def run_main(config):
''' running MAMC training & validation'''
# init model
initialize(config)
training_model = build_training_model(config)
validation_model = build_validation_model(config)
# print network graph
"""
# full-graph
mamc_graph = net_drawer.GetPydotGraph(
validation_model.net.Proto().op,
"mamc_graph",
rankdir="TB",
)
mamc_graph.write_svg("mamc_no_npairloss_graph.svg")
print("write graph over...")
sys.exit(0)
# # mini-graph
# mamc_graph_mini = net_drawer.GetPydotGraphMinimal(
# validation_model.net.Proto().op,
# "mamc_graph_minimal",
# rankdir="TB",
# minimal_dependency=True
# )
# mamc_graph_mini.write_svg("mamc_no_npairloss_graph_mini.svg")
# print("write graph over...")
# sys.exit(0)
"""
# experiment params config
# training mode
# tag = "imagenet"
tag = "cars196"
if config['finetune']:
tag = 'FINETUNE-{}'.format(tag)
else:
tag = 'RETRAIN-{}'.format(tag)
root_experiments_dir = os.path.join(config['root_dir'], 'experiments')
experiment = Experiment(root_experiments_dir, tag)
experiment.add_config_file(config['config_path'])
# add chart
chart_acc = experiment.add_chart('accuracy',
xlabel='epochs',
ylabel='accuracy')
chart_acc_5 = experiment.add_chart('accuracy_5',
xlabel='epochs',
ylabel='accuracy_5')
chart_softmax_loss = experiment.add_chart('softmax_loss',
xlabel='epochs',
ylabel='softmax_loss')
# plot params (should be added into 'experiment module'
# TODO add 'variable' object to Experiment class
training_acc_statistics = []
training_acc5_statistics = []
training_softmax_loss_statistics = []
epoch_training_acc = 0
epoch_training_acc5 = 0
epoch_training_softmax_loss = 0
training_accuracy = 0
training_accuracy_5 = 0
training_softmax_loss = 0
validation_acc_statistics = []
validation_acc5_statistics = []
validation_softmax_loss_statistics = []
# run the model
experiment.add_log(
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
)
for training_iter in tqdm(range(config['solver']['max_iterations'])):
workspace.RunNet(training_model.net)
accuracy = workspace.FetchBlob('accuracy')
accuracy_5 = workspace.FetchBlob('accuracy_5')
softmax_loss = workspace.FetchBlob('softmax_loss')
epoch_training_acc += accuracy
epoch_training_acc5 += accuracy_5
epoch_training_softmax_loss += softmax_loss
training_accuracy += accuracy
training_accuracy_5 += accuracy_5
training_softmax_loss += softmax_loss
# display training result
if training_iter != 0 and (training_iter +
1) % config['solver']['display'] == 0:
experiment.add_log("[TRAIN] epoch: {} iteration: {} accuracy: {:.4f} "\
"accuracy_5: {:.4f} softmax_loss: {:.4f}".format(
(training_iter // config['solver']['train_iterations'] + 1),
training_iter,
training_accuracy / config['solver']['display'],
training_accuracy_5 / config['solver']['display'],
training_softmax_loss / config['solver']['display'],
))
experiment.add_log("Global learning rate: {}".format(
workspace.FetchBlob(
'MultiPrecisionSgdOptimizer_0_lr_gpu{}'.format(
config['gpu_id']))))
# cleanup the counters
training_accuracy = training_accuracy_5 = training_softmax_loss = 0
# plot training statistics every epoch
if training_iter != 0 and (
training_iter + 1) % config['solver']['train_iterations'] == 0:
training_acc_statistics.append(
epoch_training_acc / config['solver']['train_iterations'])
training_acc5_statistics.append(
epoch_training_acc5 / config['solver']['train_iterations'])
training_softmax_loss_statistics.append(
epoch_training_softmax_loss /
config['solver']['train_iterations'])
epoch_training_acc = 0
epoch_training_acc5 = 0
epoch_training_softmax_loss = 0
experiment.add_plot(chart_acc, training_acc_statistics, 'r.--',
'training')
experiment.add_plot(chart_acc_5, training_acc5_statistics, 'r.--',
'training')
experiment.add_plot(chart_softmax_loss,
training_softmax_loss_statistics, 'b+--',
'training')
# snapshot training model params
if training_iter != 0 and (training_iter +
1) % config['solver']['snapshot'] == 0:
# save the model weights
print("[INFO] snapshot the model..... ")
experiment.add_init_net_snapshot(
training_model.GetAllParams(),
workspace,
config['name'],
tag,
(training_iter // config['solver']['train_iterations'] + 1),
)
print("[INFO] snapshot the model. Done.....")
