python - raspberry - tensorflow seq2seq
El recorte de degradado parece ahogarse en None (1)
Estoy tratando de agregar recorte de degradado a mi gráfico. Usé el enfoque que se recomienda aquí: ¿Cómo aplicar efectivamente el recorte de degradado en el flujo del tensor?
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)
Pero cuando enciendo el recorte de degradado, obtengo el siguiente seguimiento de pila:
<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.
¿Cómo resuelvo este problema?
Entonces, una opción que parece funcionar es esta:
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)
Parece que compute_gradients devuelve None en lugar de un cero tensor cuando el gradiente sería un tensor cero y tf.clip_by_value no admite un valor None. Así que simplemente no le pase None y no guarde ninguno.