Save and load ani

import tensorflow as tf

from deepchem.models import TensorGraph

from deepchem.models.tensorgraph.layers import Feature, Conv1D, Dense, Flatten, Reshape, Squeeze, Transpose, \

    CombineMeanStd, Repeat, Gather, GRU, L2Loss, Concat, SoftMax, Constant, Variable, Add, Multiply, Log, InteratomicL2Distances, \

  CombineMeanStd, Repeat, Gather, GRU, L2Loss, Concat, SoftMax, Constant, Variable, Add, Multiply, Log, \

  InteratomicL2Distances, \

  SoftMaxCrossEntropy, ReduceMean, ToFloat, ReduceSquareDifference, Conv2D, MaxPool, ReduceSum, GraphConv, GraphPool, \

  GraphGather, BatchNorm, WeightedError, \

  LSTMStep, AttnLSTMEmbedding, IterRefLSTMEmbedding

from deepchem.models.tensorgraph.graph_layers import Combine_AP, Separate_AP, \

  WeaveLayer, WeaveGather, DTNNEmbedding, DTNNGather, DTNNStep, \

  DTNNExtract, DAGLayer, DAGGather, MessagePassing, SetGather

from models.tensorgraph.symmetry_functions import AtomicDifferentiatedDense

def test_Conv1D_pickle():

  tg.set_loss(Gather)

  tg.build()

  tg.save()

def test_AtomicDifferentialDense_pickle():

  max_atoms = 23

  atom_features = 100

  tg = TensorGraph()

  atom_feature = Feature(shape=(None, max_atoms, atom_features))

  atom_numbers = Feature(shape=(None, max_atoms))

  atomic_differential_dense = AtomicDifferentiatedDense(max_atoms=23, out_channels=5,

                                                        in_layers=[atom_feature, atom_numbers])

  tg.add_output(atomic_differential_dense)

  tg.set_loss(atomic_differential_dense)

  tg.build()

  tg.save()

import deepchem as dc

# Load Tox21 dataset

tasks, datasets, transformers = dc.molnet.load_qm7_from_mat(

  featurizer='BPSymmetryFunction')

train_dataset, valid_dataset, test_dataset = datasets

# tasks, datasets, transformers = dc.molnet.load_qm7_from_mat(

#   featurizer='BPSymmetryFunction')

# train_dataset, valid_dataset, test_dataset = datasets

# Batch size of models

max_atoms = 23

batch_size = 128

batch_size = 16

layer_structures = [128, 128, 64]

atom_number_cases = [1, 6, 7, 8, 16]

ANItransformer = dc.trans.ANITransformer(

    max_atoms=max_atoms, atom_cases=atom_number_cases)

train_dataset = ANItransformer.transform(train_dataset)

valid_dataset = ANItransformer.transform(valid_dataset)

test_dataset = ANItransformer.transform(test_dataset)

n_feat = ANItransformer.get_num_feats() - 1

# ANItransformer = dc.trans.ANITransformer(

#     max_atoms=max_atoms, atom_cases=atom_number_cases)

# train_dataset = ANItransformer.transform(train_dataset)

# valid_dataset = ANItransformer.transform(valid_dataset)

# test_dataset = ANItransformer.transform(test_dataset)

# print(test_dataset.data_dir)

# n_feat = ANItransformer.get_num_feats() - 1

# Fit models

metric = [

]

model = dc.models.ANIRegression(

    len(tasks),

  1,

  max_atoms,

    n_feat,

  1000,

  layer_structures=layer_structures,

  atom_number_cases=atom_number_cases,

  batch_size=batch_size,

  learning_rate=0.001,

  use_queue=False,

  mode="regression")

model.build()

# Fit trained model

model.fit(train_dataset, nb_epoch=300, checkpoint_interval=100)

valid_scores = model.evaluate(valid_dataset, metric, transformers)

model.save()

model = TensorGraph.load_from_dir(model.model_dir)

train_scores2 = model.evaluate(train_dataset, metric, transformers)

valid_scores2 = model.evaluate(valid_dataset, metric, transformers)