Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is there something wrong with me? Why is the shape equals <unknown>? #4

Open
Liaokang123456 opened this issue Oct 11, 2022 · 0 comments

Comments

@Liaokang123456
Copy link

Liaokang123456 commented Oct 11, 2022

import h5py
data = h5py.File("data.hdf5","r")

writer = tf.io.TFRecordWriter("./tfrecord_1011")

#data = np.array(data)
dtype = np.float32
onehots_elements = {
'H': np.array([1, 0, 0, 0, 0, 0, 0], dtype=dtype),
'C': np.array([0, 1, 0, 0, 0, 0, 0], dtype=dtype),
'N': np.array([0, 0, 1, 0, 0, 0, 0], dtype=dtype),
'O': np.array([0, 0, 0, 1, 0, 0, 0], dtype=dtype),
'F': np.array([0, 0, 0, 0, 1, 0, 0], dtype=dtype),
'S': np.array([0, 0, 0, 0, 0, 1, 0], dtype=dtype),
'CL': np.array([0, 0, 0, 0, 0, 0, 1], dtype=dtype),
'Cl': np.array([0, 0, 0, 0, 0, 0, 1], dtype=dtype),
}
count = 0

for key in data: # Iterates over each Unique Identifier
coordinates = data[key]['coordinates'][()]
elements = data[key]['elements'][()]
monopoles = data[(key)]['monopoles'][()]
dipoles = data[(key)]['dipoles'][()]
quadrupoles = data[key]['quadrupoles'][()]
#print("element,type",elements)
elements = np.char.decode(elements,encoding="utf-8")
tensor = [onehots_elements[e] for e in elements]
graphs = build_graph(coordinates, elements, cutoff=4.0, num_kernels=32)
batch = {
'nodes': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.nodes).numpy()])),
'edges': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.edges).numpy()])),
'coordinates': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(coordinates).numpy()])),
'n_node': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.n_node).numpy()])),
'n_edge': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.n_edge).numpy()])),
'senders': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.senders).numpy()])),
'receivers': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(graphs.receivers).numpy()])),
'monopoles': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(monopoles).numpy()])),
'dipoles': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(dipoles).numpy()])),
'quadrupoles': tf.train.Feature(bytes_list=tf.train.BytesList(value=[tf.io.serialize_tensor(quadrupoles).numpy()])),
}
example = tf.train.Example(features=tf.train.Features(feature=batch)).SerializeToString()
writer.write(example)
count+=1
if count==1:
break
print("go on")

dtype_record = tf.float32
def load_data(record):
batch = tf.io.parse_single_example(record, feature_description)
nodes = tf.io.parse_tensor(batch['nodes'], out_type=dtype_record)
edges = tf.io.parse_tensor(batch['edges'], out_type=dtype_record)
coords = tf.io.parse_tensor(batch['coordinates'], out_type=dtype_record)
n_node = tf.io.parse_tensor(batch['n_node'], out_type=tf.int32)
n_edge = tf.io.parse_tensor(batch['n_edge'], out_type=tf.int32)
senders = tf.io.parse_tensor(batch['senders'], out_type=tf.int32)
receivers = tf.io.parse_tensor(batch['receivers'], out_type=tf.int32)
monopoles = tf.io.parse_tensor(batch['monopoles'], out_type=dtype_record)
dipoles = tf.io.parse_tensor(batch['dipoles'], out_type=dtype_record)
quadrupoles = D_Q(tf.io.parse_tensor(batch['quadrupoles'], out_type=dtype_record))
graph = gn.graphs.GraphsTuple(nodes, edges, globals=None, receivers=receivers, senders=senders, n_node=n_node, n_edge=n_edge)
return graph, coords, monopoles, dipoles, quadrupoles

DATASET_FOLDER = "./tfrecord_1011"

import json
from google.protobuf.json_format import MessageToJson

dataset = tf.data.TFRecordDataset("./tfrecord_1011")
for d in dataset:
ex = tf.train.Example()
ex.ParseFromString(d.numpy())
m = json.loads(MessageToJson(ex))
print(m['features']['feature'].keys(),m['features']['feature'].values())
dataset = tf.data.TFRecordDataset([DATASET_FOLDER.format(x) for x in np.random.choice(1, 1, replace=False)], num_parallel_reads=2)
dataset = dataset
.repeat()
.map(load_data, num_parallel_calls=tf.data.AUTOTUNE)
.prefetch(tf.data.AUTOTUNE)
.apply(tf.data.experimental.ignore_errors())
.shuffle(32, reshuffle_each_iteration=True)
dataset
<ShuffleDataset element_spec=(GraphsTuple(nodes=TensorSpec(shape=, dtype=tf.float32, name=None), edges=TensorSpec(shape=, dtype=tf.float32, name=None), receivers=TensorSpec(shape=, dtype=tf.int32, name=None), senders=TensorSpec(shape=, dtype=tf.int32, name=None), globals=NoneTensorSpec(), n_node=TensorSpec(shape=, dtype=tf.int32, name=None), n_edge=TensorSpec(shape=, dtype=tf.int32, name=None)), TensorSpec(shape=, dtype=tf.float32, name=None), TensorSpec(shape=, dtype=tf.float32, name=None), TensorSpec(shape=, dtype=tf.float32, name=None), TensorSpec(shape=, dtype=tf.float32, name=None))>
Is there something wrong with me? Why is the shape equals ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant