ValueError: Dimensions must be equal, but are 2 and 1 in time2vec example - tensorflow

Question

I have 2 inputs and 4 outputs. I want to use the time2vec to predict the outputs. I have used the code in https://towardsdatascience.com/time2vec-for-time-series-features-encoding-a03a4f3f937e, it works for one input and one output. But when I want to use for (2 inputs and four outputs) it gives me the following error:
import numpy as np
import tensorflow as tf
from keras.layers import Dense, Dropout, Activation, Flatten, LSTM, Embedding, Input, concatenate,
Lambda
from sklearn.preprocessing import MinMaxScaler
from keras.callbacks import EarlyStopping
import keras
import random
import os
from sklearn.metrics import mean_absolute_error
from tensorflow.keras.layers import *
from tensorflow.keras.models import *
from tensorflow.keras.callbacks import *
from tensorflow.keras.optimizers import *
from tensorflow.keras import backend as K
from kerashypetune import KerasGridSearch
import matplotlib.pyplot as plt
w = 5
ts = 10
nt = 10
ntest = nt + int(percent*nt)
X_train = np.random.rand(90,5,2)
X_test = np.random.rand(5,5,2)
y_train = np.random.rand(90,4)
y_test = np.random.rand(5,4)
""" ### DEFINE T2V LAYER ###
class T2V(Layer):
def __init__(self, output_dim=None, **kwargs):
self.output_dim = output_dim
super(T2V, self).__init__(**kwargs)
def build(self, input_shape):
self.W = self.add_weight(name='W', shape=(1, self.output_dim), initializer='uniform',
trainable=True)
self.P = self.add_weight(name='P',shape=(1,
self.output_dim),initializer='uniform',trainable=True)
self.w = self.add_weight(name='w',shape=(1, 1),initializer='uniform', trainable=True)
self.p = self.add_weight(name='p',shape=(1, 1),initializer='uniform',trainable=True)
super(T2V, self).build(input_shape)
def call(self, x):
original = self.w * x + self.p
sin_trans = K.sin(K.dot(x, self.W) + self.P)
return K.concatenate([sin_trans, original], -1)
CREATE GENERATOR FOR LSTM AND T2V
sequence_length = w
def gen_sequence(id_df, seq_length, seq_cols):
data_matrix = id_df[seq_cols].values
num_elements = data_matrix.shape[0]
for start, stop in zip(range(0, num_elements-seq_length), range(seq_length, num_elements)):
yield data_matrix[start:stop, :]
def gen_labels(id_df, seq_length, label):
data_matrix = id_df[label].values
num_elements = data_matrix.shape[0]
return data_matrix[seq_length:num_elements, :]
DEFINE MODEL STRUCTURES
def set_seed_TF2(seed):
tf.random.set_seed(seed)
os.environ['PYTHONHASHSEED'] = str(seed)
np.random.seed(seed)
random.seed(seed)
def T2V_NN(param, dim):
inp = Input(shape=(dim,2))
x = T2V(param['t2v_dim'])(inp)
x = LSTM(param['unit'], activation=param['act'])(x)
x = Dense(2)(x)
m = Model(inp, x)
m.compile(loss='mse', optimizer=Adam(lr=param['lr']))
return m
def NN(param, dim):
inp = Input(shape=(dim,2))
x = LSTM(param['unit'], activation=param['act'])(inp)
x = Dense(2)(x)
m = Model(inp, x)
m.compile(loss='mse', optimizer=Adam(lr=param['lr']))
return m
Param grid
param_grid = {'unit': [64,32],'t2v_dim': [128,64],'lr': [1e-2,1e-3], 'act': ['elu','relu'], 'epochs': 1,'batch_size': [512,1024]}
FIT T2V + LSTM
es = EarlyStopping(patience=5, verbose=0, min_delta=0.001, monitor='val_loss', mode='auto',
restore_best_weights=True)
hypermodel = lambda x: T2V_NN(param=x, dim=sequence_length)
kgs_t2v = KerasGridSearch(hypermodel, param_grid, monitor='val_loss', greater_is_better=False,
tuner_verbose=1)
kgs_t2v.set_seed(set_seed_TF2, seed=33)
kgs_t2v.search(X_train, y_train, validation_split=0.2, callbacks=[es], shuffle=False)
But when I run the model, I've got this error :
ValueError: Dimensions must be equal, but are 2 and 1 for '{{node t2v_2/MatMul}} = MatMul[T=DT_FLOAT,
transpose_a=false, transpose_b=false](t2v_2/Reshape, t2v_2/Reshape_1)' with input shapes: [?,2], [1,128].
Could you help me to solve this?

Answer 1

You have to change the parameters inside the T2V layer and inside your network in order to correctly match the shapes
class T2V(Layer):
def __init__(self, output_dim=None, **kwargs):
self.output_dim = output_dim
super(T2V, self).__init__(**kwargs)
def build(self, input_shape):
self.W = self.add_weight(name='W', shape=(input_shape[-1], self.output_dim),
initializer='uniform', trainable=True)
self.P = self.add_weight(name='P', shape=(input_shape[1], self.output_dim),
initializer='uniform', trainable=True)
self.w = self.add_weight(name='w', shape=(input_shape[1], 1),
initializer='uniform', trainable=True)
self.p = self.add_weight(name='p', shape=(input_shape[1], 1),
initializer='uniform', trainable=True)
super(T2V, self).build(input_shape)
def call(self, x):
original = self.w * x + self.p
sin_trans = K.sin(K.dot(x, self.W) + self.P)
return K.concatenate([sin_trans, original], -1)
create a dummy example
n_sample = 90
timesteps = 5
feat_inp = 2
feat_out = 4
X = np.random.uniform(0,1, (n_sample, timesteps, feat_inp))
y = np.random.uniform(0,1, (n_sample, feat_out))
def T2V_NN():
inp = Input(shape=(timesteps,feat_inp))
x = T2V(32)(inp)
x = LSTM(8)(x)
x = Dense(feat_out)(x)
m = Model(inp, x)
m.compile(loss='mse', optimizer='adam')
return m
model = T2V_NN()
model.fit(X,y, epochs=3)