python - ValueError : No gradients provided for any variable while doing regression for integer values,，其中包括使用 keras 的底片

Question

我有一个问题，我需要从图像中预测一些整数。问题是这也包括一些负整数。我做了一些研究并遇到了泊松，它确实计算了回归，但是这不起作用，因为我也需要预测一些负整数，导致泊松输出 nan 作为它的损失。我正在考虑使用 Lambda 来舍入我的模型的输出，但这导致了这个错误:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/var/folders/nc/c4mgwn897qbg8g52tp3mhbjr0000gp/T/ipykernel_8618/1788039059.py in <module>
----> 1 model.fit(x_train, y_train,callbacks=[callback], epochs = 999)

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1181                 _r=1):
   1182               callbacks.on_train_batch_begin(step)
-> 1183               tmp_logs = self.train_function(iterator)
   1184               if data_handler.should_sync:
   1185                 context.async_wait()

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    887 
    888       with OptionalXlaContext(self._jit_compile):
--> 889         result = self._call(*args, **kwds)
    890 
    891       new_tracing_count = self.experimental_get_tracing_count()

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    931       # This is the first call of __call__, so we have to initialize.
    932       initializers = []
--> 933       self._initialize(args, kwds, add_initializers_to=initializers)
    934     finally:
    935       # At this point we know that the initialization is complete (or less

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    761     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    762     self._concrete_stateful_fn = (
--> 763         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    764             *args, **kwds))
    765 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   3048       args, kwargs = None, None
   3049     with self._lock:
-> 3050       graph_function, _ = self._maybe_define_function(args, kwargs)
   3051     return graph_function
   3052 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3442 
   3443           self._function_cache.missed.add(call_context_key)
-> 3444           graph_function = self._create_graph_function(args, kwargs)
   3445           self._function_cache.primary[cache_key] = graph_function
   3446 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3277     arg_names = base_arg_names + missing_arg_names
   3278     graph_function = ConcreteFunction(
-> 3279         func_graph_module.func_graph_from_py_func(
   3280             self._name,
   3281             self._python_function,

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    997         _, original_func = tf_decorator.unwrap(python_func)
    998 
--> 999       func_outputs = python_func(*func_args, **func_kwargs)
   1000 
   1001       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    670         # the function a weak reference to itself to avoid a reference cycle.
    671         with OptionalXlaContext(compile_with_xla):
--> 672           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    673         return out
    674 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    984           except Exception as e:  # pylint:disable=broad-except
    985             if hasattr(e, "ag_error_metadata"):
--> 986               raise e.ag_error_metadata.to_exception(e)
    987             else:
    988               raise

ValueError: in user code:

    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:855 train_function  *
        return step_function(self, iterator)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:845 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1285 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica
        return fn(*args, **kwargs)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:838 run_step  **
        outputs = model.train_step(data)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:799 train_step
        self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:530 minimize
        return self.apply_gradients(grads_and_vars, name=name)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:630 apply_gradients
        grads_and_vars = optimizer_utils.filter_empty_gradients(grads_and_vars)
    /Users/jr123456jr987654321/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/utils.py:75 filter_empty_gradients
        raise ValueError("No gradients provided for any variable: %s." %

    ValueError: No gradients provided for any variable: ['conv2d_2/kernel:0', 'conv2d_2/bias:0', 'conv2d_3/kernel:0', 'conv2d_3/bias:0', 'dense_3/kernel:0', 'dense_3/bias:0', 'dense_4/kernel:0', 'dense_4/bias:0', 'dense_5/kernel:0', 'dense_5/bias:0'].

这是我对 Lambda 层的实现:

filter_size = (3,3)
filters = 32
pool = 2

input_layer = keras.Input(shape=(100,300,1))

conv_extractor = layers.Conv2D(filters,filter_size, activation='relu')(input_layer)
conv_extractor = layers.MaxPooling2D(pool_size=(pool, pool))(conv_extractor)
conv_extractor = layers.Conv2D(filters,filter_size, activation='relu')(conv_extractor)
conv_extractor = layers.MaxPooling2D(pool_size=(pool, pool))(conv_extractor)

#conv_extractor = layers.Reshape(target_shape=(100 // (pool ** 2), (100 // (pool ** 2)) * filters))(conv_extractor)
shape = ((100 // 4), (300 // 4) * 32)
#conv_extractor = layers.Dense(512, activation='relu')(conv_extractor)
conv_extractor = layers.Reshape(target_shape=(23,2336))(conv_extractor)

gru_1 = GRU(512, return_sequences=True)(conv_extractor)
gru_1b = GRU(512, return_sequences=True, go_backwards=True)(conv_extractor)
gru1_merged = add([gru_1, gru_1b])
gru_2 = GRU(512, return_sequences=True)(gru1_merged)
gru_2b = GRU(512, return_sequences=True, go_backwards=True)(gru1_merged)

x = layers.concatenate([gru_2, gru_2b])   # move concatenate layer aside
x = layers.Flatten()(x)
inner = layers.Dense(30, activation='LeakyReLU')(x)
inner = layers.Dense(10, activation='LeakyReLU')(inner)
inner = layers.Dense(3, activation='LeakyReLU')(inner)
inner  layers.Lambda(keras.backend.round)(inner)


model = Model(input_layer,inner)
model.compile(loss = "MeanSquaredError", optimizer = optimizers.Adam(2e-4), metrics=['accuracy'])
model.fit(x_train, y_train, epochs = 999)

为什么会出现这个错误？我该如何解决？如果无法修复，是否有其他方法可以解决我的问题(例如通过修改泊松损失函数)？

Answer 1

添加最小值(在本例中为负)，使所有值 >= 0。然后使用泊松分布。