我们从Python开源项目中，提取了以下21个代码示例，用于说明如何使用chainer.is_debug()。
def forward(self, inputs): x, t = inputs if chainer.is_debug(): if not ((0 <= t).all() and (t < x.shape[1]).all()): msg = 'Each label `t` need to satisfty `0 <= t < x.shape[1]`' raise ValueError(msg) xp = cuda.get_array_module(x) if xp is numpy: # This code is equivalent to `t.choose(x.T)`, but `numpy.choose` # does not work when `x.shape[1] > 32`. return x[six.moves.range(t.size), t], else: y = cuda.elementwise( 'S t, raw T x', 'T y', 'int ind[] = {i, t}; y = x[ind];', 'getitem_fwd' )(t, x) return y,
def forward(self, inputs): x, W = inputs if chainer.is_debug(): if not ((0 <= x).all() and (x < len(W)).all()): msg = 'Each `x` value need to satisfty `0 <= x < len(W)`' raise ValueError(msg) if self.ignore_label is not None: xp = cuda.get_array_module(*inputs) mask = (x == self.ignore_label) return xp.where( mask[..., None], 0, W.take(xp.where(mask, 0, x), axis=0)), return W.take(x, axis=0),
def forward_cpu(self, inputs): x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = softmax_log(x, False) if self.cache_score: self.y = numpy.exp(log_y) log_yd = numpy.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[numpy.maximum(t.ravel(), 0), six.moves.range(t.size)] # deal with the case where the SoftmaxCrossEntropy is # unpickled from the old version if getattr(self, 'normalize', True): count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = (log_p * (t.ravel() != self.ignore_label)).sum(keepdims=True) \ * (-self._coeff) return y.reshape(()),
def forward_gpu(self, inputs): cupy = cuda.cupy x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = softmax_log(x, self.use_cudnn) if self.cache_score: self.y = cupy.exp(log_y) if getattr(self, 'normalize', True): coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) ret = cuda.reduce( 'S t, raw T log_y, int32 n_channel, raw T coeff', 'T out', 't == -1 ? T(0) : log_y[_j * n_channel + t]', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self._coeff) return ret,
def forward_cpu(self, inputs): x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = numpy.log(x) if self.cache_score: self.y = x log_yd = numpy.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[numpy.maximum(t.ravel(), 0), six.moves.range(t.size)] if getattr(self, 'normalize', True): count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = (log_p * (t.ravel() != self.ignore_label)).sum(keepdims=True) * (-self._coeff) return y.reshape(()),
def forward_gpu(self, inputs): cupy = cuda.cupy x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = cupy.log(x) if self.cache_score: self.y = x if getattr(self, 'normalize', True): coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) ret = cuda.reduce( 'S t, raw T log_y, int32 n_channel, raw T coeff', 'T out', 't == -1 ? 0 : log_y[_j * n_channel + t]', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self._coeff) return ret,
def forward_cpu(self, inputs): x, t, w = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = softmax_log(x, False) if self.cache_score: self.y = numpy.exp(log_y) log_yd = numpy.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[numpy.maximum(t.ravel(), 0), six.moves.range(t.size)] # deal with the case where the SoftmaxCrossEntropy is # unpickled from the old version if getattr(self, 'normalize', True): count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = (log_p * (t.ravel() != self.ignore_label) * w.ravel()).sum(keepdims=True) \ * (-self._coeff) return y.reshape(()),
