def run_epoch(self, epoch_name: str, epoch_num, data, is_training: bool):
loss = 0
edge_loss, kl_loss, node_symbol_loss = 0, 0, 0
start_time = time.time()
processed_graphs = 0
batch_iterator = ThreadedIterator(self.make_minibatch_iterator(
data, is_training),
max_queue_size=5)
for step, batch_data in enumerate(batch_iterator):
num_graphs = batch_data[self.placeholders['num_graphs']]
processed_graphs += num_graphs
batch_data[self.placeholders['is_generative']] = False
# Randomly sample from normal distribution
batch_data[self.placeholders['z_prior']] = utils.generate_std_normal(\
self.params['batch_size'], batch_data[self.placeholders['num_vertices']],self.params['encoding_size'])
batch_data[self.placeholders['z_prior_in']] = utils.generate_std_normal(\
self.params['batch_size'], batch_data[self.placeholders['num_vertices']],self.params['hidden_size'])
if is_training:
batch_data[self.placeholders[
'out_layer_dropout_keep_prob']] = self.params[
'out_layer_dropout_keep_prob']
fetch_list = [
self.ops['loss'], self.ops['mean_edge_loss_in'],
self.ops['mean_kl_loss_in'],
self.ops['mean_node_symbol_loss_in'],
self.ops['train_step']
]
else:
batch_data[
self.placeholders['out_layer_dropout_keep_prob']] = 1.0
fetch_list = [
self.ops['loss'], self.ops['mean_edge_loss_in'],
self.ops['mean_kl_loss_in'],
self.ops['mean_node_symbol_loss_in']
]
result = self.sess.run(fetch_list, feed_dict=batch_data)
batch_loss = result[0]
loss += batch_loss * num_graphs
edge_loss += result[1] * num_graphs
kl_loss += result[2] * num_graphs
node_symbol_loss += result[3] * num_graphs
print(
"Running %s, batch %i (has %i graphs). Loss so far: %.4f. Edge loss: %.4f, KL loss: %.4f, Node symbol loss: %.4f"
% (epoch_name, step, num_graphs, loss / processed_graphs,
edge_loss / processed_graphs, kl_loss / processed_graphs,
node_symbol_loss / processed_graphs),
end='\r')
loss = loss / processed_graphs
edge_loss = edge_loss / processed_graphs
kl_loss = kl_loss / processed_graphs
node_symbol_loss = node_symbol_loss / processed_graphs
instance_per_sec = processed_graphs / (time.time() - start_time)
return (loss, edge_loss, kl_loss, node_symbol_loss), instance_per_sec
def run_epoch(self, epoch_name: str, epoch_num, data, is_training: bool):
loss = 0
start_time = time.time()
processed_graphs = 0
batch_iterator = ThreadedIterator(self.make_minibatch_iterator(
data, is_training),
max_queue_size=5)
for step, batch_data in enumerate(batch_iterator):
num_graphs = batch_data[self.placeholders['num_graphs']]
processed_graphs += num_graphs
batch_data[self.placeholders['is_generative']] = False
# Randomly sample from normal distribution
batch_data[self.placeholders['z_prior']] = utils.generate_std_normal(\
self.params['batch_size'], batch_data[self.placeholders['num_vertices']],self.params['hidden_size'])
if is_training:
batch_data[self.placeholders[
'out_layer_dropout_keep_prob']] = self.params[
'out_layer_dropout_keep_prob']
fetch_list = [
self.ops['loss'], self.ops['train_step'],
self.ops["edge_loss"], self.ops['kl_loss'],
self.ops['node_symbol_prob'],
self.placeholders['node_symbols'],
self.ops['qed_computed_values'],
self.placeholders['target_values'],
self.ops['total_qed_loss'], self.ops['mean'],
self.ops['logvariance'], self.ops['grads'],
self.ops['mean_edge_loss'],
self.ops['mean_node_symbol_loss'],
self.ops['mean_kl_loss'], self.ops['mean_total_qed_loss']
]
else:
batch_data[
self.placeholders['out_layer_dropout_keep_prob']] = 1.0
fetch_list = [
self.ops['mean_edge_loss'], self.ops['accuracy_task0']
]
result = self.sess.run(fetch_list, feed_dict=batch_data)
"""try:
if is_training:
self.save_intermediate_results(batch_data[self.placeholders['adjacency_matrix']],
