Loading deepchem/models/tf_new_models/multitask_classifier.py +5 −6 Original line number Diff line number Diff line Loading @@ -96,7 +96,7 @@ class MultitaskGraphClassifier(Model): self.optimizer_beta2 = beta2 # Set epsilon self.epsilon = K.epsilon() self.epsilon = 1e-7 self.add_optimizer() # Initialize Loading @@ -109,10 +109,10 @@ class MultitaskGraphClassifier(Model): def build(self): # Create target inputs self.label_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="label_placeholder", dtype='bool')) self.weight_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="weight_placholder", dtype='float32')) self.label_placeholder = Input(tensor=tf.placeholder( dtype='bool', shape=(None,self.n_tasks), name="label_placeholder")) self.weight_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="weight_placholder")) feat = self.model.return_outputs() output = model_ops.multitask_logits( Loading Loading @@ -151,7 +151,6 @@ class MultitaskGraphClassifier(Model): # Get other optimizer information # TODO(rbharath): Figure out how to handle phase appropriately # old_dict = {K.learning_phase() : training} feed_dict = merge_dicts([targets_dict, atoms_dict ]) return feed_dict Loading deepchem/models/tf_new_models/multitask_regressor.py +5 −6 Original line number Diff line number Diff line Loading @@ -51,7 +51,7 @@ class MultitaskGraphRegressor(Model): self.optimizer_beta2 = beta2 # Set epsilon self.epsilon = K.epsilon() self.epsilon = 1e-7 self.add_optimizer() # Initialize Loading @@ -64,10 +64,10 @@ class MultitaskGraphRegressor(Model): def build(self): # Create target inputs self.label_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="label_placeholder", dtype='float32')) self.weight_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="weight_placholder", dtype='float32')) self.label_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="label_placeholder")) self.weight_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="weight_placholder")) feat = self.model.return_outputs() feat_size = feat.get_shape()[-1].value Loading Loading @@ -116,7 +116,6 @@ class MultitaskGraphRegressor(Model): # Get other optimizer information # TODO(rbharath): Figure out how to handle phase appropriately # old_dict = {K.learning_phase() : training} feed_dict = merge_dicts([targets_dict, atoms_dict]) return feed_dict Loading deepchem/nn/copy.py +1 −0 Original line number Diff line number Diff line Loading @@ -12,6 +12,7 @@ from . import initializations from . import regularizers from . import activations from . import constraints import tensorflow as tf from keras import backend as K def to_list(x): Loading Loading
deepchem/models/tf_new_models/multitask_classifier.py +5 −6 Original line number Diff line number Diff line Loading @@ -96,7 +96,7 @@ class MultitaskGraphClassifier(Model): self.optimizer_beta2 = beta2 # Set epsilon self.epsilon = K.epsilon() self.epsilon = 1e-7 self.add_optimizer() # Initialize Loading @@ -109,10 +109,10 @@ class MultitaskGraphClassifier(Model): def build(self): # Create target inputs self.label_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="label_placeholder", dtype='bool')) self.weight_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="weight_placholder", dtype='float32')) self.label_placeholder = Input(tensor=tf.placeholder( dtype='bool', shape=(None,self.n_tasks), name="label_placeholder")) self.weight_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="weight_placholder")) feat = self.model.return_outputs() output = model_ops.multitask_logits( Loading Loading @@ -151,7 +151,6 @@ class MultitaskGraphClassifier(Model): # Get other optimizer information # TODO(rbharath): Figure out how to handle phase appropriately # old_dict = {K.learning_phase() : training} feed_dict = merge_dicts([targets_dict, atoms_dict ]) return feed_dict Loading
deepchem/models/tf_new_models/multitask_regressor.py +5 −6 Original line number Diff line number Diff line Loading @@ -51,7 +51,7 @@ class MultitaskGraphRegressor(Model): self.optimizer_beta2 = beta2 # Set epsilon self.epsilon = K.epsilon() self.epsilon = 1e-7 self.add_optimizer() # Initialize Loading @@ -64,10 +64,10 @@ class MultitaskGraphRegressor(Model): def build(self): # Create target inputs self.label_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="label_placeholder", dtype='float32')) self.weight_placeholder = Input(tensor=K.placeholder( shape=(None,self.n_tasks), name="weight_placholder", dtype='float32')) self.label_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="label_placeholder")) self.weight_placeholder = Input(tensor=tf.placeholder( dtype='float32', shape=(None,self.n_tasks), name="weight_placholder")) feat = self.model.return_outputs() feat_size = feat.get_shape()[-1].value Loading Loading @@ -116,7 +116,6 @@ class MultitaskGraphRegressor(Model): # Get other optimizer information # TODO(rbharath): Figure out how to handle phase appropriately # old_dict = {K.learning_phase() : training} feed_dict = merge_dicts([targets_dict, atoms_dict]) return feed_dict Loading
deepchem/nn/copy.py +1 −0 Original line number Diff line number Diff line Loading @@ -12,6 +12,7 @@ from . import initializations from . import regularizers from . import activations from . import constraints import tensorflow as tf from keras import backend as K def to_list(x): Loading
