def test_train_eval():
"""
test_train_eval
"""
config = WideDeepConfig()
data_path = config.data_path
batch_size = config.batch_size
epochs = config.epochs
print("epochs is {}".format(epochs))
ds_train = create_dataset(data_path, train_mode=True, epochs=epochs, batch_size=batch_size,
data_type=DataType.MINDRECORD, rank_id=get_rank(), rank_size=get_group_size())
ds_eval = create_dataset(data_path, train_mode=False, epochs=epochs + 1, batch_size=batch_size,
data_type=DataType.MINDRECORD, rank_id=get_rank(), rank_size=get_group_size())
print("ds_train.size: {}".format(ds_train.get_dataset_size()))
print("ds_eval.size: {}".format(ds_eval.get_dataset_size()))
net_builder = ModelBuilder()
train_net, eval_net = net_builder.get_net(config)
train_net.set_train()
auc_metric = AUCMetric()
model = Model(train_net, eval_network=eval_net, metrics={"auc": auc_metric})
eval_callback = EvalCallBack(model, ds_eval, auc_metric, config)
callback = LossCallBack(config=config)
context.set_auto_parallel_context(strategy_ckpt_save_file="./strategy_train.ckpt")
model.train(epochs, ds_train,
callbacks=[TimeMonitor(ds_train.get_dataset_size()), eval_callback, callback])
eval_values = list(eval_callback.eval_values)
assert eval_values[0] > 0.78
def test_train_eval():
"""
test_train_eval
"""
np.random.seed(1000)
config = WideDeepConfig()
data_path = config.data_path
batch_size = config.batch_size
epochs = config.epochs
print("epochs is {}".format(epochs))
ds_train = create_dataset(data_path, train_mode=True, epochs=epochs,
batch_size=batch_size, rank_id=get_rank(), rank_size=get_group_size())
ds_eval = create_dataset(data_path, train_mode=False, epochs=epochs + 1,
batch_size=batch_size, rank_id=get_rank(), rank_size=get_group_size())
print("ds_train.size: {}".format(ds_train.get_dataset_size()))
print("ds_eval.size: {}".format(ds_eval.get_dataset_size()))
net_builder = ModelBuilder()
train_net, eval_net = net_builder.get_net(config)
train_net.set_train()
auc_metric = AUCMetric()
model = Model(train_net, eval_network=eval_net, metrics={"auc": auc_metric})
eval_callback = EvalCallBack(model, ds_eval, auc_metric, config)
callback = LossCallBack(config=config)
ckptconfig = CheckpointConfig(save_checkpoint_steps=ds_train.get_dataset_size(), keep_checkpoint_max=5)
ckpoint_cb = ModelCheckpoint(prefix='widedeep_train',
directory=config.ckpt_path, config=ckptconfig)
out = model.eval(ds_eval)
print("=====" * 5 + "model.eval() initialized: {}".format(out))
model.train(epochs, ds_train,
callbacks=[TimeMonitor(ds_train.get_dataset_size()), eval_callback, callback, ckpoint_cb])
def test_eval(config):
"""
test evaluate
"""
data_path = config.data_path
batch_size = config.batch_size
ds_eval = create_dataset(data_path, train_mode=False, epochs=2,
batch_size=batch_size)
print("ds_eval.size: {}".format(ds_eval.get_dataset_size()))
net_builder = ModelBuilder()
train_net, eval_net = net_builder.get_net(config)
param_dict = load_checkpoint(config.ckpt_path)
load_param_into_net(eval_net, param_dict)
auc_metric = AUCMetric()
model = Model(train_net, eval_network=eval_net, metrics={"auc": auc_metric})
eval_callback = EvalCallBack(model, ds_eval, auc_metric, config)
model.eval(ds_eval, callbacks=eval_callback)
if __name__ == "__main__":
widedeep_config = WideDeepConfig()
widedeep_config.argparse_init()
test_eval(widedeep_config)
batch_size=batch_size)
print("ds_train.size: {}".format(ds_train.get_dataset_size()))
net_builder = ModelBuilder()
train_net, _ = net_builder.get_net(configure)
train_net.set_train()
model = Model(train_net)
callback = LossCallBack(config=configure)
ckptconfig = CheckpointConfig(
save_checkpoint_steps=ds_train.get_dataset_size(),
keep_checkpoint_max=5)
ckpoint_cb = ModelCheckpoint(prefix='widedeep_train',
directory=configure.ckpt_path,
config=ckptconfig)
model.train(epochs,
ds_train,
callbacks=[
TimeMonitor(ds_train.get_dataset_size()), callback,
ckpoint_cb
])
if __name__ == "__main__":
config = WideDeepConfig()
config.argparse_init()
context.set_context(mode=context.GRAPH_MODE,
device_target=config.device_target)
test_train(config)
directory=config.ckpt_path + '/ckpt_' +
str(get_rank()) + '/',
config=ckptconfig)
callback_list = [
TimeMonitor(ds_train.get_dataset_size()), eval_callback, callback
]
if get_rank() == 0:
callback_list.append(ckpoint_cb)
model.train(epochs,
ds_train,
callbacks=callback_list,
dataset_sink_mode=(parameter_server and cache_enable))
if __name__ == "__main__":
wide_deep_config = WideDeepConfig()
wide_deep_config.argparse_init()
context.set_context(mode=context.GRAPH_MODE,
device_target=wide_deep_config.device_target,
save_graphs=True)
cache_enable = wide_deep_config.vocab_cache_size > 0
if cache_enable and wide_deep_config.device_target != "GPU":
context.set_context(variable_memory_max_size="24GB")
context.set_ps_context(enable_ps=True)
init()
context.set_context(save_graphs_path='./graphs_of_device_id_' +
str(get_rank()))
if cache_enable:
context.set_auto_parallel_context(
parallel_mode=ParallelMode.AUTO_PARALLEL, gradients_mean=True)
def create_network(name, *args, **kwargs):
if name == 'wide_and_deep_multitable':
wide_deep_config = WideDeepConfig()
eval_net = get_WideDeep_net(wide_deep_config)
return eval_net
raise NotImplementedError(f"{name} is not implemented in the repo")
