feed the minibatch.
# The key of the dictionary is the placeholder node of the graph to be fed,
# and the value is the numpy array to feed to it.
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 500 == 0):
print("Minibatch loss at step %d: %f" % (step, l))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))