result[11], result[12], result[4], result[5], result[9], result[10], result[6], result[7], result[13], result[14])
except IndexError:
pass"""
batch_loss = result[0]
loss += batch_loss * num_graphs
print("Running %s, batch %i (has %i graphs). Loss so far: %.4f" %
(epoch_name, step, num_graphs, loss / processed_graphs),
end='\r')
loss = loss / processed_graphs
instance_per_sec = processed_graphs / (time.time() - start_time)
return loss, instance_per_sec
def run_epoch(self, epoch_name: str, epoch_num, data, is_training: bool):
loss = 0
mean_edge_loss = 0
mean_node_loss = 0
mean_kl_loss = 0
mean_qed_loss = 0
node_loss_error = -10000000
node_pred_error = 0
start_time = time.time()
processed_graphs = 0
if is_training and self.params['num_teacher_forcing'] >= epoch_num:
teacher_forcing = True
else:
teacher_forcing = False
batch_iterator = ThreadedIterator(
self.make_minibatch_iterator(data, is_training),
max_queue_size=self.params['batch_size']
) # self.params['batch_size'])
for step, batch_data in enumerate(batch_iterator):
num_graphs = batch_data[self.placeholders['num_graphs']]
processed_graphs += num_graphs
batch_data[self.placeholders['is_generative']] = False
batch_data[self.placeholders[
'use_teacher_forcing_nodes']] = teacher_forcing
batch_data[
self.placeholders['z_prior']] = utils.generate_std_normal(
self.params['batch_size'],
batch_data[self.placeholders['num_vertices']],
self.params['hidden_size_encoder'])
if is_training:
batch_data[self.placeholders[
'out_layer_dropout_keep_prob']] = self.params[
'out_layer_dropout_keep_prob']
fetch_list = [
self.ops['loss'], self.ops['train_step'],
self.ops["edge_loss"], self.ops['kl_loss'],
self.ops['node_symbol_prob'],
self.placeholders['node_symbols'],
self.ops['qed_computed_values'],
self.placeholders['target_values'],
self.ops['total_qed_loss'], self.ops['mean'],
self.ops['logvariance'], self.ops['grads'],
self.ops['mean_edge_loss'],
self.ops['mean_node_symbol_loss'],
self.ops['mean_kl_loss'], self.ops['mean_total_qed_loss'],
self.ops['grads2'], self.ops['node_loss_error'],
self.ops['node_pred_error']
]
else:
batch_data[
self.placeholders['out_layer_dropout_keep_prob']] = 1.0
fetch_list = [
self.ops['loss'], self.ops['mean_edge_loss'],
self.ops['mean_node_symbol_loss'],
self.ops['mean_kl_loss'], self.ops['mean_total_qed_loss'],
self.ops['sampled_atoms'], self.ops['node_loss_error'],
self.ops['node_pred_error']
]
result = self.sess.run(fetch_list, feed_dict=batch_data)
batch_loss = result[0]
loss += batch_loss * num_graphs
if is_training:
mean_edge_loss += result[12] * num_graphs
mean_node_loss += result[13] * num_graphs
mean_kl_loss += result[14] * num_graphs
mean_qed_loss += result[15] * num_graphs
node_loss_error = max(node_loss_error, np.max(result[17]))
node_pred_error += result[18]
else:
mean_edge_loss += result[1] * num_graphs
mean_node_loss += result[2] * num_graphs
mean_kl_loss += result[3] * num_graphs
mean_qed_loss += result[4] * num_graphs
node_loss_error = max(node_loss_error, np.max(result[6]))
node_pred_error += result[7]
print(
"Running %s, batch %i (has %i graphs). Total loss: %.4f. Edge loss: %.4f. Node loss: %.4f. KL loss: %.4f. Property loss: %.4f. Node error: %.4f. Node pred: %.4f."
% (epoch_name, step, num_graphs, loss / processed_graphs,
mean_edge_loss / processed_graphs, mean_node_loss /
processed_graphs, mean_kl_loss / processed_graphs,
mean_qed_loss / processed_graphs, node_loss_error,
node_pred_error / processed_graphs),
end='\r')
mean_edge_loss /= processed_graphs
mean_node_loss /= processed_graphs
mean_kl_loss /= processed_graphs
mean_qed_loss /= processed_graphs
loss = loss / processed_graphs
instance_per_sec = processed_graphs / (time.time() - start_time)
return loss, mean_edge_loss, mean_node_loss, mean_kl_loss, mean_qed_loss, instance_per_sec