Commit 3f42da48 authored by Bharat123rox's avatar Bharat123rox
Browse files

Refactor code in models/ folder

parent 19eeac11

deepchem/models/cnn.py

+9 −6
Original line number Diff line number Diff line
@@ -6,7 +6,10 @@ from deepchem.models.layers import SwitchedDropout 
from deepchem.metrics import to_one_hot

from tensorflow.keras.layers import Input, Dense, Reshape, Softmax, Dropout, Activation, Lambda

import tensorflow.keras.layers as layers

import collections

try:

  from collections.abc import Sequence as SequenceCollection

except:

  from collections import Sequence as SequenceCollection





class CNN(KerasModel):
@@ -128,15 +131,15 @@ class CNN(KerasModel): 
    n_layers = len(layer_filters)

    if not isinstance(kernel_size, list):

      kernel_size = [kernel_size] * n_layers

    if not isinstance(strides, collections.Sequence):

    if not isinstance(strides, SequenceCollection):

      strides = [strides] * n_layers

    if not isinstance(weight_init_stddevs, collections.Sequence):

    if not isinstance(weight_init_stddevs, SequenceCollection):

      weight_init_stddevs = [weight_init_stddevs] * (n_layers + 1)

    if not isinstance(bias_init_consts, collections.Sequence):

    if not isinstance(bias_init_consts, SequenceCollection):

      bias_init_consts = [bias_init_consts] * (n_layers + 1)

    if not isinstance(dropouts, collections.Sequence):

    if not isinstance(dropouts, SequenceCollection):

      dropouts = [dropouts] * n_layers

    if not isinstance(activation_fns, collections.Sequence):

    if not isinstance(activation_fns, SequenceCollection):

      activation_fns = [activation_fns] * n_layers

    if weight_decay_penalty != 0.0:

      if weight_decay_penalty_type == 'l1':

deepchem/models/fcnet.py

+12 −9
Original line number Diff line number Diff line
@@ -6,7 +6,10 @@ import time 
import numpy as np

import tensorflow as tf

import threading

import collections

try:

  from collections.abc import Sequence as SequenceCollection

except:

  from collections import Sequence as SequenceCollection



import deepchem as dc

from deepchem.models import KerasModel
@@ -94,13 +97,13 @@ class MultitaskClassifier(KerasModel): 
    self.n_features = n_features

    self.n_classes = n_classes

    n_layers = len(layer_sizes)

    if not isinstance(weight_init_stddevs, collections.Sequence):

    if not isinstance(weight_init_stddevs, SequenceCollection):

      weight_init_stddevs = [weight_init_stddevs] * n_layers

    if not isinstance(bias_init_consts, collections.Sequence):

    if not isinstance(bias_init_consts, SequenceCollection):

      bias_init_consts = [bias_init_consts] * n_layers

    if not isinstance(dropouts, collections.Sequence):

    if not isinstance(dropouts, SequenceCollection):

      dropouts = [dropouts] * n_layers

    if not isinstance(activation_fns, collections.Sequence):

    if not isinstance(activation_fns, SequenceCollection):

      activation_fns = [activation_fns] * n_layers

    if weight_decay_penalty != 0.0:

      if weight_decay_penalty_type == 'l1':
@@ -240,13 +243,13 @@ class MultitaskRegressor(KerasModel): 
    self.n_tasks = n_tasks

    self.n_features = n_features

    n_layers = len(layer_sizes)

    if not isinstance(weight_init_stddevs, collections.Sequence):

    if not isinstance(weight_init_stddevs, SequenceCollection):

      weight_init_stddevs = [weight_init_stddevs] * (n_layers + 1)

    if not isinstance(bias_init_consts, collections.Sequence):

    if not isinstance(bias_init_consts, SequenceCollection):

      bias_init_consts = [bias_init_consts] * (n_layers + 1)

    if not isinstance(dropouts, collections.Sequence):

    if not isinstance(dropouts, SequenceCollection):

      dropouts = [dropouts] * n_layers

    if not isinstance(activation_fns, collections.Sequence):

    if not isinstance(activation_fns, SequenceCollection):

      activation_fns = [activation_fns] * n_layers

    if weight_decay_penalty != 0.0:

      if weight_decay_penalty_type == 'l1':

