tutorial seq2seq raspberry neural network learning instalar espaƱol ejemplos como python machine-learning tensorflow

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.