def test_dot_real(data_dict):
"""Dot operator testing with real datasets"""
data_dir = os.path.join(os.getcwd(), 'data')
path = os.path.join(data_dir, data_dict['data_name'])
if not os.path.exists(path):
get_data(
data_dir,
data_dict['data_name'],
data_dict['url'],
data_dict['data_origin_name']
)
assert os.path.exists(path)
k = data_dict['feature_dim']
m = data_dict['m']
batch_size_list = data_dict['batch_size']
default_output_index = data_dict['default_index']['output_dim']
default_batch_size_index = data_dict['default_index']['batch_size']
density = estimate_density(path, data_dict['feature_dim'])
num_batches = data_dict['num_batches']
assert default_batch_size_index < len(batch_size_list)
assert default_output_index < len(m)
if ARGS.verbose:
print("Running Benchmarking on %r data") % data_dict['data_mini']
print('{:>15} {:>10} {:>10} {:>10} {:>20} {:>15} {:>15} {:>10} {:>10}'.format('density(%)',
'n',
'm',
'k',
't_dense/t_sparse',
't_dense(ms)',
't_sparse(ms)',
'is_transpose',
'rhs_rsp'))
for output_dim in m:
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches,
transpose=True)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches, rsp=True)
for batch_size in batch_size_list:
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, m[default_output_index], density, batch_size, num_batches)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, m[default_output_index], density, batch_size, num_batches,
transpose=True)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches, rsp=True)
def test_dot_real(data_dict):
"""Dot operator testing with real datasets"""
data_dir = os.path.join(os.getcwd(), 'data')
path = os.path.join(data_dir, data_dict['data_name'])
if not os.path.exists(path):
get_bz2_data(
data_dir,
data_dict['data_name'],
data_dict['url'],
data_dict['data_origin_name']
)
assert os.path.exists(path)
k = data_dict['feature_dim']
m = data_dict['m']
batch_size_list = data_dict['batch_size']
default_output_index = data_dict['default_index']['output_dim']
default_batch_size_index = data_dict['default_index']['batch_size']
density = estimate_density(path, data_dict['feature_dim'])
num_batches = data_dict['num_batches']
assert default_batch_size_index < len(batch_size_list)
assert default_output_index < len(m)
if ARGS.verbose:
print("Running Benchmarking on %r data") % data_dict['data_mini']
print('{:>15} {:>10} {:>10} {:>10} {:>20} {:>15} {:>15} {:>10} {:>10}'.format('density(%)',
'n',
'm',
'k',
't_dense/t_sparse',
't_dense(ms)',
't_sparse(ms)',
'is_transpose',
'rhs_rsp'))
for output_dim in m:
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches,
transpose=True)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches, rsp=True)
for batch_size in batch_size_list:
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, m[default_output_index], density, batch_size, num_batches)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, m[default_output_index], density, batch_size, num_batches,
transpose=True)
_compare_sparse_dense(data_dir, data_dict['data_name'], data_dict['data_mini'],
k, output_dim, density,
batch_size_list[default_batch_size_index], num_batches, rsp=True)
def test_dot_real(data_dict):
def get_iter(path, data_shape, batch_size):
data_train = mx.io.LibSVMIter(data_libsvm=path,
data_shape=data_shape,
batch_size=batch_size)
data_iter = iter(data_train)
return data_iter
data_dir = os.path.join(os.getcwd(), 'data')
path = os.path.join(data_dir, data_dict['data_name'])
if not os.path.exists(path):
get_bz2_data(data_dir, data_dict['data_name'], data_dict['url'],
data_dict['data_origin_name'])
assert os.path.exists(path)
k = data_dict['feature_dim']
m = data_dict['m']
density = estimate_density(path, data_dict['feature_dim'])
mini_path = os.path.join(data_dir, data_dict['data_mini'])
if not os.path.exists(mini_path):
os.system("head -n 2000 %r > %r" % (path, mini_path))
assert os.path.exists(mini_path)
print("Running Benchmarking on %r data" % data_dict['data_mini'])
for batch_size in data_dict[
'batch_size']: # iterator through different batch size of choice
print("batch_size is %d" % batch_size)
# model
data_shape = (k, )
train_iter = get_iter(mini_path, data_shape, batch_size)
weight = mx.nd.random.uniform(low=0, high=1, shape=(k, m))
csr_data = []
dns_data = []
num_batch = 0
for batch in train_iter:
data = train_iter.getdata()
csr_data.append(data)
dns_data.append(data.tostype('default'))
num_batch += 1
bag_of_data = [csr_data, dns_data]
num_repeat = 5
costs = []
for d in bag_of_data:
weight.wait_to_read()
cost = 0.
count = 0
for d_batch in d:
d_batch.wait_to_read()
cost += measure_cost(num_repeat, mx.nd.dot, d_batch, weight)
count += 1
costs.append(cost / count)
t_sparse = costs[0]
t_dense = costs[1]
ratio = t_dense / t_sparse
print('density(%)\tn\tm\tk\tt_dense/t_sparse\tt_dense\tt_sparse')
fmt = "%0.4f\t\t%d\t%d\t%d\t%0.2f\t\t\t%0.4f\t%0.6f"
print(fmt %
(density * 100, batch_size, m, k, ratio, t_dense, t_sparse))
def test_dot_real(data_dict):
def get_iter(path, data_shape, batch_size):
data_train = mx.io.LibSVMIter(data_libsvm=path,
data_shape=data_shape,
batch_size=batch_size)
data_iter = iter(data_train)
return data_iter
data_dir = os.path.join(os.getcwd(), 'data')
path = os.path.join(data_dir, data_dict['data_name'])
if not os.path.exists(path):
get_bz2_data(
data_dir,
data_dict['data_name'],
data_dict['url'],
data_dict['data_origin_name']
)
assert os.path.exists(path)
k = data_dict['feature_dim']
m = data_dict['m']
density = estimate_density(path, data_dict['feature_dim'])
mini_path = os.path.join(data_dir, data_dict['data_mini'])
if not os.path.exists(mini_path):
os.system("head -n 2000 %r > %r" % (path, mini_path))
assert os.path.exists(mini_path)
print "Running Benchmarking on %r data" % data_dict['data_mini']
for batch_size in data_dict['batch_size']: # iterator through different batch size of choice
print "batch_size is %d" % batch_size
# model
data_shape = (k, )
train_iter = get_iter(mini_path, data_shape, batch_size)
weight = mx.nd.random.uniform(low=0, high=1, shape=(k, m))
csr_data = []
dns_data = []
num_batch = 0
for batch in train_iter:
data = train_iter.getdata()
csr_data.append(data)
dns_data.append(data.tostype('default'))
num_batch += 1
bag_of_data = [csr_data, dns_data]
num_repeat = 5
costs = []
for d in bag_of_data:
weight.wait_to_read()
cost = 0.
count = 0
for d_batch in d:
d_batch.wait_to_read()
cost += measure_cost(num_repeat, mx.nd.dot, d_batch, weight)
count += 1
costs.append(cost/count)
t_sparse = costs[0]
t_dense = costs[1]
ratio = t_dense / t_sparse
print('density(%)\tn\tm\tk\tt_dense/t_sparse\tt_dense\tt_sparse')
fmt = "%0.4f\t\t%d\t%d\t%d\t%0.2f\t\t\t%0.4f\t%0.6f"
print(fmt % (density * 100, batch_size, m, k, ratio, t_dense, t_sparse))