# start to validate the model
if training_iter != 0 and (training_iter +
1) % config['solver']['test_interval'] == 0:
test_accuracy = 0
test_accuracy_5 = 0
test_softmax_loss = 0
for test_iter in range(config['solver']['test_iterations']):
workspace.RunNet(validation_model.net)
accuracy = workspace.FetchBlob('accuracy')
accuracy_5 = workspace.FetchBlob('accuracy_5')
softmax_loss = workspace.FetchBlob('softmax_loss')
# update counter
test_accuracy += accuracy
test_accuracy_5 += accuracy_5
test_softmax_loss += softmax_loss
experiment.add_log("[VALIDATION] accuracy: {:.4f} accuracy_5: {:.4f} "\
"softmax_loss: {:.4f}".format(
accuracy, accuracy_5, softmax_loss))
# end validation
experiment.add_log(
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
)
experiment.add_log("[VALIDATION] avg_acc: {:.4f} avg_acc_5: {:.4f} "\
"avg_softmax_loss: {:.4f}".format(
test_accuracy / config['solver']['test_iterations'],
test_accuracy_5 / config['solver']['test_iterations'],
test_softmax_loss / config['solver']['test_iterations'],
)
)
# plot validation statistics
validation_acc_statistics.append(
test_accuracy / config['solver']['test_iterations'])
validation_acc5_statistics.append(
test_accuracy_5 / config['solver']['test_iterations'])
validation_softmax_loss_statistics.append(
test_softmax_loss / config['solver']['test_iterations'])
experiment.add_plot(chart_acc, validation_acc_statistics, 'c.--',
'validation')
experiment.add_plot(chart_acc_5, validation_acc5_statistics,
'c.--', 'validation')
experiment.add_plot(chart_softmax_loss,
validation_softmax_loss_statistics, 'g+--',
'validation')
experiment.add_log(
"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
)
def run_main(config):
''' running MAMC training & validation'''
# init model
initialize(config)
# build model
training_model = build_training_model(config)
validation_model = build_validation_model(config)
# print network graph
# generate_network_graph(validation_model, config, use_mini=True)
# generate_network_graph(validation_model, config, use_mini=False)
# generate_network_graph(validation_model, config, tag="topk", use_mini=True)
# generate_network_graph(validation_model, config, tag="topk", use_mini=False)
# sys.exit(0)
# experiment params config
root_experiments_dir = os.path.join(config['root_dir'], 'experiments')
assert(config['dataset_name'] is not None)
if config['model_name'] is not None:
root_experiments_dir = os.path.join(
root_experiments_dir,
"{}-{}".format(
config['dataset_name'],
config['model_name'],
),
)
else:
root_experiments_dir = os.path.join(
root_experiments_dir, config['dataset_name'])
config_file_name = os.path.splitext(
os.path.basename(config['config_path']))[0]
tag = "{}-{}".format(config['name'], config_file_name)
experiment = Experiment(root_experiments_dir, tag)
experiment.add_config_file(config['config_path'])
# add chart
chart_acc = experiment.add_chart('accuracy', xlabel='epochs',
ylabel='accuracy')
chart_acc_5 = experiment.add_chart('accuracy_5', xlabel='epochs',
ylabel='accuracy_5')
chart_softmax_loss = experiment.add_chart('softmax_loss', xlabel='epochs',
ylabel='softmax_loss')
# plot params (should be added into 'experiment module'
# TODO add 'variable' object to Experiment class
training_acc_statistics = []
training_acc5_statistics = []
training_softmax_loss_statistics = []
epoch_training_acc = 0
epoch_training_acc5 = 0
epoch_training_softmax_loss = 0
training_accuracy = 0
training_accuracy_5 = 0
training_softmax_loss = 0
validation_acc_statistics = []
validation_acc5_statistics = []
validation_softmax_loss_statistics = []
best_acc = 0
# run the model
experiment.add_log("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
for training_iter in tqdm(range(config['solver']['max_iterations'])):
workspace.RunNet(training_model.net)
accuracy = workspace.FetchBlob('accuracy')
accuracy_5 = workspace.FetchBlob('accuracy_5')