deepchem/models/gan.py

+4 −1
Original line number Diff line number Diff line
@@ -2,6 +2,9 @@ 


from deepchem.models import KerasModel, layers, losses

from tensorflow.keras.layers import Input, Lambda, Layer, Softmax, Reshape, Multiply

try:

  from collections.abc import Sequence

except:

  from collections import Sequence

import numpy as np

import tensorflow as tf

deepchem/models/graph_models.py

+12 −9
Original line number Diff line number Diff line 
import collections

try:

  from collections.abc import Sequence as SequenceCollection

except:

  from collections import Sequence as SequenceCollection



import deepchem as dc

import numpy as np
@@ -181,20 +184,20 @@ class WeaveModel(KerasModel): 
    if mode not in ['classification', 'regression']:

      raise ValueError("mode must be either 'classification' or 'regression'")



    if not isinstance(n_atom_feat, collections.Sequence):

    if not isinstance(n_atom_feat, SequenceCollection):

      n_atom_feat = [n_atom_feat] * n_weave

    if not isinstance(n_pair_feat, collections.Sequence):

    if not isinstance(n_pair_feat, SequenceCollection):

      n_pair_feat = [n_pair_feat] * n_weave

    n_layers = len(fully_connected_layer_sizes)

    if not isinstance(conv_weight_init_stddevs, collections.Sequence):

    if not isinstance(conv_weight_init_stddevs, SequenceCollection):

      conv_weight_init_stddevs = [conv_weight_init_stddevs] * n_weave

    if not isinstance(weight_init_stddevs, collections.Sequence):

    if not isinstance(weight_init_stddevs, SequenceCollection):

      weight_init_stddevs = [weight_init_stddevs] * n_layers

    if not isinstance(bias_init_consts, collections.Sequence):

    if not isinstance(bias_init_consts, SequenceCollection):

      bias_init_consts = [bias_init_consts] * n_layers

    if not isinstance(dropouts, collections.Sequence):

    if not isinstance(dropouts, SequenceCollection):

      dropouts = [dropouts] * n_layers

    if not isinstance(activation_fns, collections.Sequence):

    if not isinstance(activation_fns, SequenceCollection):

      activation_fns = [activation_fns] * n_layers

    if weight_decay_penalty != 0.0:

      if weight_decay_penalty_type == 'l1':
@@ -790,7 +793,7 @@ class _GraphConvKerasModel(tf.keras.Model): 
    self.mode = mode

    self.uncertainty = uncertainty



    if not isinstance(dropout, collections.Sequence):

    if not isinstance(dropout, SequenceCollection):

      dropout = [dropout] * (len(graph_conv_layers) + 1)

    if len(dropout) != len(graph_conv_layers) + 1:

      raise ValueError('Wrong number of dropout probabilities provided')

deepchem/models/layers.py

+7 −4
Original line number Diff line number Diff line 
# -*- coding: utf-8 -*-

import tensorflow as tf

import numpy as np

import collections

try:

  from collections.abc import Sequence as SequenceCollection

except:

  from collections import Sequence as SequenceCollection

from typing import Callable, Dict, List

from tensorflow.keras import activations, initializers, backend

from tensorflow.keras.layers import Dropout, BatchNormalization
@@ -1098,7 +1101,7 @@ class NeighborList(tf.keras.layers.Layer): 
    return config



  def call(self, inputs):

    if isinstance(inputs, collections.Sequence):

    if isinstance(inputs, SequenceCollection):

      if len(inputs) != 1:

        raise ValueError("NeighborList can only have one input")

      inputs = inputs[0]
@@ -2118,7 +2121,7 @@ class Highway(tf.keras.layers.Layer): 
    return config



  def build(self, input_shape):

    if isinstance(input_shape, collections.Sequence):

    if isinstance(input_shape, SequenceCollection):

      input_shape = input_shape[0]

    out_channels = input_shape[1]
@@ -2140,7 +2143,7 @@ class Highway(tf.keras.layers.Layer): 
    self.built = True



  def call(self, inputs):

    if isinstance(inputs, collections.Sequence):

    if isinstance(inputs, SequenceCollection):

      parent = inputs[0]

    else:

      parent = inputs

CRA Git | Maintained and supported by SUSTech CRA and CCSE