TF 1.0.1 (5639ccb5) · Commits · 钟慕尧 / deepchem

README.md

+2 −2

Original line number	Diff line number	Diff line
		@@ -44,7 +44,7 @@ You can install deepchem in a new conda environment using the conda commands in

		```bash
		bash scripts/install_deepchem_conda.sh deepchem
		pip install tensorflow-gpu==0.12.1 # If you want GPU support
		pip install tensorflow-gpu==1.0.1 # If you want GPU support
		git clone https://github.com/deepchem/deepchem.git # Clone deepchem source code from GitHub
		cd deepchem
		python setup.py install # Manual install
		@@ -95,7 +95,7 @@ via this installation procedure.
		contact your local sysadmin to work out a custom installation. If your
		version of Linux is recent, then the following command will work:
		```
		pip install tensorflow-gpu==0.12.1
		pip install tensorflow-gpu==1.0.1
		```

		9. `deepchem`: Clone the `deepchem` github repo:

+4 −1

Original line number	Diff line number	Diff line
		@@ -5,6 +5,8 @@ from __future__ import print_function
		from __future__ import division
		from __future__ import unicode_literals

		from pkg_resources import get_distribution

		import deepchem.data
		import deepchem.feat
		import deepchem.hyper
		@@ -16,3 +18,4 @@ import deepchem.trans
		import deepchem.utils
		import deepchem.dock
		import deepchem.molnet

+3 −3

Original line number	Diff line number	Diff line
		@@ -608,8 +608,8 @@ class TensorflowClassifier(TensorflowGraphModel):
		A tensor with shape batch_size containing the weighted cost for each
		example.
		"""
		return tf.mul(
		tf.nn.softmax_cross_entropy_with_logits(logits, labels), weights)
		return tf.multiply(
		tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels), weights)

		def add_label_placeholders(self, graph, name_scopes):
		"""Add Placeholders for labels for each task.
		@@ -762,7 +762,7 @@ class TensorflowRegressor(TensorflowGraphModel):
		A tensor with shape batch_size containing the weighted cost for each
		example.
		"""
		return tf.mul(0.5 * tf.square(output - labels), weights)
		return tf.multiply(0.5 * tf.square(output - labels), weights)

		def add_label_placeholders(self, graph, name_scopes):
		"""Add Placeholders for labels for each task.

+3 −3

Original line number	Diff line number	Diff line
		@@ -35,7 +35,7 @@ def weight_decay(penalty_type, penalty):
		else:
		raise NotImplementedError('Unsupported penalty_type %s' % penalty_type)
		cost *= penalty
		tf.scalar_summary('Weight Decay Cost', cost)
		tf.summary.scalar('Weight Decay Cost', cost)
		return cost


		@@ -124,8 +124,8 @@ class TensorflowLogisticRegression(TensorflowGraphModel):
		return loss

		def cost(self, logits, labels, weights):
		return tf.mul(
		tf.nn.sigmoid_cross_entropy_with_logits(logits, labels), weights)
		return tf.multiply(
		tf.nn.sigmoid_cross_entropy_with_logits(logits=logits, labels=labels), weights)

		def add_output_ops(self, graph, output):
		# adding output nodes of sigmoid function

+2 −2

Original line number	Diff line number	Diff line
		@@ -173,11 +173,11 @@ class ProgressiveJointRegressor(TensorflowMultiTaskRegressor):
		prev_layers.append(all_layers[(i - 1, prev_task)])
		# prev_layers is a list with elements of size
		# (batch_size, layer_sizes[i-1])
		prev_layer = tf.concat(1, prev_layers)
		prev_layer = tf.concat(axis=1, values=prev_layers)
		alpha = tf.Variable(tf.truncated_normal([
		1,
		], stddev=alpha_init_stddev))
		prev_layer = tf.mul(alpha, prev_layer)
		prev_layer = tf.multiply(alpha, prev_layer)
		prev_layer_size = task * layer_sizes[i - 1]
		print("Creating V_layer_%d_task%d of shape %s" %
		(i, task, str([prev_layer_size, layer_sizes[i - 1]])))