Loading deepchem/models/__init__.py +31 −14 Original line number Diff line number Diff line Loading @@ -54,16 +54,32 @@ class Model(object): raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") Loading Loading @@ -140,15 +156,13 @@ class Model(object): y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True, pad_batches=pad_batches): batch_size, deterministic=True): n_samples = len(X_batch) y_pred_batch = self.predict_on_batch(X_batch) ################################################################### DEBUG #print("X_batch.shape, y_batch.shape") #print(X_batch.shape, y_batch.shape) #print("y_pred_batch.shape") #print(y_pred_batch.shape) ################################################################### DEBUG ########################################################## DEBUG y_pred_batch = self.predict_on_batch(X_batch, pad_batch=pad_batches) # Discard any padded predictions y_pred_batch = y_pred_batch[:n_samples] ########################################################## DEBUG y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) Loading Loading @@ -358,10 +372,13 @@ class Model(object): y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True, pad_batches=pad_batches): y_pred_batch = self.predict_proba_on_batch(X_batch) batch_size = len(y_batch) y_pred_batch = np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes)) batch_size, deterministic=True): ################################################################# DEBUG n_samples = len(X_batch) y_pred_batch = self.predict_proba_on_batch(X_batch, pad_batch=pad_batches) y_pred_batch = y_pred_batch[:n_samples] ################################################################# DEBUG y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks, n_classes)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) Loading deepchem/models/keras_models/__init__.py +26 −2 Original line number Diff line number Diff line Loading @@ -55,7 +55,18 @@ class KerasModel(Model): model.load_weights(h5_filename) self.model_instance = model def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Keras Models. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict_on_batch(X) # TODO(rbharath): The methods below aren't extensible and depend on Loading @@ -67,5 +78,18 @@ class KerasModel(Model): def get_num_tasks(self): return self.model_instance.n_tasks def predict_proba_on_batch(self, X, n_classes=2): def predict_proba_on_batch(self, X, pad_batch=False, n_classes=2): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. n_classes: int Number of classifier classes """ return self.model_instance.predict_proba_on_batch(X, n_classes) deepchem/models/sklearn_models/__init__.py +18 −2 Original line number Diff line number Diff line Loading @@ -33,15 +33,31 @@ class SklearnModel(Model): self.model_instance.fit(X, y) y_pred_raw = self.model_instance.predict(X) def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict(X) def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """ Makes per-class predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict_proba(X) Loading deepchem/models/tensorflow_models/__init__.py +6 −3 Original line number Diff line number Diff line Loading @@ -277,7 +277,7 @@ class TensorflowGraphModel(object): self.verbosity) ############################################################## TIMING def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """Return model output for the provided input. Restore(checkpoint) must have previously been called on this object. Loading @@ -297,6 +297,8 @@ class TensorflowGraphModel(object): AssertionError: If model is not in evaluation mode. ValueError: If output and labels are not both 3D or both 2D. """ if pad_batch: X = pad_features(self.batch_size, X) if not self._restored_model: self.restore() Loading Loading @@ -514,7 +516,7 @@ class TensorflowClassifier(TensorflowGraphModel): name='labels_%d' % task))) return labels def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """Return model output for the provided input. Restore(checkpoint) must have previously been called on this object. Loading @@ -532,10 +534,11 @@ class TensorflowClassifier(TensorflowGraphModel): AssertionError: If model is not in evaluation mode. ValueError: If output and labels are not both 3D or both 2D. """ if pad_batch: X = pad_features(self.batch_size, X) if not self._restored_model: self.restore() with self.eval_graph.graph.as_default(): # run eval data through the model n_tasks = self.n_tasks outputs = [] Loading Loading
