检查模型输入时出错：预期没有数据，但得到：

Question

我想把SSD512体系结构的一部分提取到一个单独的模型中。返回所需模型的函数如下：

def ssd_512_end(image_size,
        n_classes,
        mode='training',
        l2_regularization=0.0005,
        min_scale=None,
        max_scale=None,
        scales=None,
        aspect_ratios_global=None,
        aspect_ratios_per_layer=[[1.0, 2.0, 0.5],
                                 [1.0, 2.0, 0.5, 3.0, 1.0/3.0],
                                 [1.0, 2.0, 0.5, 3.0, 1.0/3.0],
                                 [1.0, 2.0, 0.5, 3.0, 1.0/3.0],
                                 [1.0, 2.0, 0.5, 3.0, 1.0/3.0],
                                 [1.0, 2.0, 0.5],
                                 [1.0, 2.0, 0.5]],
        two_boxes_for_ar1=True,
        steps=[8, 16, 32, 64, 128, 256, 512],
        offsets=None,
        clip_boxes=False,
        variances=[0.1, 0.1, 0.2, 0.2],
        coords='centroids',
        normalize_coords=True,
        subtract_mean=[123, 117, 104],
        divide_by_stddev=None,
        swap_channels=[2, 1, 0],
        confidence_thresh=0.01,
        iou_threshold=0.45,
        top_k=200,
        nms_max_output_size=400,
        return_predictor_sizes=False):

n_predictor_layers = 7 # The number of predictor conv layers in the network is 7 for the original SSD512
n_classes += 1 # Account for the background class.
l2_reg = l2_regularization # Make the internal name shorter.
img_height, img_width, img_channels = image_size[0], image_size[1], image_size[2]

############################################################################
# Get a few exceptions out of the way.
############################################################################

if aspect_ratios_global is None and aspect_ratios_per_layer is None:
    raise ValueError("`aspect_ratios_global` and `aspect_ratios_per_layer` cannot both be None. At least one needs to be specified.")
if aspect_ratios_per_layer:
    if len(aspect_ratios_per_layer) != n_predictor_layers:
        raise ValueError("It must be either aspect_ratios_per_layer is None or len(aspect_ratios_per_layer) == {}, but len(aspect_ratios_per_layer) == {}.".format(n_predictor_layers, len(aspect_ratios_per_layer)))

if (min_scale is None or max_scale is None) and scales is None:
    raise ValueError("Either `min_scale` and `max_scale` or `scales` need to be specified.")
if scales:
    if len(scales) != n_predictor_layers+1:
        raise ValueError("It must be either scales is None or len(scales) == {}, but len(scales) == {}.".format(n_predictor_layers+1, len(scales)))
else: # If no explicit list of scaling factors was passed, compute the list of scaling factors from `min_scale` and `max_scale`
    scales = np.linspace(min_scale, max_scale, n_predictor_layers+1)

if len(variances) != 4:
    raise ValueError("4 variance values must be pased, but {} values were received.".format(len(variances)))
variances = np.array(variances)
if np.any(variances <= 0):
    raise ValueError("All variances must be >0, but the variances given are {}".format(variances))

if (not (steps is None)) and (len(steps) != n_predictor_layers):
    raise ValueError("You must provide at least one step value per predictor layer.")

if (not (offsets is None)) and (len(offsets) != n_predictor_layers):
    raise ValueError("You must provide at least one offset value per predictor layer.")

