我在尝试实现 AlexNet 来解决 GTSRB 时收到此错误消息：从 1 中减去 'max_pooling2d_8/MaxPool' 的 3 导致的负维度大小 错误位于标有 #3 的块中
法典：
def buildAlex(width, height, depth, classes, reg=0.0002):
# initialize the model along with the input shape to be
# "channels last" and the channels dimension itself
model = keras.Sequential()
inputShape = (height, width, depth)
chanDim = -1
# Block #1: first CONV => RELU => POOL layer set
model.add(Conv2D(96, (11, 11), strides=(4, 4),
input_shape=inputShape, padding="same",
kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #1
model.add(Dropout(0.25))
# Block #2: second CONV => RELU => POOL layer set
model.add(Conv2D(256, (5, 5), padding="same",
kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #2
model.add(Dropout(0.25))
# Block #3: CONV => RELU => CONV => RELU => CONV => RELU
model.add(Conv2D(384, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(384, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(Conv2D(256, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization(axis=chanDim))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #3
model.add(Dropout(0.25))
# Block #4: first set of FC => RELU layers
model.add(Flatten())
model.add(Dense(4096, kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization())
model.add(Dropout(0.5))
# Block #5: second set of FC => RELU layers
model.add(Dense(4096, kernel_regularizer=l2(reg)))
model.add(Activation("relu"))
model.add(BatchNormalization())
model.add(Dropout(0.5))
# softmax classifier
model.add(Dense(classes, kernel_regularizer=l2(reg)))
model.add(Activation("softmax"))
# return the constructed network architecture
return model
modelAlex = buildAlex(28, 28, 1, 43)
追踪：
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1550 try:
-> 1551 c_op = c_api.TF_FinishOperation(op_desc)
1552 except errors.InvalidArgumentError as e:
InvalidArgumentError: Negative dimension size caused by subtracting 3 from 1 for 'max_pooling2d_8/MaxPool' (op: 'MaxPool') with input shapes: [?,1,1,256].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-36-7205823f509c> in <module>
----> 1 modelAlex = buildAlex(28, 28, 1, 43)
<ipython-input-35-e4a6adb73a0a> in buildAlex(width, height, depth, classes, reg)
36 model.add(Activation("relu"))
37 model.add(BatchNormalization(axis=chanDim))
---> 38 model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #3
39 model.add(Dropout(0.25))
40
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
456 self._self_setattr_tracking = False # pylint: disable=protected-access
457 try:
--> 458 result = method(self, *args, **kwargs)
459 finally:
460 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/keras/engine/sequential.py in add(self, layer)
191 # If the model is being built continuously on top of an input layer:
192 # refresh its output.
--> 193 output_tensor = layer(self.outputs[0])
194 if len(nest.flatten(output_tensor)) != 1:
195 raise TypeError('All layers in a Sequential model '
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
660 not base_layer_utils.is_in_eager_or_tf_function()):
661 with auto_control_deps.AutomaticControlDependencies() as acd:
--> 662 outputs = call_fn(inputs, *args, **kwargs)
663 # Wrap Tensors in `outputs` in `tf.identity` to avoid
664 # circular dependencies.
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/keras/layers/pooling.py in call(self, inputs)
246 strides=strides,
247 padding=self.padding.upper(),
--> 248 data_format=conv_utils.convert_data_format(self.data_format, 4))
249 return outputs
250
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py in max_pool(value, ksize, strides, padding, data_format, name, input)
3750 padding=padding,
3751 data_format=data_format,
-> 3752 name=name)
3753
3754
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/ops/gen_nn_ops.py in max_pool(input, ksize, strides, padding, data_format, name)
5670 _, _, _op = _op_def_lib._apply_op_helper(
5671 "MaxPool", input=input, ksize=ksize, strides=strides, padding=padding,
-> 5672 data_format=data_format, name=name)
5673 _result = _op.outputs[:]
5674 _inputs_flat = _op.inputs
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
786 op = g.create_op(op_type_name, inputs, dtypes=None, name=scope,
787 input_types=input_types, attrs=attr_protos,
--> 788 op_def=op_def)
789 return output_structure, op_def.is_stateful, op
790
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py in create_op(***failed resolving arguments***)
463 return super(FuncGraph, self).create_op(
464 op_type, inputs, dtypes, input_types, name, attrs, op_def,
--> 465 compute_device=compute_device)
466
467 def capture(self, tensor, name=None):
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
505 'in a future version' if date is None else ('after %s' % date),
506 instructions)
--> 507 return func(*args, **kwargs)
508
509 doc = _add_deprecated_arg_notice_to_docstring(
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in create_op(***failed resolving arguments***)
3294 input_types=input_types,
3295 original_op=self._default_original_op,
-> 3296 op_def=op_def)
3297 self._create_op_helper(ret, compute_device=compute_device)
3298 return ret
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in __init__(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
1712 op_def, inputs, node_def.attr)
1713 self._c_op = _create_c_op(self._graph, node_def, grouped_inputs,
-> 1714 control_input_ops)
1715
1716 # Initialize self._outputs.
~/Documents/Environments/my_env/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
1552 except errors.InvalidArgumentError as e:
1553 # Convert to ValueError for backwards compatibility.
-> 1554 raise ValueError(str(e))
1555
1556 return c_op
ValueError: Negative dimension size caused by subtracting 3 from 1 for 'max_pooling2d_8/MaxPool' (op: 'MaxPool') with input shapes: [?,1,1,256].
嗯，有道理不是吗？
原始的AlexNet在(224,224,3)尺寸的图像上运行。在这里，您正在通过(28,28,1)这是很小的。错误的意思是，在您的模型中不远处，它最终会得到一个input size < 0.更具体地说，这是输出如何减少(height, width(维度。
(28, 28)
|
V
model.add(Conv2D(96, (11, 11), strides=(4, 4), ...)
|
V
(7, 7)
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #1
|
V
(3, 3)
model.add(Conv2D(256, (5, 5), padding="same",
kernel_regularizer=l2(reg)))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #2
|
V
(1, 1)
model.ad(Dropout(0.25))
# Block #3: CONV => RELU => CONV => RELU => CONV => RELU
# Block #3: CONV => RELU => CONV => RELU => CONV => RELU
model.add(Conv2D(384, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
model.add(Conv2D(384, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
model.add(Conv2D(256, (3, 3), padding="same",
kernel_regularizer=l2(reg)))
(Error) --->model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2))) #3
model.add(Dropout(0.25))
在这里，最后一个MaxPooling2D层不能在 (1,1( 大小的图像上以步幅 2 操作。因此错误。还要记住，默认情况下MaxPooling2Dpadding='valid'。
补救 措施：
- 增加您的输入大小，
- 摆脱一些
Maxpooling2D层。