def _test():
path = "/store/slowmoyang/QGJets/dijet_100_110/dijet_100_110_test.root"
dset = BDTVarSet(path, extra=["pt", "eta"])
data_iter = DataIterator(dset, batch_size=128)
batch = data_iter.next()
for key, value in batch.iteritems():
print(key, value.shape)
print(data_iter._dataset[:1]["x"].shape[1:])
print(data_iter.get_shape("x", False))
print(data_iter.get_shape("x", True))
def _test():
from dataset import C10Set
from keras4hep.data import DataIterator
path = "/store/slowmoyang/QGJets/dijet_100_110/dijet_100_110_test.root"
dset = C10Set(path)
data_iter = DataIterator(dset, batch_size=128)
batch = data_iter.next()
x_shape = data_iter.get_shape("x", batch_shape=False)
model = build_a_model(x_shape)
logits = model.predict_on_batch(batch.x)
print("logits: {}".format(logits.shape))
def get_data_iter(path,
extra=[],
batch_size=128,
**kwargs):
dset = HybridSet(path=path, extra=extra)
data_iter = DataIterator(dset, batch_size=batch_size, **kwargs)
return data_iter
def _test():
from keras4hep.data import DataIterator
from dataset import JetSeqSet
path = "/store/slowmoyang/QGJets/dijet_100_110/dijet_100_110_test.root"
prep_path = "./logs/dijet_100_110_training.npz"
dset = JetSeqSet(path, extra=["pt", "eta"],
seq_maxlen={"x": 50})
data_iter = DataIterator(dset, batch_size=128)
batch = data_iter.next()
x_shape = data_iter.get_shape("x", batch_shape=False)
model = build_a_model(x_shape)
y_score = model.predict_on_batch([batch.x])
print("y_score: {}".format(y_score.shape))
def get_data_iter(path,
seq_maxlen,
extra=[],
batch_size=128,
**kwargs):
dset = PIDOneHotSet(path=path, seq_maxlen=seq_maxlen, extra=extra)
data_iter = DataIterator(dset, batch_size=batch_size, **kwargs)
return data_iter
def _test():
from keras4hep.projects.qgjets.utils import get_dataset_paths
path = get_dataset_paths(min_pt=100)["training"]
dset = JetSeqSet(path,
extra=["pt", "eta"],
seq_maxlen={
"x_kin": 50,
"x_pid": 50
})
data_iter = DataIterator(dset, batch_size=128)
batch = data_iter.next()
for key, value in batch.iteritems():
print(key, value.shape)
print(data_iter.get_shape("x_pid", False))
print(data_iter.get_shape("x_kin", True))
data_iter.fit_generator_input = {"x": ["x_kin", "x_pid"], "y": ["y"]}
data_iter.fit_generator_mode = True
for idx, (x, y) in enumerate(data_iter):
if idx == 3:
break
print(len(x))
for each in x:
print("x: {}".format(each.shape))
def get_data_iter(self,
path,
batch_size,
cycle,
fit_generator_mode):
dataset = self.get_dataset(path)
data_iter = DataIterator(
dataset,
batch_size=batch_size,
cycle=cycle,
fit_generator_mode=fit_generator_mode)
return data_iter
def _test():
path = "/store/slowmoyang/QGJets/dijet_100_110/dijet_100_110_test.root"
dset = JetSeqSet(path, extra=["pt", "eta"], seq_maxlen={"x": 50})
data_iter = DataIterator(dset, batch_size=128)
batch = data_iter.next()
for key, value in batch.iteritems():
print(key, value.shape)
print(data_iter.get_shape("x", False))
print(data_iter.get_shape("x", True))
data_iter.fit_generator_input = {"x": ["x"], "y": ["y"]}
data_iter.fit_generator_mode = True
for idx, (x, y) in enumerate(data_iter):
if idx == 3:
break
print(len(x))
for each in x:
print("x: {}".format(each.shape))
def get_data_iter(path, batch_size=128, full_info=False, extra=[], **kwargs):
dset = BDTVarSet(path=path, full_info=full_info, extra=extra)
data_iter = DataIterator(dset, batch_size=batch_size, **kwargs)
return data_iter
def get_data_iter(path, prep_path=None, batch_size=128, extra=[], **kwargs):
dset = C10Set(path=path, prep_path=prep_path, extra=extra)
data_iter = DataIterator(dset, batch_size=batch_size, **kwargs)
return data_iter