deepchem/models/__init__.py +31 −14 Original line number Diff line number Diff line Loading @@ -54,16 +54,32 @@ class Model(object): raise NotImplementedError( "Each model is responsible for its own fit_on_batch method.") def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ raise NotImplementedError( "Each model is responsible for its own predict_on_batch method.") Loading Loading @@ -140,15 +156,13 @@ class Model(object): y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True, pad_batches=pad_batches): batch_size, deterministic=True): n_samples = len(X_batch) y_pred_batch = self.predict_on_batch(X_batch) ################################################################### DEBUG #print("X_batch.shape, y_batch.shape") #print(X_batch.shape, y_batch.shape) #print("y_pred_batch.shape") #print(y_pred_batch.shape) ################################################################### DEBUG ########################################################## DEBUG y_pred_batch = self.predict_on_batch(X_batch, pad_batch=pad_batches) # Discard any padded predictions y_pred_batch = y_pred_batch[:n_samples] ########################################################## DEBUG y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) Loading Loading @@ -358,10 +372,13 @@ class Model(object): y_preds = [] n_tasks = self.get_num_tasks() for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches( batch_size, deterministic=True, pad_batches=pad_batches): y_pred_batch = self.predict_proba_on_batch(X_batch) batch_size = len(y_batch) y_pred_batch = np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes)) batch_size, deterministic=True): ################################################################# DEBUG n_samples = len(X_batch) y_pred_batch = self.predict_proba_on_batch(X_batch, pad_batch=pad_batches) y_pred_batch = y_pred_batch[:n_samples] ################################################################# DEBUG y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks, n_classes)) y_pred_batch = undo_transforms(y_pred_batch, transformers) y_preds.append(y_pred_batch) y_pred = np.vstack(y_preds) Loading
deepchem/models/keras_models/__init__.py +26 −2 Original line number Diff line number Diff line Loading @@ -55,7 +55,18 @@ class KerasModel(Model): model.load_weights(h5_filename) self.model_instance = model def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Keras Models. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict_on_batch(X) # TODO(rbharath): The methods below aren't extensible and depend on Loading @@ -67,5 +78,18 @@ class KerasModel(Model): def get_num_tasks(self): return self.model_instance.n_tasks def predict_proba_on_batch(self, X, n_classes=2): def predict_proba_on_batch(self, X, pad_batch=False, n_classes=2): """ Makes predictions of class probabilities on given batch of new data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. n_classes: int Number of classifier classes """ return self.model_instance.predict_proba_on_batch(X, n_classes)
deepchem/models/sklearn_models/__init__.py +18 −2 Original line number Diff line number Diff line Loading @@ -33,15 +33,31 @@ class SklearnModel(Model): self.model_instance.fit(X, y) y_pred_raw = self.model_instance.predict(X) def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """ Makes predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict(X) def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """ Makes per-class predictions on batch of data. Parameters ---------- X: np.ndarray Features pad_batch: bool, optional Ignored for Sklearn Model. Only used for Tensorflow models with rigid batch-size requirements. """ return self.model_instance.predict_proba(X) Loading
deepchem/models/tensorflow_models/__init__.py +6 −3 Original line number Diff line number Diff line Loading @@ -277,7 +277,7 @@ class TensorflowGraphModel(object): self.verbosity) ############################################################## TIMING def predict_on_batch(self, X): def predict_on_batch(self, X, pad_batch=False): """Return model output for the provided input. Restore(checkpoint) must have previously been called on this object. Loading @@ -297,6 +297,8 @@ class TensorflowGraphModel(object): AssertionError: If model is not in evaluation mode. ValueError: If output and labels are not both 3D or both 2D. """ if pad_batch: X = pad_features(self.batch_size, X) if not self._restored_model: self.restore() Loading Loading @@ -514,7 +516,7 @@ class TensorflowClassifier(TensorflowGraphModel): name='labels_%d' % task))) return labels def predict_proba_on_batch(self, X): def predict_proba_on_batch(self, X, pad_batch=False): """Return model output for the provided input. Restore(checkpoint) must have previously been called on this object. Loading @@ -532,10 +534,11 @@ class TensorflowClassifier(TensorflowGraphModel): AssertionError: If model is not in evaluation mode. ValueError: If output and labels are not both 3D or both 2D. """ if pad_batch: X = pad_features(self.batch_size, X) if not self._restored_model: self.restore() with self.eval_graph.graph.as_default(): # run eval data through the model n_tasks = self.n_tasks outputs = [] Loading
