def sample(args):
# Need to load the model from somewhere
params = pickle.load(open('./save/{0}.model_param'.format(args.params)))
model = RegressionModel(params, infer=True)
model.inference(model.data_placeholder)
with tf.Session() as sess:
# TODO: This loads the most recent checkpoint not
tf.initialize_all_variables().run()
saver = tf.train.Saver(tf.all_variables())
checkpoints = glob.glob("./save/model_{0}.ckpt-*".format(params.id))
if len(checkpoints) > 0:
# We have worked on training this model before. Resume work rather than
# starting from scratch
# Get the iteration number for all of them
iterations = np.array([int(c.split('-')[1]) for c in checkpoints])
# Index of the checkpoint with the most iterations
idx = np.argmax(iterations)
restore_path = checkpoints[idx]
saver.restore(sess, restore_path)
print "restoring {0}".format(restore_path)
print model.sample(sess, args.n, args.prime)
else:
print "Unable to restore - no checkpoints found"
def sample(args):
# Need to load the model from somewhere
params = pickle.load(open("./save/{0}.model_param".format(args.params)))
model = RegressionModel(params, infer=True)
model.inference(model.data_placeholder)
with tf.Session() as sess:
# TODO: This loads the most recent checkpoint not
tf.initialize_all_variables().run()
saver = tf.train.Saver(tf.all_variables())
checkpoints = glob.glob("./save/model_{0}.ckpt-*".format(params.id))
if len(checkpoints) > 0:
# We have worked on training this model before. Resume work rather than
# starting from scratch
# Get the iteration number for all of them
iterations = np.array([int(c.split("-")[1]) for c in checkpoints])
# Index of the checkpoint with the most iterations
idx = np.argmax(iterations)
restore_path = checkpoints[idx]
saver.restore(sess, restore_path)
print "restoring {0}".format(restore_path)
print model.sample(sess, args.n, args.prime)
else:
print "Unable to restore - no checkpoints found"
def main():
params = Params()
model = RegressionModel(params)
# Use functions of the model to build the graph
out, states = model.inference(model.data_placeholder)
loss = model.loss(out, model.labels_placeholder)
train_op = model.train(loss, params.step_size)
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
saver = tf.train.Saver(tf.all_variables())
for i in range(params.train_steps + 1):
data, labels = get_batch(params.batch_size, params.sequence_length,
params.input_channels)
feed_dict = {
model.data_placeholder: data,
model.labels_placeholder: labels
}
# Run one step of the model. The return values are the activations
# from the `train_op` (which is discarded) and the `loss` Op. To
# inspect the values of your Ops or variables, you may include them
# in the list passed to sess.run() and the value tensors will be
# returned in the tuple from the call.
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
if i % params.print_every == 0:
print i, loss_value
if i % params.save_every == 0:
name = "model_{0}.ckpt".format(params.get_id)
checkpoint_path = os.path.join('./save', name)
# TODO: If we restore a model for further training, we should
# add the number of training steps it had completed to our global step here
saver.save(sess, checkpoint_path, global_step=i)
print "model saved to {0}-{1}".format(checkpoint_path, i)
with open('./save/{0}.model_param'.format(params.get_id),
'w') as f:
pickle.dump(
params,
f,
protocol=2 # pickle.HIGHEST_PROTOCOL as of writing
)
data, labels = get_batch(params.batch_size, params.sequence_length,
params.input_channels)
feed_dict = {
model.data_placeholder: data,
model.labels_placeholder: labels
}
vars = sess.run(out + states, feed_dict)
out_ = vars[0:len(out)]
states_ = vars[len(out) + 1:]
d = data[0, 0, :]
o = np.array(out_)[:, 0, 0]
l = labels[0, 0, :]
x1 = range(d.shape[0])
x2 = range(1, d.shape[0] + 1)
# TODO: output graph every 100 steps
plt.scatter(x1, d, c='r')
plt.scatter(x2, o, c='g')
plt.scatter(x2, l, c='b', alpha=0.5)
plt.show()
print "data third dim", d
print "out", o
# print "states", np.array(states_)
print "labels third dim", l
def main():
params = Params()
model = RegressionModel(params)
# Use functions of the model to build the graph
out, states = model.inference(model.data_placeholder)
loss = model.loss(out, model.labels_placeholder)
train_op = model.train(loss, params.step_size)
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
saver = tf.train.Saver(tf.all_variables())
for i in range(params.train_steps + 1):
data, labels = get_batch(params.batch_size, params.sequence_length, params.input_channels)
feed_dict = {
model.data_placeholder: data,
model.labels_placeholder: labels
}
# Run one step of the model. The return values are the activations
# from the `train_op` (which is discarded) and the `loss` Op. To
# inspect the values of your Ops or variables, you may include them
# in the list passed to sess.run() and the value tensors will be
# returned in the tuple from the call.
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
if i % params.print_every == 0:
print i, loss_value
if i % params.save_every == 0:
name = "model_{0}.ckpt".format(params.get_id)
checkpoint_path = os.path.join('./save', name)
# TODO: If we restore a model for further training, we should
# add the number of training steps it had completed to our global step here
saver.save(sess, checkpoint_path, global_step=i)
print "model saved to {0}-{1}".format(checkpoint_path, i)
with open('./save/{0}.model_param'.format(params.get_id), 'w') as f:
pickle.dump(params,
f,
protocol=2 # pickle.HIGHEST_PROTOCOL as of writing
)
data, labels = get_batch(params.batch_size, params.sequence_length, params.input_channels)
feed_dict = {
model.data_placeholder: data,
model.labels_placeholder: labels
}
vars = sess.run(out + states, feed_dict)
out_ = vars[0:len(out)]
states_ = vars[len(out)+1:]
d = data[0,0,:]
o = np.array(out_)[:, 0, 0]
l = labels[0,0,:]
x1 = range(d.shape[0])
x2 = range(1, d.shape[0] + 1)
# TODO: output graph every 100 steps
plt.scatter(x1, d, c='r')
plt.scatter(x2, o, c='g')
plt.scatter(x2, l, c='b', alpha=0.5)
plt.show()
print "data third dim", d
print "out", o
# print "states", np.array(states_)
print "labels third dim", l
