Fixed errors in training models with uncertainty (5fdefa5a) · Commits · 钟慕尧 / deepchem

deepchem/models/fcnet.py

+13 −2

Original line number	Diff line number	Diff line
		@@ -314,8 +314,19 @@ class MultitaskRegressor(KerasModel):
		output_types = ['prediction', 'variance', 'loss', 'loss']

		def loss(outputs, labels, weights):
		diff = labels[0] - outputs[0]
		return tf.reduce_mean(diff * diff / tf.exp(outputs[1]) + outputs[1])
		output, labels = dc.models.losses._make_tf_shapes_consistent(
		outputs[0], labels[0])
		output, labels = dc.models.losses._ensure_float(output, labels)
		losses = tf.square(output - labels) / tf.exp(outputs[1]) + outputs[1]
		w = weights[0]
		if len(w.shape) < len(losses.shape):
		if tf.is_tensor(w):
		shape = tuple(w.shape.as_list())
		else:
		shape = w.shape
		shape = tuple(-1 if x is None else x for x in shape)
		w = tf.reshape(w, shape + (1,) * (len(losses.shape) - len(w.shape)))
		return tf.reduce_mean(losses * w) + sum(self.model.losses)
		else:
		outputs = [output]
		output_types = ['prediction']

deepchem/models/graph_models.py

+39 −6

Original line number	Diff line number	Diff line
		@@ -693,8 +693,19 @@ class DAGModel(KerasModel):
		output_types = ['prediction', 'variance', 'loss', 'loss']

		def loss(outputs, labels, weights):
		diff = labels[0] - outputs[0]
		return tf.reduce_mean(diff * diff / tf.exp(outputs[1]) + outputs[1])
		output, labels = dc.models.losses._make_tf_shapes_consistent(
		outputs[0], labels[0])
		output, labels = dc.models.losses._ensure_float(output, labels)
		losses = tf.square(output - labels) / tf.exp(outputs[1]) + outputs[1]
		w = weights[0]
		if len(w.shape) < len(losses.shape):
		if tf.is_tensor(w):
		shape = tuple(w.shape.as_list())
		else:
		shape = w.shape
		shape = tuple(-1 if x is None else x for x in shape)
		w = tf.reshape(w, shape + (1,) * (len(losses.shape) - len(w.shape)))
		return tf.reduce_mean(losses * w) + sum(self.model.losses)
		else:
		outputs = [output]
		output_types = ['prediction']
		@@ -961,8 +972,19 @@ class GraphConvModel(KerasModel):
		output_types = ['prediction', 'variance', 'loss', 'loss', 'embedding']

		def loss(outputs, labels, weights):
		diff = labels[0] - outputs[0]
		return tf.reduce_mean(diff * diff / tf.exp(outputs[1]) + outputs[1])
		output, labels = dc.models.losses._make_tf_shapes_consistent(
		outputs[0], labels[0])
		output, labels = dc.models.losses._ensure_float(output, labels)
		losses = tf.square(output - labels) / tf.exp(outputs[1]) + outputs[1]
		w = weights[0]
		if len(w.shape) < len(losses.shape):
		if tf.is_tensor(w):
		shape = tuple(w.shape.as_list())
		else:
		shape = w.shape
		shape = tuple(-1 if x is None else x for x in shape)
		w = tf.reshape(w, shape + (1,) * (len(losses.shape) - len(w.shape)))
		return tf.reduce_mean(losses * w) + sum(self.model.losses)
		else:
		output_types = ['prediction', 'embedding']
		loss = L2Loss()
		@@ -1102,8 +1124,19 @@ class MPNNModel(KerasModel):
		output_types = ['prediction', 'variance', 'loss', 'loss']

		def loss(outputs, labels, weights):
		diff = labels[0] - outputs[0]
		return tf.reduce_mean(diff * diff / tf.exp(outputs[1]) + outputs[1])
		output, labels = dc.models.losses._make_tf_shapes_consistent(
		outputs[0], labels[0])
		output, labels = dc.models.losses._ensure_float(output, labels)
		losses = tf.square(output - labels) / tf.exp(outputs[1]) + outputs[1]
		w = weights[0]
		if len(w.shape) < len(losses.shape):
		if tf.is_tensor(w):
		shape = tuple(w.shape.as_list())
		else:
		shape = w.shape
		shape = tuple(-1 if x is None else x for x in shape)
		w = tf.reshape(w, shape + (1,) * (len(losses.shape) - len(w.shape)))
		return tf.reduce_mean(losses * w) + sum(self.model.losses)
		else:
		outputs = [output]
		output_types = ['prediction']

Admin message