def forward(self, bottom, top):
pred = bottom[0].data()
label = bottom[1].data()[:, np.newaxis]
prob = logexp.exp(pred)
numexpr.evaluate("prob / (1. + prob)", out=prob)
diff = bottom[0].init_diff(setzero=False)
numexpr.evaluate("label - prob", out=diff)
self._loss = np.dot(label.flat, logexp.log(prob).flat) + \
np.dot((1. - label).flat, logexp.log(1. - prob).flat)
# finally, scale down by the number of data points
# Also, since we we computing the Loss (minimizing), we change the
# sign of the loss value.
diff *= - self.spec['weight'] / diff.shape[0]
self._loss *= - self.spec['weight'] / diff.shape[0]
def forward(self, bottom, top):
pred = bottom[0].data()
label = bottom[1].data()[:, np.newaxis]
prob = logexp.exp(pred)
numexpr.evaluate("prob / (1. + prob)", out=prob)
diff = bottom[0].init_diff(setzero=False)
numexpr.evaluate("label - prob", out=diff)
self._loss = np.dot(label.flat, logexp.log(prob).flat) + \
np.dot((1. - label).flat, logexp.log(1. - prob).flat)
# finally, scale down by the number of data points
# Also, since we we computing the Loss (minimizing), we change the
# sign of the loss value.
diff *= -self.spec['weight'] / diff.shape[0]
self._loss *= -self.spec['weight'] / diff.shape[0]
def forward(self, bottom, top):
prob = bottom[0].data()
label = bottom[1].data()
diff = bottom[0].init_diff()
if label.ndim == 1:
# The labels are given as a sparse vector.
indices = np.arange(diff.shape[0])
prob_sub = np.ascontiguousarray(prob[indices, label])
diff[indices, label] = 1. / prob_sub
self._loss = logexp.log(prob_sub).sum()
else:
numexpr.evaluate('label / prob', out=diff)
self._loss = np.dot(label.flat, logexp.log(prob).flat)
# finally, scale down by the number of data points
diff *= - self.spec['weight'] / diff.shape[0]
self._loss *= - self.spec['weight'] / diff.shape[0]
def forward(self, bottom, top):
prob = bottom[0].data()
label = bottom[1].data()
diff = bottom[0].init_diff()
if label.ndim == 1:
# The labels are given as a sparse vector.
indices = np.arange(diff.shape[0])
prob_sub = np.ascontiguousarray(prob[indices, label])
diff[indices, label] = 1. / prob_sub
self._loss = logexp.log(prob_sub).sum()
else:
numexpr.evaluate('label / prob', out=diff)
self._loss = np.dot(label.flat, logexp.log(prob).flat)
# finally, scale down by the number of data points
diff *= -self.spec['weight'] / diff.shape[0]
self._loss *= -self.spec['weight'] / diff.shape[0]
def forward(self, bottom, top):
pred = bottom[0].data()
prob = self._prob.init_data(pred.shape, pred.dtype, setdata=False)
prob[:] = pred
prob -= prob.max(axis=1)[:, np.newaxis]
logexp.exp(prob, out=prob)
prob /= prob.sum(axis=1)[:, np.newaxis]
diff = bottom[0].init_diff(setzero=False)
diff[:] = prob
logexp.log(prob, out=prob)
label = bottom[1].data()
if label.ndim == 1:
# The labels are given as a sparse vector.
diff[np.arange(diff.shape[0]), label] -= 1.
self._loss = -prob[np.arange(diff.shape[0]), label].sum()
else:
# The labels are given as a dense matrix.
diff -= label
self._loss = -np.dot(prob.flat, label.flat)
# finally, scale down by the number of data points
diff *= self.spec['weight'] / diff.shape[0]
self._loss *= self.spec['weight'] / diff.shape[0]
def forward(self, bottom, top):
pred = bottom[0].data()
prob = self._prob.init_data(
pred.shape, pred.dtype, setdata=False)
prob[:] = pred
prob -= prob.max(axis=1)[:, np.newaxis]
logexp.exp(prob, out=prob)
prob /= prob.sum(axis=1)[:, np.newaxis]
diff = bottom[0].init_diff(setzero=False)
diff[:] = prob
logexp.log(prob, out=prob)
label = bottom[1].data()
if label.ndim == 1:
# The labels are given as a sparse vector.
diff[np.arange(diff.shape[0]), label] -= 1.
self._loss = -prob[np.arange(diff.shape[0]), label].sum()
else:
# The labels are given as a dense matrix.
diff -= label
self._loss = -np.dot(prob.flat, label.flat)
# finally, scale down by the number of data points
diff *= self.spec['weight'] / diff.shape[0]
self._loss *= self.spec['weight'] / diff.shape[0]
