Python 构造张量流双射体误差
我不太会使用tensorflow。我想构造一个具有以下性质的Bijter：它取一个N维概率分布p（x1，x2，…，xn），它只变换两个特定的维数i和j，使得席席＝Xi，xj′＝xj*EXP（s（席））+t（xj），其中S和T是利用神经网络实现的两个函数。它输出p（x1，x2，…，xi'，…，xj'，…，xn）。 我有一个基本代码，如下所示：Python 构造张量流双射体误差,python,tensorflow,machine-learning,unsupervised-learning,tensorflow-probability,Python,Tensorflow,Machine Learning,Unsupervised Learning,Tensorflow Probability,我不太会使用tensorflow。我想构造一个具有以下性质的Bijter：它取一个N维概率分布p（x1，x2，…，xn），它只变换两个特定的维数i和j，使得席席＝Xi，xj′＝xj*EXP（s（席））+t（xj），其中S和T是利用神经网络实现的两个函数。它输出p（x1，x2，…，xi'，…，xj'，…，xn）。 我有一个基本代码，如下所示： def net(x, out_size, block_w_id, block_d_id, layer_id): x = tf.contrib.l
def net(x, out_size, block_w_id, block_d_id, layer_id):
x = tf.contrib.layers.fully_connected(x, 256, reuse=tf.AUTO_REUSE, scope='x1_block_w_{}_block_d_{}_layer_{}'.format(block_w_id, \
block_d_id,\
layer_id))
x = tf.contrib.layers.fully_connected(x, 256, reuse=tf.AUTO_REUSE, scope='x2_block_w_{}_block_d_{}_layer_{}'.format(block_w_id,\
block_d_id,\
layer_id))
y = tf.contrib.layers.fully_connected(x, out_size, reuse=tf.AUTO_REUSE, scope='y_block_w_{}_block_d_{}_layer_{}'.format(block_w_id,\
block_d_id,\
layer_id))
# return layers.stack(x, layers.fully_connected(reuse=tf.AUTO_REUSE), [512, 512, out_size])
return y
但它没有像我想的那样起作用。当我使用该类时，它会弹出一个错误：
base_dist = tfd.MultivariateNormalDiag(loc=tf.zeros([2], DTYPE))
num_bijectors = 4
bijectors = []
bijectors.append(NVPCoupling(input_idx1=0, input_idx2=1, \
block_w_id=0, block_d_id=0, layer_id=0))
bijectors.append(NVPCoupling(input_idx1=1, input_idx2=0, \
block_w_id=0, block_d_id=0, layer_id=1))
bijectors.append(NVPCoupling(input_idx1=0, input_idx2=1, \
block_w_id=0, block_d_id=0, layer_id=2))
bijectors.append(NVPCoupling(input_idx1=0, input_idx2=1, \
block_w_id=0, block_d_id=0, layer_id=3))
flow_bijector = tfb.Chain(list(reversed(bijectors)))
dist = tfd.TransformedDistribution(
distribution=base_dist,
bijector=flow_bijector)
dist.sample(1000)
有误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-16-04da05d30f8d> in <module>()
----> 1 dist.sample(1000)
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/ops/distributions/distribution.pyc in sample(self, sample_shape, seed, name)
708 samples: a `Tensor` with prepended dimensions `sample_shape`.
709 """
--> 710 return self._call_sample_n(sample_shape, seed, name)
711
712 def _log_prob(self, value):
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/ops/distributions/transformed_distribution.pyc in _call_sample_n(self, sample_shape, seed, name, **kwargs)
412 # returned result.
413 y = self.bijector.forward(x, **kwargs)
--> 414 y = self._set_sample_static_shape(y, sample_shape)
415
416 return y
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/ops/distributions/distribution.pyc in _set_sample_static_shape(self, x, sample_shape)
1220 shape = tensor_shape.TensorShape(
1221 [None]*(ndims - event_ndims)).concatenate(self.event_shape)
-> 1222 x.set_shape(x.get_shape().merge_with(shape))
1223
1224 # Infer batch shape.
