def test_pull_box_sparse_op(self):
paddle.enable_static()
program = fluid.Program()
with fluid.program_guard(program):
x = fluid.layers.data(name='x',
shape=[1],
dtype='int64',
lod_level=0)
y = fluid.layers.data(name='y',
shape=[1],
dtype='int64',
lod_level=0)
emb_x, emb_y = _pull_box_sparse([x, y], size=1)
def run_boxps_preload(self, is_cpu=True):
x = fluid.layers.data(name='x', shape=[1], dtype='int64', lod_level=0)
y = fluid.layers.data(name='y', shape=[1], dtype='int64', lod_level=0)
emb_x, emb_y = _pull_box_sparse([x, y], size=2)
emb_xp = _pull_box_sparse(x, size=2)
layers.Print(emb_xp)
concat = layers.concat([emb_x, emb_y], axis=1)
fc = layers.fc(input=concat,
name="fc",
size=1,
num_flatten_dims=1,
bias_attr=False)
loss = layers.reduce_mean(fc)
layers.Print(loss)
place = fluid.CPUPlace(
) if is_cpu or not core.is_compiled_with_cuda() else fluid.CUDAPlace(0)
exe = fluid.Executor(place)
optimizer = fluid.optimizer.SGD(learning_rate=0.5)
batch_size = 2
def binary_print(slot, fout):
fout.write(str(len(slot)) + " ")
for e in slot:
fout.write(str(e) + " ")
batch1 = np.ones(
(batch_size, 2, 1)).astype("int64").reshape(batch_size, 2, 1)
filelist = []
place_str = "cpu" if is_cpu else "gpu"
for i in range(2):
filelist.append("test_hdfs_" + place_str + "_" + str(i))
for f in filelist:
with open(f, "w") as fout:
for ins in batch1:
for slot in ins:
binary_print(slot, fout)
fout.write("\n")
def create_dataset():
dataset = fluid.DatasetFactory().create_dataset("BoxPSDataset")
dataset.set_use_var([x, y])
dataset.set_batch_size(2)
dataset.set_thread(1)
dataset.set_filelist(filelist)
return dataset
datasets = []
datasets.append(create_dataset())
datasets.append(create_dataset())
optimizer.minimize(loss)
exe.run(fluid.default_startup_program())
datasets[0].load_into_memory()
datasets[0].begin_pass()
datasets[1].preload_into_memory()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=datasets[0],
print_period=1)
datasets[0].end_pass()
datasets[1].wait_preload_done()
datasets[1].begin_pass()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=datasets[1],
print_period=1)
datasets[1].end_pass()
for f in filelist:
os.remove(f)
def run_dataset(self, is_cpu):
x = fluid.layers.data(name='x', shape=[1], dtype='int64', lod_level=0)
y = fluid.layers.data(name='y', shape=[1], dtype='int64', lod_level=0)
rank_offset = fluid.layers.data(name="rank_offset",
shape=[-1, 7],
dtype="int32",
lod_level=0,
append_batch_size=False)
emb_x, emb_y = _pull_box_sparse([x, y], size=2)
emb_xp = _pull_box_sparse(x, size=2)
concat = layers.concat([emb_x, emb_y], axis=1)
fc = layers.fc(input=concat,
name="fc",
size=1,
num_flatten_dims=1,
bias_attr=False)
loss = layers.reduce_mean(fc)
place = fluid.CPUPlace(
) if is_cpu or not core.is_compiled_with_cuda() else fluid.CUDAPlace(0)
exe = fluid.Executor(place)
with open("test_run_with_dump_a.txt", "w") as f:
data = "1 1702f830eee19501ad7429505f714c1d 1 1 1 9\n"
data += "1 1702f830eee19502ad7429505f714c1d 1 2 1 8\n"
data += "1 1702f830eee19503ad7429505f714c1d 1 3 1 7\n"
data += "1 1702f830eee0de01ad7429505f714c2d 1 4 1 6\n"
data += "1 1702f830eee0df01ad7429505f714c3d 1 5 1 5\n"
data += "1 1702f830eee0df02ad7429505f714c3d 1 6 1 4\n"
f.write(data)
with open("test_run_with_dump_b.txt", "w") as f:
data = "1 1702f830fff22201ad7429505f715c1d 1 1 1 1\n"
data += "1 1702f830fff22202ad7429505f715c1d 1 2 1 2\n"
data += "1 1702f830fff22203ad7429505f715c1d 1 3 1 3\n"
data += "1 1702f830fff22101ad7429505f714ccd 1 4 1 4\n"
data += "1 1702f830fff22102ad7429505f714ccd 1 5 1 5\n"