def forward_gpu(self, inputs): cupy = cuda.cupy x, t, w = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = softmax_log(x, self.use_cudnn) if self.cache_score: self.y = cupy.exp(log_y) if getattr(self, 'normalize', True): coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) ret = cuda.reduce( 'S t, T w, raw T log_y, int32 n_channel, raw T coeff', 'T out', 't == -1 ? T(0) : log_y[_j * n_channel + t] * w', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, w, log_y.reduced_view(), log_y.shape[-1], self._coeff) return ret,
def forward_cpu(self, inputs): x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x, self.use_cudnn) if self.cache_score: self.y = numpy.exp(log_y) if self.class_weight is not None: if self.class_weight.shape != x.shape: shape = [1 if d != 1 else -1 for d in six.moves.range(x.ndim)] self.class_weight = numpy.broadcast_to( self.class_weight.reshape(shape), x.shape) log_y *= self.class_weight log_yd = numpy.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[numpy.maximum(t.ravel(), 0), numpy.arange(t.size)] # deal with the case where the SoftmaxCrossEntropy is # unpickled from the old version if self.normalize: count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = (log_p * (t.ravel() != self.ignore_label)).sum(keepdims=True) \ * (-self._coeff) return y.reshape(()),
def forward_gpu(self, inputs): cupy = cuda.cupy x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x, self.use_cudnn) if self.cache_score: self.y = cupy.exp(log_y) if self.class_weight is not None: shape = [1 if d != 1 else -1 for d in six.moves.range(x.ndim)] log_y *= cupy.broadcast_to( self.class_weight.reshape(shape), x.shape) if self.normalize: coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) ret = cuda.reduce( 'S t, raw T log_y, int32 n_channel, raw T coeff', 'T out', 't == -1 ? T(0) : log_y[_j * n_channel + t]', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self._coeff) return ret,
def setUp(self): self.x = numpy.random.uniform(-1, 1, (2, 2)).astype(numpy.float32) # `0` is required to avoid NaN self.t = numpy.array([self.t_value, 0], dtype=numpy.int32) self.original_debug = chainer.is_debug() chainer.set_debug(True)
def forward(self, inputs): xp = cuda.get_array_module(inputs[0]) self.input_length = inputs[0] length_unigram = inputs[1] label_unigram = inputs[2] label_bigram = inputs[3] length_bigram = length_unigram xs = inputs[4:] if chainer.is_debug(): # batch size check. assert len(xs[0]) == len(label_unigram) assert len(xs[0]) == len(self.input_length) assert len(xs[0]) == len(length_unigram) # length check. assert len(xs) >= xp.max(self.input_length) assert len(label_unigram[0]) >= xp.max(length_unigram) # unit check assert xs[0].shape[1] > xp.max(label_unigram) assert xs[0].shape[1] > xp.max(label_bigram) assert xs[0].shape[1] > self.blank_symbol self.path_length = length_unigram * 3 + 1 yseq_shape = (len(xs),) + xs[0].shape self.yseq = _softmax(xp.vstack(xs).reshape(yseq_shape), xp) log_yseq = _log_matrix(self.yseq, xp, self.zero_padding) self.path = _label_to_path(label_unigram, label_bigram, self.blank_symbol, xp) self.prob_trans = _compute_transition_probability(log_yseq, self.input_length, label_unigram, length_unigram, label_bigram, length_bigram, self.path, self.path_length, xp, self.zero_padding) loss = -_logsumexp(self.prob_trans[0], xp, axis=1) if self.reduce == 'mean': loss = utils.force_array(xp.mean(loss)) return loss,
def forward_cpu(self, inputs): x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x) if self.cache_score: self.y = np.exp(log_y) if self.class_weight is not None: shape = [1 if d != 1 else -1 for d in six.moves.range(x.ndim)] log_y *= _broadcast_to(self.class_weight.reshape(shape), x.shape) log_yd = np.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[np.maximum(t.ravel(), 0), np.arange(t.size)] log_p *= (t.ravel() != self.ignore_label) if self.reduce == 'mean': # deal with the case where the SoftmaxCrossEntropy is # unpickled from the old version if self.normalize: count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = log_p.sum(keepdims=True) * (-self._coeff) return y.reshape(()), else: return -log_p.reshape(t.shape),
