我必须将密集网络中的 fc 层转换为 conv 层。下面是密集网络的架构。
# Dense Block
def denseblock(input, num_filter = 12, dropout_rate = 0.0):
global compression
temp = input
for _ in range(l):
BatchNorm = layers.BatchNormalization()(temp)
relu = layers.Activation('relu')(BatchNorm)
Conv2D_3_3 = layers.Conv2D(int(num_filter*compression), (3,3), use_bias=False ,padding='same')(relu)
if dropout_rate>0:
Conv2D_3_3 = layers.Dropout(dropout_rate)(Conv2D_3_3)
concat = layers.Concatenate(axis=-1)([temp,Conv2D_3_3])
temp = concat
return temp
## transition Block
def transition(input, num_filter = 12, dropout_rate = 0.0):
global compression
BatchNorm = layers.BatchNormalization()(input)
relu = layers.Activation('relu')(BatchNorm)
Conv2D_BottleNeck = layers.Conv2D(int(num_filter*compression), (1,1), use_bias=False ,padding='same')(relu)
if dropout_rate>0:
Conv2D_BottleNeck = layers.Dropout(dropout_rate)(Conv2D_BottleNeck)
avg = layers.AveragePooling2D(pool_size=(2,2))(Conv2D_BottleNeck)
return avg
#output layer
def output_layer(input):
global compression
BatchNorm = layers.BatchNormalization()(input)
relu = layers.Activation('relu')(BatchNorm)
AvgPooling = layers.AveragePooling2D(pool_size=(2,2))(relu)
flat = layers.Flatten()(AvgPooling)
output = layers.Dense(num_classes, activation='softmax')(flat)
return output
input = layers.Input(shape=(img_height, img_width, channel,))
First_Conv2D = layers.Conv2D(num_filter, (3,3), use_bias=False ,padding='same')(input)
First_Block = denseblock(First_Conv2D, num_filter, dropout_rate)
First_Transition = transition(First_Block, num_filter, dropout_rate)
Second_Block = denseblock(First_Transition, num_filter, dropout_rate)
Second_Transition = transition(Second_Block, num_filter, dropout_rate)
Third_Block = denseblock(Second_Transition, num_filter, dropout_rate)
Third_Transition = transition(Third_Block, num_filter, dropout_rate)
Last_Block = denseblock(Third_Transition, num_filter, dropout_rate)
output = output_layer(Last_Block)
我已经通过这些行更改了输出层的最后两行
fc2conv1 = layers.Conv2D(864, 2, 1, padding='valid')(AvgPooling)
output = layers.Conv2D(10, 1, 1, padding='valid')(fc2conv1)
但是在训练模型时出现错误。
ValueError: A target array with shape (5000, 10) was passed for an output of shape (None, 1, 1, 10) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output.
完整的错误跟踪
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-40-245431de828d> in <module>
5 verbose = 1,
6 validation_data=(x_val, y_val),
----> 7 callbacks = [lr_scheduler, csv_logger, model_chkpt, callbacks]
8 )
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\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_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
222 validation_data=validation_data,
223 validation_steps=validation_steps,
--> 224 distribution_strategy=strategy)
225
226 total_samples = _get_total_number_of_samples(training_data_adapter)
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _process_training_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights, steps_per_epoch, validation_split, validation_data, validation_steps, shuffle, distribution_strategy, max_queue_size, workers, use_multiprocessing)
562 class_weights=class_weights,
563 steps=validation_steps,
--> 564 distribution_strategy=distribution_strategy)
565 elif validation_steps:
566 raise ValueError('`validation_steps` should not be specified if '
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _process_inputs(model, x, y, batch_size, epochs, sample_weights, class_weights, shuffle, steps, distribution_strategy, max_queue_size, workers, use_multiprocessing)
592 batch_size=batch_size,
593 check_steps=False,
--> 594 steps=steps)
595 adapter = adapter_cls(
596 x,
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
2536 # Additional checks to avoid users mistakenly using improper loss fns.
2537 training_utils.check_loss_and_target_compatibility(
-> 2538 y, self._feed_loss_fns, feed_output_shapes)
2539
2540 # If sample weight mode has not been set and weights are None for all the
~\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py in check_loss_and_target_compatibility(targets, loss_fns, output_shapes)
741 raise ValueError('A target array with shape ' + str(y.shape) +
742 ' was passed for an output of shape ' + str(shape) +
--> 743 ' while using as loss `' + loss_name + '`. '
744 'This loss expects targets to have the same shape '
745 'as the output.')
ValueError: A target array with shape (5000, 10) was passed for an output of shape (None, 1, 1, 10) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output.