How to get a prediction from Tensorflow - python-3.x

Question

I took the dynamic RNN example from aymericdamian: https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/dynamic_rnn.py
and modified it a little to fit my data. The data is a list of 7500 data sets of 60 entries.
There are 5 labels as output data.
The code runs perfect and I get an accuracy of 75%.
Now I want to feed the model with a data set and get a predicted label back, but I get the following error:
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder_2' with dtype int32
The code is listed below and the two last lines is where I want to get the prediction back.
What am I doing wrong?
# ==========
# MODEL
# ==========
# Parameters
learning_rate = 0.01
training_iters = 1000000
batch_size = 128
display_step = 10
# Network Parameters
seq_max_len = 60 # Sequence max length
n_hidden = 64 # hidden layer num of features
n_classes = 5 # large rise, small rise, almost equal, small drop, large drop
trainset = ToySequenceData(n_samples=7500, max_seq_len=seq_max_len)
testset = copy.copy(trainset)
# take 50% of total data to use for training
trainpart = int(0.2 * trainset.data.__len__())
pred_data = testset.data[testset.data.__len__() - 2:testset.labels.__len__() - 1][:]
pred_label = testset.labels[testset.labels.__len__() - 1:][:]
trainset.data = trainset.data[:trainpart][:]
testset.data = testset.data[trainpart:testset.data.__len__() - 2][:]
trainset.labels = trainset.labels[:trainpart][:]
testset.labels = testset.labels[trainpart:testset.labels.__len__() - 2][:]
trainset.seqlen = trainset.seqlen[:trainpart][:]
testset.seqlen = testset.seqlen[trainpart:testset.seqlen.__len__() - 2]
# tf Graph input
x = tf.placeholder("float", [None, seq_max_len, 1])
y = tf.placeholder("float", [None, n_classes])
# A placeholder for indicating each sequence length
seqlen = tf.placeholder(tf.int32, [None])
# Define weights
weights = {
'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
'out': tf.Variable(tf.random_normal([n_classes]))
}
def dynamic_rnn(x, seqlen, weights, biases):
# Prepare data shape to match `rnn` function requirements
# Current data input shape: (batch_size, n_steps, n_input)
# Required shape: 'n_steps' tensors list of shape (batch_size, n_input)
# Permuting batch_size and n_steps
x = tf.transpose(x, [1, 0, 2])
# Reshaping to (n_steps*batch_size, n_input)
x = tf.reshape(x, [-1, 1])
# Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
x = tf.split(0, seq_max_len, x)
# Define a lstm cell with tensorflow
lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden)
# Get lstm cell output, providing 'sequence_length' will perform dynamic
# calculation.
outputs, states = tf.nn.rnn(lstm_cell, x, dtype=tf.float32,
sequence_length=seqlen)
# When performing dynamic calculation, we must retrieve the last
# dynamically computed output, i.e., if a sequence length is 10, we need
# to retrieve the 10th output.
# However TensorFlow doesn't support advanced indexing yet, so we build
# a custom op that for each sample in batch size, get its length and
# get the corresponding relevant output.
# 'outputs' is a list of output at every timestep, we pack them in a Tensor
# and change back dimension to [batch_size, n_step, n_input]
outputs = tf.pack(outputs)
outputs = tf.transpose(outputs, [1, 0, 2])
# Hack to build the indexing and retrieve the right output.
batch_size = tf.shape(outputs)[0]
# Start indices for each sample
index = tf.range(0, batch_size) * seq_max_len + (seqlen - 1)
# Indexing
outputs = tf.gather(tf.reshape(outputs, [-1, n_hidden]), index)
# Linear activation, using outputs computed above
return tf.matmul(outputs, weights['out']) + biases['out']
pred = dynamic_rnn(x, seqlen, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y, batch_seqlen = trainset.next(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
seqlen: batch_seqlen})
if step % display_step == 0:
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y,
seqlen: batch_seqlen})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y,
seqlen: batch_seqlen})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " +
"{:.6f}".format(loss) + ", Training Accuracy= " +
"{:.5f}".format(acc))
step += 1
print("Optimization Finished!")
# Calculate accuracy
test_data = testset.data
test_label = testset.labels
test_seqlen = testset.seqlen
print("Testing Accuracy:",
sess.run(accuracy, feed_dict={x: test_data, y: test_label,
seqlen: test_seqlen}))
print(pred.eval(feed_dict={x: pred_data}))
print(pred_label)

Answer 1

In TensorFlow, when you do not provide a name to tf.placeholder, it assumes the default name "Placeholder". The next placeholder created is named "Placeholder_1" and the third one is called "Placeholder_2".
This is done to uniquely identify each placeholder. Now in your last line, you are trying to get the value of pred.eval(). Looking at your dynamic_rnn code, it seems like you need a value in the seq_len placeholder, which is the third placeholder defined (that's why "Placeholder_2". Simply add the following key-value to your feed_dict,
print(pred.eval(feed_dict={x: pred_data, seqlen: pred_seqlen}))
Of course, you will need to define pred_seqlen properly like you defined the other two seq_len variables.