corrected errors and added tests for SparseSoftmaxCrossEntropy (c0fc63dd) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/layers.py

+3 −1

Original line number	Diff line number	Diff line
		@@ -4319,7 +4319,9 @@ class Hingeloss(Layer):
		if len(inputs) != 2:
		raise ValueError()
		labels, logits = inputs[0], inputs[1]
		out_tensor = tf.losses.hinge_loss(labels=labels, logits=logits)
		reduction = tf.losses.Reduction
		out_tensor = tf.losses.hinge_loss(
		labels=labels, logits=logits, reduction=reduction.NONE)
		if set_tensors:
		self.out_tensor = out_tensor
		return out_tensor

deepchem/models/tensorgraph/tests/test_layers.py

+14 −1

Original line number	Diff line number	Diff line
		@@ -46,6 +46,7 @@ from deepchem.models.tensorgraph.layers import Sigmoid
		from deepchem.models.tensorgraph.layers import SigmoidCrossEntropy
		from deepchem.models.tensorgraph.layers import SoftMax
		from deepchem.models.tensorgraph.layers import SoftMaxCrossEntropy
		from deepchem.models.tensorgraph.layers import SparseSoftmaxCrossEntropy
		from deepchem.models.tensorgraph.layers import StopGradient
		from deepchem.models.tensorgraph.layers import TensorWrapper
		from deepchem.models.tensorgraph.layers import TimeSeriesDense
		@@ -382,6 +383,18 @@ class TestLayers(test_util.TensorFlowTestCase):
		out_tensor = out_tensor.eval()
		assert out_tensor.shape == (batch_size,)

		def test_sparse_softmax_cross_entropy(self):
		batch_size = 10
		n_features = 5
		logit_tensor = np.randon.rand(batch_size, n_features)
		label_tensor = np.random.rand(batch_size)
		with self.test_session() as sess:
		logit_tensor = tf.convert_to_tensor(logit_tensor, dtype=tf.float32)
		label_tensor = tf.convert_to_tensor(label_tensor, dtype=tf.float32)
		out_tensor = SparseSoftmaxCrossEntropy()(logit_tensor, label_tensor)
		out_tensor = out_tensor.eval()
		assert out_tensor.shape == (batch_size,)

		def test_reduce_mean(self):
		"""Test that ReduceMean can be invoked."""
		batch_size = 10
		@@ -879,7 +892,7 @@ class TestLayers(test_util.TensorFlowTestCase):

		def test_hingeloss(self):

		labels = 2
		labels = 1
		logits = 0.0001
		logits_tensor = np.random.uniform(logits)
		labels_tensor = np.random.rand(labels)

deepchem/models/tensorgraph/tests/test_layers_pickle.py

+14 −5

Original line number	Diff line number	Diff line
		@@ -10,7 +10,7 @@ from deepchem.models.tensorgraph.layers import Feature, Conv1D, Dense, Flatten,
		SoftMaxCrossEntropy, ReduceMean, ToFloat, ReduceSquareDifference, Conv2D, MaxPool2D, ReduceSum, GraphConv, GraphPool, \
		GraphGather, BatchNorm, WeightedError, ReLU, \
		Conv3D, MaxPool3D, Conv2DTranspose, Conv3DTranspose, \
		LSTMStep, AttnLSTMEmbedding, IterRefLSTMEmbedding, GraphEmbedPoolLayer, GraphCNN, Cast,Hingeloss
		LSTMStep, AttnLSTMEmbedding, IterRefLSTMEmbedding, GraphEmbedPoolLayer, GraphCNN, Cast,Hingeloss,SparseSoftmaxCrossEntropy
		from deepchem.models.tensorgraph.symmetry_functions import AtomicDifferentiatedDense
		from deepchem.models.tensorgraph.IRV import IRVLayer, IRVRegularize, Slice

		@@ -269,6 +269,17 @@ def test_SoftmaxCrossEntropy_pickle():
		tg.save()


		def test_SparseSoftmaxCrossEntropy_pickle():
		tg = TensorGraph()
		logits = Feature(shape=(tg.batch_size, 1))
		labels = Feature(shape=(tg.batch_size))
		layer = SparseSoftmaxCrossEntropy(in_layers=[logits, labels])
		tg.add_output(layer)
		tg.set_loss(layer)
		tg.build()
		tg.save()


		def test_SigmoidCrossEntropy_pickle():
		tg = TensorGraph()
		feature = Feature(shape=(tg.batch_size, 1))
		@@ -685,11 +696,9 @@ def test_Slice_pickle():


		def test_hingeloss_pickle():
		labels = 2
		logits = 0.001
		tg = TensorGraph()
		feature = Feature(shape=(tg.batch_size, 1))
		layer = Hingeloss(labels=labels, logits=logits, in_layers=[feature, feature])
		feature = Feature(shape=(1))
		layer = Hingeloss(in_layers=[feature, feature])
		tg.add_output(layer)
		tg.set_loss(layer)
		tg.build()

Admin message