def setUp(self): self.link = links.EmbedID(2, 2) self.t = numpy.array([self.t_value], dtype=numpy.int32) self.original_debug = chainer.is_debug() chainer.set_debug(True)
def setUp(self): self.original_debug = chainer.is_debug() chainer.set_debug(True) self.one = numpy.array([1], numpy.float32) self.f = chainer.Function()
def setUp(self): self.x = numpy.random.uniform(-1, 1, (1, 2)).astype(numpy.float32) self.t = numpy.array([self.t_value], dtype=numpy.int32) self.original_debug = chainer.is_debug() chainer.set_debug(True)
def forward_cpu(self, inputs): x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x) if self.cache_score: self.y = np.exp(log_y) if self.class_weight is not None: shape = [1 if d != 1 else -1 for d in xrange(x.ndim)] log_y *= _broadcast_to(self.class_weight.reshape(shape), x.shape) log_yd = np.rollaxis(log_y, 1) log_yd = log_yd.reshape(len(log_yd), -1) log_p = log_yd[np.maximum(t.ravel(), 0), np.arange(t.size)] log_p *= (t.ravel() != self.ignore_label) if self.reduce == 'mean': # deal with the case where the SoftmaxCrossEntropy is # unpickled from the old version if self.normalize: count = (t != self.ignore_label).sum() else: count = len(x) self._coeff = 1.0 / max(count, 1) y = log_p.sum(keepdims=True) * (-self._coeff) return y.reshape(()), else: return -log_p.reshape(t.shape),
def forward_gpu(self, inputs): cupy = cuda.cupy x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x) if self.cache_score: self.y = cupy.exp(log_y) if self.class_weight is not None: shape = [1 if d != 1 else -1 for d in six.moves.range(x.ndim)] log_y *= cupy.broadcast_to( self.class_weight.reshape(shape), x.shape) if self.normalize: coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) if self.reduce == 'mean': ret = cuda.reduce( 'S t, raw T log_y, int32 n_channel, raw T coeff, ' 'S ignore_label', 'T out', 't == ignore_label ? T(0) : log_y[_j * n_channel + t]', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self._coeff, self.ignore_label) else: ret = cuda.elementwise( 'S t, raw T log_y, int32 n_channel, T ignore', 'T out', ''' if (t == ignore) { out = 0; } else { out = -log_y[i * n_channel + t]; } ''', 'softmax_crossent_no_reduce_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self.ignore_label) ret = ret.reshape(t.shape) return ret,
def forward_gpu(self, inputs): cupy = cuda.cupy x, t = inputs if chainer.is_debug(): self._check_input_values(x, t) log_y = log_softmax._log_softmax(x) if self.cache_score: self.y = cupy.exp(log_y) if self.class_weight is not None: shape = [1 if d != 1 else -1 for d in xrange(x.ndim)] log_y *= cupy.broadcast_to( self.class_weight.reshape(shape), x.shape) if self.normalize: coeff = cupy.maximum(1, (t != self.ignore_label).sum()) else: coeff = max(1, len(t)) self._coeff = cupy.divide(1.0, coeff, dtype=x.dtype) log_y = cupy.rollaxis(log_y, 1, log_y.ndim) if self.reduce == 'mean': ret = cuda.reduce( 'S t, raw T log_y, int32 n_channel, raw T coeff, ' 'S ignore_label', 'T out', 't == ignore_label ? T(0) : log_y[_j * n_channel + t]', 'a + b', 'out = a * -coeff[0]', '0', 'crossent_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self._coeff, self.ignore_label) else: ret = cuda.elementwise( 'S t, raw T log_y, int32 n_channel, T ignore', 'T out', ''' if (t == ignore) { out = 0; } else { out = -log_y[i * n_channel + t]; } ''', 'softmax_crossent_no_reduce_fwd' )(t, log_y.reduced_view(), log_y.shape[-1], self.ignore_label) ret = ret.reshape(t.shape) return ret,