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.pyc in merge_with(self, other)
671 return TensorShape(new_dims)
672 except ValueError:
--> 673 raise ValueError("Shapes %s and %s are not compatible" % (self, other))
674
675 def concatenate(self, other):
ValueError: Shapes (1000, 4) and (?, 2) are not compatible
---------------------------------------------------------------------------
ValueError回溯（最近一次调用上次）
在（）
---->1区样品（1000）
/示例中的Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/Python/ops/distributions/distribution.pyc（self、sample_shape、seed、name）
708个样本：一个带有前置尺寸“样本形状”的“张量”。
709 """
-->710返回自我。调用样本（样本形状、种子、名称）
711
712定义日志问题（自身，值）：
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/Python/ops/distributions/transformed_distribution.pyc in_call_sample_n（self，sample_shape，seed，name，**kwargs）
412#返回结果。
413 y=自双喷射器向前（x，**kwargs）
-->414 y=自身。\设置\样本\静态\形状（y，样本\形状）
415
416返回y
/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/Python/ops/distributions/distribution.pyc in\u set\u sample\u static\u shape（self，x，sample\u shape）
1220形状=张量_形状。张量形状(
1221[None]*（ndims-event\u ndims））.concatenate（self.event\u形状）
->1222 x.set_shape（x.get_shape（）.将_与（shape）合并）
1223
1224#推断批次形状。
/库/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/Python/framework/tensor\u shape.pyc与（self，other）合并
671返回张力形状（新尺寸）
672除值错误外：
-->673提升值错误（“形状%s和%s不兼容”%（自身、其他））
674
675 def串联（自身、其他）：
ValueError:形状（1000,4）和（？，2）不兼容
真的希望一些专家能帮助我理解我哪里做错了，以及如何纠正。非常感谢！
H.我认为问题就在这里（为了清晰起见，稍微重新格式化）： 这假设了
idx2>idx1idx1=1idx2=0\u forwardprint("self.idx1: %s" % self.idx1)
print("self.idx2: %s" % self.idx2)
print("x[:,0:self.idx1]: %s" % x[:,0:self.idx1].shape)
print("x_left: %s" % x_left.shape)
print("x[:, self.idx1+1:self.idx2]: %s" %
x[:, self.idx1+1:self.idx2].shape)
print("x_right.shape: %s" % x_right.shape)
print("y_right: %s" % y_right.shape)
print("x[:, (self.idx2+1):]: %s" % x[:, (self.idx2+1):].shape)
print("output_tensor.shape: %s" % output_tensor.shape)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 0)
output_tensor.shape: (1000, 2)
self.idx1: 1
self.idx2: 0
x[:,0:self.idx1]: (1000, 1)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 1)
output_tensor.shape: (1000, 4)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 2)
output_tensor.shape: (1000, 4)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 2)
output_tensor.shape: (1000, 4)
print("self.idx1: %s" % self.idx1)
print("self.idx2: %s" % self.idx2)
print("x[:,0:self.idx1]: %s" % x[:,0:self.idx1].shape)
print("x_left: %s" % x_left.shape)
print("x[:, self.idx1+1:self.idx2]: %s" %
x[:, self.idx1+1:self.idx2].shape)
print("x_right.shape: %s" % x_right.shape)
print("y_right: %s" % y_right.shape)
print("x[:, (self.idx2+1):]: %s" % x[:, (self.idx2+1):].shape)
print("output_tensor.shape: %s" % output_tensor.shape)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 0)
output_tensor.shape: (1000, 2)
self.idx1: 1
self.idx2: 0
x[:,0:self.idx1]: (1000, 1)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 1)
output_tensor.shape: (1000, 4)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 2)
output_tensor.shape: (1000, 4)
self.idx1: 0
self.idx2: 1
x[:,0:self.idx1]: (1000, 0)
x_left: (1000, 1)
x[:, self.idx1+1:self.idx2]: (1000, 0)
x_right.shape: (1000, 1)
y_right: (1000, 1)
x[:, (self.idx2+1):]: (1000, 2)
output_tensor.shape: (1000, 4)