While running a GCN model it seems that the size of the prediction is contingent upon the batch_size.
Here is some dummy data with 240 samples:
!pip install --pre deepchem
!pip install --pre rdkit
import deepchem as dc
import numpy as np
import tensorflow as tf
from deepchem.feat.mol_graphs import ConvMol
mol = ['C-C-O']*240
ftr = dc.feat.ConvMolFeaturizer(per_atom_fragmentation=False)
X=ftr.featurize(mol)
y = np.arange(0,240,1)
w = np.arange(0,240,1)
ids = np.arange(0,240,1)
ds = dc.data.NumpyDataset(X=X, y=y, ids=ids)
And here is the data_generator:
def data_generator(dataset, epochs=1, batch_size = 100, pad_batches = True):
print(dataset)
for ind, (X_b, y_b, w_b, ids_b) in enumerate(dataset.iterbatches(batch_size, epochs,
deterministic=False, pad_batches=pad_batches)):
multiConvMol = ConvMol.agglomerate_mols(X_b)
inputs = [multiConvMol.get_atom_features(), multiConvMol.deg_slice, np.array(multiConvMol.membership)]
for i in range(1, len(multiConvMol.get_deg_adjacency_lists())):
inputs.append(multiConvMol.get_deg_adjacency_lists()[i])
labels = [y_b]
weights = [w_b]
yield (inputs, labels, weights)
Now we can define the model and fit it to the dataset generated above:
batch_size = 100
n_tasks = 1
class TestModel(tf.keras.Model):
def __init__(self, model = 1):
super(TestModel, self).__init__()
self.model = model
#____________Test Model 1___________
if self.model == 1:
self.gc1 = GraphConv(128, activation_fn=tf.nn.tanh)
self.readout = GraphGather(batch_size=batch_size,
activation_fn=tf.nn.tanh)
self.dense2 = layers.Dense(1)
def call(self, inputs):
#____________Test Model 1___________
if self.model == 1:
gc1_output = self.gc1(inputs)
readout_output = self.readout([gc1_output]+ inputs[1:])
dense2_output = self.dense2(readout_output)
return dense2_output
#Fit_generator
print("_________\nFitting:")
testmodel = dc.models.KerasModel(TestModel(1), loss=dc.models.losses.L2Loss())
testmodel.fit_generator(data_generator(ds, epochs=1, batch_size = 100))
Finally we try to predict the dataset labels. Setting batch_size = 100 and pad_batches to False, we expect the shape of pred to be (240,1) but it comes out to be (300,1):
#Predict
print("_________\nPredicting:")
pred = testmodel.predict_on_generator(data_generator(ds, epochs = 2, batch_size = 100, pad_batches = False))
print(ds.y.shape, pred.shape)
_________
Predicting:
<NumpyDataset X.shape: (240,), y.shape: (240,), w.shape: (240,), ids: [0 1 2 ... 237 238 239], task_names: [0]>
(240,) (300, 1)
I assumed that it had something to do with the dataset not being a multiple of batch size and changed it to 80 and then 60. The former still returned a pred shape of (300,1) while the latter gave a shape of (400,1). I also tried batch sizes of 120 (which returned an error) and 40 (for which the output shape was (600,1))
Can someone solve the mystery?