############################################################################
# Compute the anchor box parameters.
############################################################################

# Set the aspect ratios for each predictor layer. These are only needed for the anchor box layers.
if aspect_ratios_per_layer:
    aspect_ratios = aspect_ratios_per_layer
else:
    aspect_ratios = [aspect_ratios_global] * n_predictor_layers

# Compute the number of boxes to be predicted per cell for each predictor layer.
# We need this so that we know how many channels the predictor layers need to have.
if aspect_ratios_per_layer:
    n_boxes = []
    for ar in aspect_ratios_per_layer:
        if (1 in ar) & two_boxes_for_ar1:
            n_boxes.append(len(ar) + 1) # +1 for the second box for aspect ratio 1
        else:
            n_boxes.append(len(ar))
else: # If only a global aspect ratio list was passed, then the number of boxes is the same for each predictor layer
    if (1 in aspect_ratios_global) & two_boxes_for_ar1:
        n_boxes = len(aspect_ratios_global) + 1
    else:
        n_boxes = len(aspect_ratios_global)
    n_boxes = [n_boxes] * n_predictor_layers

if steps is None:
    steps = [None] * n_predictor_layers
if offsets is None:
    offsets = [None] * n_predictor_layers

############################################################################
# Define functions for the Lambda layers below.
############################################################################

def identity_layer(tensor):
    return tensor

def input_mean_normalization(tensor):
    return tensor - np.array(subtract_mean)

def input_stddev_normalization(tensor):
    return tensor / np.array(divide_by_stddev)

def input_channel_swap(tensor):
    if len(swap_channels) == 3:
        return K.stack([tensor[...,swap_channels[0]], tensor[...,swap_channels[1]], tensor[...,swap_channels[2]]], axis=-1)
    elif len(swap_channels) == 4:
        return K.stack([tensor[...,swap_channels[0]], tensor[...,swap_channels[1]], tensor[...,swap_channels[2]], tensor[...,swap_channels[3]]], axis=-1)

############################################################################
# Build the network.
############################################################################

x = Input(shape=(img_height, img_width, img_channels))

# The following identity layer is only needed so that the subsequent lambda layers can be optional.
x1 = Lambda(identity_layer, output_shape=(img_height, img_width, img_channels), name='identity_layer')(x)
if not (subtract_mean is None):
    x1 = Lambda(input_mean_normalization, output_shape=(img_height, img_width, img_channels), name='input_mean_normalization')(x1)
if not (divide_by_stddev is None):
    x1 = Lambda(input_stddev_normalization, output_shape=(img_height, img_width, img_channels), name='input_stddev_normalization')(x1)
if swap_channels:
    x1 = Lambda(input_channel_swap, output_shape=(img_height, img_width, img_channels), name='input_channel_swap')(x1)

conv1_1 = Conv2D(64, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv1_1')(x1)
conv1_2 = Conv2D(64, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv1_2')(conv1_1)
pool1 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool1')(conv1_2)

conv2_1 = Conv2D(128, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv2_1')(pool1)
conv2_2 = Conv2D(128, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv2_2')(conv2_1)
pool2 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool2')(conv2_2)

conv3_1 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_1')(pool2)
conv3_2 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_2')(conv3_1)
conv3_3 = Conv2D(256, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv3_3')(conv3_2)
pool3 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool3')(conv3_3)

conv4_1 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_1')(pool3)
conv4_2 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_2')(conv4_1)
conv4_3 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3')(conv4_2)
pool4 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same', name='pool4')(conv4_3)

conv5_1 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_1')(pool4)
conv5_2 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_2')(conv5_1)
conv5_3 = Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv5_3')(conv5_2)
pool5 = MaxPooling2D(pool_size=(3, 3), strides=(1, 1), padding='same', name='pool5')(conv5_3)

fc6 = Conv2D(1024, (3, 3), dilation_rate=(6, 6), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc6')(pool5)

fc7 = Conv2D(1024, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7')(fc6)

conv6_1 = Conv2D(256, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_1')(fc7)
conv6_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv6_padding')(conv6_1)
conv6_2 = Conv2D(512, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2')(conv6_1)

conv7_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_1')(conv6_2)
conv7_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv7_padding')(conv7_1)
conv7_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2')(conv7_1)

conv8_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_1')(conv7_2)
conv8_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv8_padding')(conv8_1)
conv8_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2')(conv8_1)

