GCN_reload (10009118) · Commits · 钟慕尧 / deepchem

deepchem/models/layers.py

+65 −10

Original line number	Diff line number	Diff line
		@@ -127,14 +127,14 @@ class GraphConv(tf.keras.layers.Layer):
		num_deg = 2 * self.max_degree + (1 - self.min_degree)
		self.W_list = [
		self.add_weight(
		name='kernel',
		name='kernel'+str(k),
		shape=(int(input_shape[0][-1]), self.out_channel),
		initializer='glorot_uniform',
		trainable=True) for k in range(num_deg)
		]
		self.b_list = [
		self.add_weight(
		name='bias',
		name='bias'+str(k),
		shape=(self.out_channel,),
		initializer='zeros',
		trainable=True) for k in range(num_deg)
		@@ -2344,7 +2344,13 @@ class WeaveLayer(tf.keras.layers.Layer):
		input_shape: tuple
		Ignored since we don't need the input shape to create internal weights.
		"""
		init = initializers.get(self.init) # Set weight initialization

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.W_AA = init([self.n_atom_input_feat, self.n_hidden_AA])
		self.b_AA = backend.zeros(shape=[
		@@ -2566,7 +2572,14 @@ class WeaveGather(tf.keras.layers.Layer):

		def build(self, input_shape):
		if self.compress_post_gaussian_expansion:
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.W = init([self.n_input * 11, self.n_input])
		self.b = backend.zeros(shape=[self.n_input])
		self.built = True
		@@ -2673,7 +2686,14 @@ class DTNNEmbedding(tf.keras.layers.Layer):
		return config

		def build(self, input_shape):
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.embedding_list = init([self.periodic_table_length, self.n_embedding])
		self.built = True

		@@ -2726,7 +2746,14 @@ class DTNNStep(tf.keras.layers.Layer):
		return config

		def build(self, input_shape):
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.W_cf = init([self.n_embedding, self.n_hidden])
		self.W_df = init([self.n_distance, self.n_hidden])
		self.W_fc = init([self.n_hidden, self.n_embedding])
		@@ -2811,7 +2838,14 @@ class DTNNGather(tf.keras.layers.Layer):
		def build(self, input_shape):
		self.W_list = []
		self.b_list = []
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		prev_layer_size = self.n_embedding
		for i, layer_size in enumerate(self.layer_sizes):
		self.W_list.append(init([prev_layer_size, layer_size]))
		@@ -3217,9 +3251,16 @@ class EdgeNetwork(tf.keras.layers.Layer):
		return config

		def build(self, input_shape):

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		n_pair_features = self.n_pair_features
		n_hidden = self.n_hidden
		init = initializers.get(self.init)
		self.W = init([n_pair_features, n_hidden * n_hidden])
		self.b = backend.zeros(shape=(n_hidden * n_hidden,))
		self.built = True
		@@ -3249,7 +3290,14 @@ class GatedRecurrentUnit(tf.keras.layers.Layer):

		def build(self, input_shape):
		n_hidden = self.n_hidden
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.Wz = init([n_hidden, n_hidden])
		self.Wr = init([n_hidden, n_hidden])
		self.Wh = init([n_hidden, n_hidden])
		@@ -3304,7 +3352,14 @@ class SetGather(tf.keras.layers.Layer):
		return config

		def build(self, input_shape):
		init = initializers.get(self.init)

		def init(input_shape):
		return self.add_weight(
		name='kernel',
		shape=(input_shape[0], input_shape[1]),
		initializer=self.init,
		trainable=True)

		self.U = init((2 * self.n_hidden, 4 * self.n_hidden))
		self.b = tf.Variable(
		np.concatenate((np.zeros(self.n_hidden), np.ones(self.n_hidden),

deepchem/models/tests/test_reload.py

+352 −363

File changed.

Preview size limit exceeded, changes collapsed.

Admin message