# data iterator
train_data = mx.io.LibSVMIter(data_libsvm=train_data,
data_shape=(num_features, ),
batch_size=batch_size,
num_parts=num_worker,
part_index=rank)
eval_data = mx.io.LibSVMIter(data_libsvm=val_data,
data_shape=(num_features, ),
batch_size=batch_size)
# model
# The positive class weight, says how much more we should upweight the importance of
# positive instances in the objective function.
# This is used to combat the extreme class imbalance.
positive_class_weight = 2
model = linear_model(num_features, positive_class_weight)
# module
mod = mx.mod.Module(symbol=model,
data_names=['data'],
label_names=['softmax_label'])
mod.bind(data_shapes=train_data.provide_data,
label_shapes=train_data.provide_label)
mod.init_params()
optim = mx.optimizer.create(optimizer,
learning_rate=0.01,
rescale_grad=1.0 / batch_size / num_worker)
mod.init_optimizer(optimizer=optim, kvstore=kv)
# use accuracy as the metric
metric = mx.gluon.metric.create(['nll_loss'])
get_avazu_data(data_dir, AVAZU['train'], AVAZU['url'])
get_avazu_data(data_dir, AVAZU['test'], AVAZU['url'])
# data iterator
train_data = mx.io.LibSVMIter(data_libsvm=train_data, data_shape=(num_features,),
batch_size=batch_size, num_parts=num_worker,
part_index=rank)
eval_data = mx.io.LibSVMIter(data_libsvm=val_data, data_shape=(num_features,),
batch_size=batch_size)
# model
# The positive class weight, says how much more we should upweight the importance of
# positive instances in the objective function.
# This is used to combat the extreme class imbalance.
positive_class_weight = 2
model = linear_model(num_features, positive_class_weight)
# module
mod = mx.mod.Module(symbol=model, data_names=['data'], label_names=['softmax_label'])
mod.bind(data_shapes=train_data.provide_data, label_shapes=train_data.provide_label)
mod.init_params()
optim = mx.optimizer.create(optimizer, learning_rate=0.01, rescale_grad=1.0/batch_size/num_worker)
mod.init_optimizer(optimizer=optim, kvstore=kv)
# use accuracy as the metric
metric = mx.metric.create(['nll_loss'])
# get the sparse weight parameter
speedometer = mx.callback.Speedometer(batch_size, 100)
logging.info('Training started ...')
for epoch in range(num_epoch):