渐变剪裁似乎在无上窒息
Posted
技术标签:
【中文标题】渐变剪裁似乎在无上窒息【英文标题】:Gradient clipping appears to choke on None 【发布时间】:2017-01-10 17:33:21 【问题描述】:我正在尝试将渐变剪辑添加到我的图表中。我使用了这里推荐的方法:How to effectively apply gradient clipping in tensor flow?
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
if gradient_clipping:
gradients = optimizer.compute_gradients(loss)
clipped_gradients = [(tf.clip_by_value(grad, -1, 1), var) for grad, var in gradients]
opt = optimizer.apply_gradients(clipped_gradients, global_step=global_step)
else:
opt = optimizer.minimize(loss, global_step=global_step)
但是当我打开渐变剪裁时,我得到以下堆栈跟踪:
<ipython-input-19-be0dcc63725e> in <listcomp>(.0)
61 if gradient_clipping:
62 gradients = optimizer.compute_gradients(loss)
---> 63 clipped_gradients = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gradients]
64 opt = optimizer.apply_gradients(clipped_gradients, global_step=global_step)
65 else:
/home/armence/mlsandbox/venv/lib/python3.4/site-packages/tensorflow/python/ops/clip_ops.py in clip_by_value(t, clip_value_min, clip_value_max, name)
51 with ops.op_scope([t, clip_value_min, clip_value_max], name,
52 "clip_by_value") as name:
---> 53 t = ops.convert_to_tensor(t, name="t")
54
55 # Go through list of tensors, for each value in each tensor clip
/home/armence/mlsandbox/venv/lib/python3.4/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref)
619 for base_type, conversion_func in funcs_at_priority:
620 if isinstance(value, base_type):
--> 621 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
622 if ret is NotImplemented:
623 continue
/home/armence/mlsandbox/venv/lib/python3.4/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
178 as_ref=False):
179 _ = as_ref
--> 180 return constant(v, dtype=dtype, name=name)
181
182
/home/armence/mlsandbox/venv/lib/python3.4/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
161 tensor_value = attr_value_pb2.AttrValue()
162 tensor_value.tensor.CopyFrom(
--> 163 tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))
164 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
165 const_tensor = g.create_op(
/home/armence/mlsandbox/venv/lib/python3.4/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape)
344 else:
345 if values is None:
--> 346 raise ValueError("None values not supported.")
347 # if dtype is provided, forces numpy array to be the type
348 # provided if possible.
ValueError: None values not supported.
我该如何解决这个问题?
【问题讨论】:
【参考方案1】:所以,一个似乎可行的选择是:
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
if gradient_clipping:
gradients = optimizer.compute_gradients(loss)
def ClipIfNotNone(grad):
if grad is None:
return grad
return tf.clip_by_value(grad, -1, 1)
clipped_gradients = [(ClipIfNotNone(grad), var) for grad, var in gradients]
opt = optimizer.apply_gradients(clipped_gradients, global_step=global_step)
else:
opt = optimizer.minimize(loss, global_step=global_step)
当梯度是零张量并且 tf.clip_by_value 不支持 None 值时,compute_gradients 返回 None 而不是零张量。所以不要将 None 传递给它并保留 None 值。
【讨论】:
如果有人有更好的想法,我非常愿意接受。回答我自己的问题不是计划。以上是关于渐变剪裁似乎在无上窒息的主要内容,如果未能解决你的问题,请参考以下文章