conv9_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_1')(conv8_2)
conv9_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv9_padding')(conv9_1)
conv9_2 = Conv2D(256, (3, 3), strides=(2, 2), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2')(conv9_1)

conv10_1 = Conv2D(128, (1, 1), activation='relu', padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_1')(conv9_2)
conv10_1 = ZeroPadding2D(padding=((1, 1), (1, 1)), name='conv10_padding')(conv10_1)
conv10_2 = Conv2D(256, (4, 4), strides=(1, 1), activation='relu', padding='valid', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2')(conv10_1)

conv4_3_input = Input(tensor = conv4_3, name = 'conv4_3_input')
fc7_input = Input(tensor = fc7, name = 'fc7_input')
conv6_2_input = Input(tensor = conv6_2, name = 'conv6_2_input')
conv7_2_input = Input(tensor = conv7_2, name = 'conv7_2_input')
conv8_2_input = Input(tensor = conv8_2, name = 'conv8_2_input')
conv9_2_input = Input(tensor = conv9_2, name = 'conv9_2_input')
conv10_2_input = Input(tensor = conv10_2, name = 'conv10_2_input')

# Feed conv4_3 into the L2 normalization layer
conv4_3_norm = L2Normalization(gamma_init=20, name='conv4_3_norm')(conv4_3)

### Build the convolutional predictor layers on top of the base network

# We precidt `n_classes` confidence values for each box, hence the confidence predictors have depth `n_boxes * n_classes`
# Output shape of the confidence layers: `(batch, height, width, n_boxes * n_classes)`
conv4_3_norm_mbox_conf = Conv2D(n_boxes[0] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3_norm_mbox_conf')(conv4_3_norm)
fc7_mbox_conf = Conv2D(n_boxes[1] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7_mbox_conf')(fc7)
conv6_2_mbox_conf = Conv2D(n_boxes[2] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2_mbox_conf')(conv6_2)
conv7_2_mbox_conf = Conv2D(n_boxes[3] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2_mbox_conf')(conv7_2)
conv8_2_mbox_conf = Conv2D(n_boxes[4] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2_mbox_conf')(conv8_2)
conv9_2_mbox_conf = Conv2D(n_boxes[5] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2_mbox_conf')(conv9_2)
conv10_2_mbox_conf = Conv2D(n_boxes[6] * n_classes, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2_mbox_conf')(conv10_2)
# We predict 4 box coordinates for each box, hence the localization predictors have depth `n_boxes * 4`
# Output shape of the localization layers: `(batch, height, width, n_boxes * 4)`
conv4_3_norm_mbox_loc = Conv2D(n_boxes[0] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv4_3_norm_mbox_loc')(conv4_3_norm)
fc7_mbox_loc = Conv2D(n_boxes[1] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='fc7_mbox_loc')(fc7)
conv6_2_mbox_loc = Conv2D(n_boxes[2] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv6_2_mbox_loc')(conv6_2)
conv7_2_mbox_loc = Conv2D(n_boxes[3] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv7_2_mbox_loc')(conv7_2)
conv8_2_mbox_loc = Conv2D(n_boxes[4] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv8_2_mbox_loc')(conv8_2)
conv9_2_mbox_loc = Conv2D(n_boxes[5] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv9_2_mbox_loc')(conv9_2)
conv10_2_mbox_loc = Conv2D(n_boxes[6] * 4, (3, 3), padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(l2_reg), name='conv10_2_mbox_loc')(conv10_2)

