def top1(self, yhat):
yhatT = tf.transpose(yhat)
term1 = tf.reduce_mean(tf.nn.sigmoid(-gpu_diag_wide(yhat) + yhatT) +
tf.nn.sigmoid(yhatT**2),
axis=0)
term2 = tf.nn.sigmoid(gpu_diag_wide(yhat)**
2) / (self.batch_size + self.n_samples)
return tf.reduce_mean(term1 - term2)
def cross_entropy_logits(self, yhat, M):
if self.smoothing:
n_out = M + self.n_sample
return T.cast(
T.mean((1.0 -
(n_out /
(n_out - 1)) * self.smoothing) * gpu_diag_wide(yhat) +
(self.smoothing / (n_out - 1)) * T.sum(yhat, axis=1)),
theano.config.floatX)
else:
return T.cast(T.mean(gpu_diag_wide(yhat)), theano.config.floatX)
def top1(self, yhat, M):
ydiag = gpu_diag_wide(yhat).dimshuffle((0, 'x'))
return T.cast(
T.mean(
T.mean(T.nnet.sigmoid(-ydiag + yhat) + T.nnet.sigmoid(yhat**2),
axis=1) - T.nnet.sigmoid(ydiag**2) /
(M + self.n_sample)), theano.config.floatX)
def bpr_max(self, yhat):
softmax_scores = self.softmax_neg(yhat)
###tf.expand_dims(gpu_diag_wide(yhat),1) [y1,y1,y1,...,y1][y2,...]
term1 = - tf.log(
tf.reduce_sum(tf.sigmoid(tf.expand_dims(gpu_diag_wide(yhat),1) - yhat) * softmax_scores, axis=1) + 1e-24)
term2 = self.bpr_max_lambda * tf.reduce_sum((yhat ** 2) * softmax_scores, axis=1)
return tf.reduce_mean(term1 + term2)
def bpr_max(self, yhat, M):
softmax_scores = self.softmax_neg(yhat)
return T.cast(
T.mean(-T.log(
T.sum(T.nnet.sigmoid(
gpu_diag_wide(yhat).dimshuffle(
(0, 'x')) - yhat) * softmax_scores,
axis=1) + 1e-24) +
self.bpreg * T.sum((yhat**2) * softmax_scores, axis=1)),
theano.config.floatX)
def top1_max(self, yhat):
term1 = self.softmax_neg(yhat)
term2 = tf.sigmoid(-tf.expand_dims(gpu_diag_wide(yhat), 1) +
yhat) + tf.sigmoid(yhat**2)
return tf.reduce_mean(tf.reduce_sum(term1 * term2, axis=1))
def bpr(self, yhat):
yhatT = tf.transpose(yhat)
return tf.reduce_mean(
-tf.log(tf.nn.sigmoid(gpu_diag_wide(yhat) - yhatT)))
def cross_entropy(self, yhat):
return tf.reduce_mean(-tf.log(gpu_diag_wide(yhat) + 1e-24))
def top1_max(self, yhat, M):
softmax_scores = self.softmax_neg(yhat)
y = softmax_scores * (T.nnet.sigmoid(-gpu_diag_wide(yhat).dimshuffle(
(0, 'x')) + yhat) + T.nnet.sigmoid(yhat**2))
return T.cast(T.mean(T.sum(y, axis=1)), theano.config.floatX)
def bpr(self, yhat, M):
return T.cast(
T.mean(-T.log(
T.nnet.sigmoid(
gpu_diag_wide(yhat).dimshuffle((0, 'x')) - yhat))),
theano.config.floatX)
def top1_max(self, yhat, M):
softmax_scores = self.softmax_neg(yhat)
y = softmax_scores*(T.nnet.sigmoid(-gpu_diag_wide(yhat).dimshuffle((0, 'x'))+yhat)+T.nnet.sigmoid(yhat**2))
return T.cast(T.mean(T.sum(y, axis=1)), theano.config.floatX)
def top1(self, yhat, M):
ydiag = gpu_diag_wide(yhat).dimshuffle((0, 'x'))
return T.cast(T.mean(T.mean(T.nnet.sigmoid(-ydiag+yhat)+T.nnet.sigmoid(yhat**2), axis=1)-T.nnet.sigmoid(ydiag**2)/(M+self.n_sample)), theano.config.floatX)
def bpr_max(self, yhat, M):
softmax_scores = self.softmax_neg(yhat)
return T.cast(T.mean(-T.log(T.sum(T.nnet.sigmoid(gpu_diag_wide(yhat).dimshuffle((0,'x'))-yhat)*softmax_scores, axis=1)+1e-24)+self.bpreg*T.sum((yhat**2)*softmax_scores, axis=1)), theano.config.floatX)
def bpr(self, yhat, M):
return T.cast(T.mean(-T.log(T.nnet.sigmoid(gpu_diag_wide(yhat).dimshuffle((0, 'x'))-yhat))), theano.config.floatX)
def cross_entropy_logits(self, yhat, M):
if self.smoothing:
n_out = M + self.n_sample
return T.cast(T.mean((1.0-(n_out/(n_out-1))*self.smoothing) * gpu_diag_wide(yhat) + (self.smoothing/(n_out-1)) * T.sum(yhat, axis=1)), theano.config.floatX)
else:
return T.cast(T.mean(gpu_diag_wide(yhat)), theano.config.floatX)
