def __init__(self, channels, n_layers, n_out):
super().__init__()
tf.random.set_seed(0)
self.convs = []
for l in range(n_layers-1):
tf.random.set_seed(l)
self.convs.append(GINConv(channels, epsilon=0, mlp_hidden=[channels, channels], kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform'))
tf.random.set_seed(n_layers-1)
self.conv2 = GINConv(channels, epsilon=0, mlp_hidden=[channels, n_out], kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
def __init__(self, channels, n_layers):
super().__init__()
self.conv1 = GINConv(channels, epsilon=0, mlp_hidden=[channels, channels])
self.convs = []
for i in range(1, n_layers):
self.convs.append(
GINConv(channels, epsilon=0, mlp_hidden=[channels, channels]))
self.pool = GlobalAvgPool()
self.dense1 = Dense(channels, activation='relu')
self.dropout = Dropout(0.5)
self.dense2 = Dense(n_out, activation='softmax')
X, A, _, y = ogb.dataset_to_numpy(dataset, dtype='f8') A = [a.toarray() for a in A] F = X[0].shape[-1] X = pad_jagged_array(X, (N, F)) A = pad_jagged_array(A, (N, N)) X_tr, A_tr, y_tr = X[tr_idx], A[tr_idx], y[tr_idx] X_va, A_va, y_va = X[va_idx], A[va_idx], y[va_idx] X_te, A_te, y_te = X[te_idx], A[te_idx], y[te_idx] ################################################################################ # BUILD MODEL ################################################################################ X_in = Input(shape=(N, F)) A_in = Input(shape=(N, N)) X_1 = GINConv(32, mlp_hidden=[32], activation='relu')([X_in, A_in]) X_1, A_1 = MinCutPool(N // 2)([X_1, A_in]) X_2 = GINConv(32, mlp_hidden=[32], activation='relu')([X_1, A_1]) X_3 = GlobalSumPool()(X_2) output = Dense(n_out)(X_3) # Build model model = Model(inputs=[X_in, A_in], outputs=output) opt = Adam(lr=learning_rate) model.compile(optimizer=opt, loss='mse') model.summary() ################################################################################ # FIT MODEL ################################################################################ model.fit([X_tr, A_tr],