我正在为多类音频分类问题构建一个 CNN。我已经从我的音频文件中提取了频谱图特征，我正在尝试将 4D 数组传递给我的 CNN。我还为我的标签执行了 One-Hot 编码。但我不明白为什么我会得到这个 ValueError。请帮助。
这是我的代码：
D = [] # Dataset
for row in df.itertuples():
file_path = os.path.join('/Users/akellaniranjan/MyWorkspace/Projects/Hobby_Projects/Whistle_Based_Automation/Folder_Approach/',row.Fold,row.File)
y, sr = librosa.load(file_path,sr = 44100)
ps = librosa.feature.melspectrogram(y=y, sr=sr)
ps = ps[:,:128]
if ps.shape != (128, 128): continue
D.append( (ps, row.Class) )
X_train, y_train = zip(*D)
X_train = np.array([x.reshape( (128, 128, 1) ) for x in X_train])
le = LabelEncoder()
y_train = np_utils.to_categorical(le.fit_transform(y_train))
X_train.shape #Output - (50,128,128,1)
y_train.shape #Output - (50,4)
#Model Creation
num_classes = 4 #Number of Classes
model = Sequential()
model.add(Conv2D(256,(5,5),input_shape=(128,128,1)))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
模型摘要：
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 124, 124, 256) 6656
_________________________________________________________________
activation (Activation) (None, 124, 124, 256) 0
_________________________________________________________________
dropout (Dropout) (None, 124, 124, 256) 0
_________________________________________________________________
dense (Dense) (None, 124, 124, 512) 131584
_________________________________________________________________
activation_1 (Activation) (None, 124, 124, 512) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 124, 124, 512) 0
_________________________________________________________________
dense_1 (Dense) (None, 124, 124, 256) 131328
_________________________________________________________________
activation_2 (Activation) (None, 124, 124, 256) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 124, 124, 256) 0
_________________________________________________________________
dense_2 (Dense) (None, 124, 124, 4) 1028
_________________________________________________________________
activation_3 (Activation) (None, 124, 124, 4) 0
=================================================================
Total params: 270,596
Trainable params: 270,596
Non-trainable params: 0
#Fit Model
model.fit(X_train,y_train,batch_size=10,epochs=200)
错误：
Epoch 1/200
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-63-215c349ba276> in <module>
----> 1 model.fit(X_train,y_train,batch_size=10,epochs=200)
~/miniforge3/envs/DL/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)
1098 _r=1):
1099 callbacks.on_train_batch_begin(step)
-> 1100 tmp_logs = self.train_function(iterator)
1101 if data_handler.should_sync:
1102 context.async_wait()
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
826 tracing_count = self.experimental_get_tracing_count()
827 with trace.Trace(self._name) as tm:
--> 828 result = self._call(*args, **kwds)
829 compiler = "xla" if self._experimental_compile else "nonXla"
830 new_tracing_count = self.experimental_get_tracing_count()
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
869 # This is the first call of __call__, so we have to initialize.
870 initializers = []
--> 871 self._initialize(args, kwds, add_initializers_to=initializers)
872 finally:
873 # At this point we know that the initialization is complete (or less
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
723 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
724 self._concrete_stateful_fn = (
--> 725 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
726 *args, **kwds))
727
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2967 args, kwargs = None, None
2968 with self._lock:
-> 2969 graph_function, _ = self._maybe_define_function(args, kwargs)
2970 return graph_function
2971
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
3359
3360 self._function_cache.missed.add(call_context_key)
-> 3361 graph_function = self._create_graph_function(args, kwargs)
3362 self._function_cache.primary[cache_key] = graph_function
3363
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3194 arg_names = base_arg_names + missing_arg_names
3195 graph_function = ConcreteFunction(
-> 3196 func_graph_module.func_graph_from_py_func(
3197 self._name,
3198 self._python_function,
~/miniforge3/envs/DL/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)
988 _, original_func = tf_decorator.unwrap(python_func)
989
--> 990 func_outputs = python_func(*func_args, **func_kwargs)
991
992 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
632 xla_context.Exit()
633 else:
--> 634 out = weak_wrapped_fn().__wrapped__(*args, **kwds)
635 return out
636
~/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
975 except Exception as e: # pylint:disable=broad-except
976 if hasattr(e, "ag_error_metadata"):
--> 977 raise e.ag_error_metadata.to_exception(e)
978 else:
979 raise
ValueError: in user code:
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:805 train_function *
return step_function(self, iterator)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:788 run_step **
outputs = model.train_step(data)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:755 train_step
loss = self.compiled_loss(
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:157 __call__
losses = call_fn(y_true, y_pred)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:261 call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/losses.py:1562 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/keras/backend.py:4869 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/Users/akellaniranjan/miniforge3/envs/DL/lib/python3.8/site-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (10, 4) and (10, 128, 128, 4) are incompatible
答案 0 :(得分：2)
在最后一个块之前添加一个扁平层：
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Flatten()) # <-- this is new
model.add(Dense(num_classes))
model.add(Activation('softmax'))
更多信息在这里：https://www.tensorflow.org/api_docs/python/tf/keras/layers/Flatten 或在这里：https://keras.io/api/layers/reshaping_layers/flatten/
答案 1 :(得分：0)
我认为对于您的情况，您应该在模型的最后一层之前添加一个 Flatten 层。
>>> model.add(Flatten())
在您的情况下，输出是多维向量，但是您只需要与类对应的一维输出。
更多信息：https://keras.io/api/layers/reshaping_layers/flatten/
PS：您还应该考虑使用 Maxpooling 层，它们将帮助您的模型训练更快，因为它们减少了输入的维度。