data += "1 1702f830fff22103ad7429505f714ccd 1 6 1 6\n"
data += "1 1702f830fff22104ad7429505f714ccd 1 6 1 7\n"
f.write(data)
self.set_data_config()
self.dataset.set_use_var([x, y])
self.dataset.set_filelist(
["test_run_with_dump_a.txt", "test_run_with_dump_b.txt"])
optimizer = fluid.optimizer.SGD(learning_rate=0.5)
optimizer = fluid.optimizer.PipelineOptimizer(optimizer,
cut_list=[],
place_list=[place],
concurrency_list=[1],
queue_size=1,
sync_steps=-1)
optimizer.minimize(loss)
exe.run(fluid.default_startup_program())
self.dataset.set_current_phase(1)
self.dataset.load_into_memory()
self.dataset.preprocess_instance()
self.dataset.begin_pass()
pv_num = self.dataset.get_pv_data_size()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=self.dataset,
print_period=1)
self.dataset.set_current_phase(0)
self.dataset.postprocess_instance()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=self.dataset,
print_period=1)
self.dataset.end_pass(True)
os.remove("test_run_with_dump_a.txt")
os.remove("test_run_with_dump_b.txt")
def run_boxps_preload(self, is_cpu=True, random_with_lineid=False):
program = fluid.Program()
with fluid.program_guard(program):
x = fluid.layers.data(name='x',
shape=[1],
dtype='int64',
lod_level=0)
y = fluid.layers.data(name='y',
shape=[1],
dtype='int64',
lod_level=0)
emb_x, emb_y = _pull_box_sparse([x, y], size=2)
emb_xp = _pull_box_sparse(x, size=2)
concat = layers.concat([emb_x, emb_y], axis=1)
fc = layers.fc(input=concat,
name="fc",
size=1,
num_flatten_dims=1,
bias_attr=False)
loss = layers.reduce_mean(fc)
layers.Print(loss)
place = fluid.CPUPlace(
) if is_cpu or not core.is_compiled_with_cuda(
) else fluid.CUDAPlace(0)
exe = fluid.Executor(place)
batch_size = 100
def binary_print(slot, fout):
fout.write(str(len(slot)) + " ")
for e in slot:
fout.write(str(e) + " ")
batch1 = np.ones(
(batch_size, 2, 1)).astype("int64").reshape(batch_size, 2, 1)
filelist = []
place_str = "cpu" if is_cpu else "gpu"
for i in range(2):
filelist.append("test_hdfs_" + place_str + "_" + str(i))
for f in filelist:
with open(f, "w") as fout:
for ins in batch1:
for slot in ins:
binary_print(slot, fout)
fout.write("\n")
def create_dataset():
dataset = fluid.DatasetFactory().create_dataset("BoxPSDataset")
dataset.set_date("20190930")
dataset.set_use_var([x, y])
dataset.set_batch_size(2)
dataset.set_thread(1)
dataset.set_filelist(filelist)
return dataset
datasets = []
datasets.append(create_dataset())
datasets.append(create_dataset())
optimizer = fluid.optimizer.SGD(learning_rate=0.5)
optimizer = fluid.optimizer.PipelineOptimizer(optimizer,
cut_list=[],
place_list=[place],
concurrency_list=[1],
queue_size=1,
sync_steps=-1)
optimizer.minimize(loss)
program._pipeline_opt["dump_fields"] = [
"fc.tmp_0", "fc.tmp_0@GRAD", "hehe"
]
program._pipeline_opt["dump_fields_path"] = "./dump_log/"
program._pipeline_opt["dump_param"] = ["fc.w_0"]
program._pipeline_opt["enable_random_dump"] = True
program._pipeline_opt["dump_interval"] = 10
program._pipeline_opt["random_with_lineid"] = random_with_lineid
exe.run(fluid.default_startup_program())
datasets[0].load_into_memory()
datasets[0].begin_pass()
datasets[1].preload_into_memory()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=datasets[0],
print_period=1)
datasets[0].end_pass(True)
datasets[1].wait_preload_done()
datasets[1].begin_pass()
exe.train_from_dataset(program=fluid.default_main_program(),
dataset=datasets[1],
print_period=1,
debug=True)
datasets[1].end_pass(False)
for f in filelist:
os.remove(f)
if os.path.isdir("dump_log"):
shutil.rmtree("dump_log")