softmax_loss = workspace.FetchBlob('softmax_loss')
epoch_training_acc += accuracy
epoch_training_acc5 += accuracy_5
epoch_training_softmax_loss += softmax_loss
training_accuracy += accuracy
training_accuracy_5 += accuracy_5
training_softmax_loss += softmax_loss
# display training result
if training_iter != 0 and (training_iter + 1) % config['solver']['display'] == 0:
experiment.add_log("[TRAIN] epoch: {} iteration: {} accuracy: {:.4f} "\
"accuracy_5: {:.4f} softmax_loss: {:.4f}".format(
(training_iter // config['solver']['train_iterations'] + 1),
training_iter,
training_accuracy / config['solver']['display'],
training_accuracy_5 / config['solver']['display'],
training_softmax_loss / config['solver']['display'],
))
experiment.add_log("Global learning rate: {}".format(
workspace.FetchBlob('MultiPrecisionSgdOptimizer_0_lr_gpu{}'.format(config['gpu_id']))))
# cleanup the counters
training_accuracy = training_accuracy_5 = training_softmax_loss = 0
# plot training statistics every epoch
if training_iter != 0 and (training_iter + 1) % config['solver']['train_iterations'] == 0:
training_acc_statistics.append(epoch_training_acc / config['solver']['train_iterations'])
training_acc5_statistics.append(epoch_training_acc5 / config['solver']['train_iterations'])
training_softmax_loss_statistics.append(epoch_training_softmax_loss / config['solver']['train_iterations'])
epoch_training_acc = 0
epoch_training_acc5 = 0
epoch_training_softmax_loss = 0
experiment.add_plot(chart_acc, training_acc_statistics, 'r.--', 'training')
experiment.add_plot(chart_acc_5, training_acc5_statistics, 'r.--', 'training')
experiment.add_plot(chart_softmax_loss, training_softmax_loss_statistics, 'b+--', 'training')
# start to validate the model
if training_iter != 0 and (training_iter + 1) % config['solver']['test_interval'] == 0:
test_accuracy = 0
test_accuracy_5 = 0
test_softmax_loss = 0
test_loss = 0
for test_iter in range(config['solver']['test_iterations']):
workspace.RunNet(validation_model.net)
accuracy = workspace.FetchBlob('accuracy')
accuracy_5 = workspace.FetchBlob('accuracy_5')
softmax_loss = workspace.FetchBlob('softmax_loss')
# update counter
test_accuracy += accuracy
test_accuracy_5 += accuracy_5
test_softmax_loss += softmax_loss
experiment.add_log("[VALIDATION] accuracy: {:.4f} accuracy_5: {:.4f} "\
"softmax_loss: {:.4f}".format(
accuracy, accuracy_5, softmax_loss))
# end validation
if test_accuracy / config['solver']['test_iterations'] > best_acc:
best_acc = test_accuracy / config['solver']['test_iterations']
experiment.add_log("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
experiment.add_log("[VALIDATION] avg_acc: {:.4f} best_acc: {:.4f} avg_acc_5: {:.4f} "\
"avg_softmax_loss: {:.4f}".format(
test_accuracy / config['solver']['test_iterations'],
best_acc,
test_accuracy_5 / config['solver']['test_iterations'],
test_softmax_loss / config['solver']['test_iterations'],
)
)
# snapshot training model params
print("[INFO] snapshot the model..... ")
experiment.add_init_net_snapshot(
training_model.GetAllParams(),
workspace,
config,
(training_iter // config['solver']['train_iterations'] + 1),
test_accuracy / config['solver']['test_iterations'],
best_acc,
)
print("[INFO] snapshot the model. Done.....")
# plot validation statistics
validation_acc_statistics.append(test_accuracy / config['solver']['test_iterations'])
validation_acc5_statistics.append(test_accuracy_5 / config['solver']['test_iterations'])
validation_softmax_loss_statistics.append(test_softmax_loss / config['solver']['test_iterations'])
experiment.add_plot(chart_acc, validation_acc_statistics, 'c.--', 'validation')
experiment.add_plot(chart_acc_5, validation_acc5_statistics, 'c.--', 'validation')
experiment.add_plot(chart_softmax_loss, validation_softmax_loss_statistics, 'g+--', 'validation')
experiment.add_log("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")