### Generate the anchor boxes (called "priors" in the original Caffe/C++ implementation, so I'll keep their layer names)

# Output shape of anchors: `(batch, height, width, n_boxes, 8)`
conv4_3_norm_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[0], next_scale=scales[1], aspect_ratios=aspect_ratios[0],
                                         two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[0], this_offsets=offsets[0], clip_boxes=clip_boxes,
                                         variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv4_3_norm_mbox_priorbox')(conv4_3_norm_mbox_loc)
fc7_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[1], next_scale=scales[2], aspect_ratios=aspect_ratios[1],
                                two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[1], this_offsets=offsets[1], clip_boxes=clip_boxes,
                                variances=variances, coords=coords, normalize_coords=normalize_coords, name='fc7_mbox_priorbox')(fc7_mbox_loc)
conv6_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[2], next_scale=scales[3], aspect_ratios=aspect_ratios[2],
                                    two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[2], this_offsets=offsets[2], clip_boxes=clip_boxes,
                                    variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv6_2_mbox_priorbox')(conv6_2_mbox_loc)
conv7_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[3], next_scale=scales[4], aspect_ratios=aspect_ratios[3],
                                    two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[3], this_offsets=offsets[3], clip_boxes=clip_boxes,
                                    variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv7_2_mbox_priorbox')(conv7_2_mbox_loc)
conv8_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[4], next_scale=scales[5], aspect_ratios=aspect_ratios[4],
                                    two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[4], this_offsets=offsets[4], clip_boxes=clip_boxes,
                                    variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv8_2_mbox_priorbox')(conv8_2_mbox_loc)
conv9_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[5], next_scale=scales[6], aspect_ratios=aspect_ratios[5],
                                    two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[5], this_offsets=offsets[5], clip_boxes=clip_boxes,
                                    variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv9_2_mbox_priorbox')(conv9_2_mbox_loc)
conv10_2_mbox_priorbox = AnchorBoxes(img_height, img_width, this_scale=scales[6], next_scale=scales[7], aspect_ratios=aspect_ratios[6],
                                    two_boxes_for_ar1=two_boxes_for_ar1, this_steps=steps[6], this_offsets=offsets[6], clip_boxes=clip_boxes,
                                    variances=variances, coords=coords, normalize_coords=normalize_coords, name='conv10_2_mbox_priorbox')(conv10_2_mbox_loc)

### Reshape

# Reshape the class predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, n_classes)`
# We want the classes isolated in the last axis to perform softmax on them
conv4_3_norm_mbox_conf_reshape = Reshape((-1, n_classes), name='conv4_3_norm_mbox_conf_reshape')(conv4_3_norm_mbox_conf)
fc7_mbox_conf_reshape = Reshape((-1, n_classes), name='fc7_mbox_conf_reshape')(fc7_mbox_conf)
conv6_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv6_2_mbox_conf_reshape')(conv6_2_mbox_conf)
conv7_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv7_2_mbox_conf_reshape')(conv7_2_mbox_conf)
conv8_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv8_2_mbox_conf_reshape')(conv8_2_mbox_conf)
conv9_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv9_2_mbox_conf_reshape')(conv9_2_mbox_conf)
conv10_2_mbox_conf_reshape = Reshape((-1, n_classes), name='conv10_2_mbox_conf_reshape')(conv10_2_mbox_conf)
# Reshape the box predictions, yielding 3D tensors of shape `(batch, height * width * n_boxes, 4)`
# We want the four box coordinates isolated in the last axis to compute the smooth L1 loss
conv4_3_norm_mbox_loc_reshape = Reshape((-1, 4), name='conv4_3_norm_mbox_loc_reshape')(conv4_3_norm_mbox_loc)
fc7_mbox_loc_reshape = Reshape((-1, 4), name='fc7_mbox_loc_reshape')(fc7_mbox_loc)
conv6_2_mbox_loc_reshape = Reshape((-1, 4), name='conv6_2_mbox_loc_reshape')(conv6_2_mbox_loc)
conv7_2_mbox_loc_reshape = Reshape((-1, 4), name='conv7_2_mbox_loc_reshape')(conv7_2_mbox_loc)
conv8_2_mbox_loc_reshape = Reshape((-1, 4), name='conv8_2_mbox_loc_reshape')(conv8_2_mbox_loc)
conv9_2_mbox_loc_reshape = Reshape((-1, 4), name='conv9_2_mbox_loc_reshape')(conv9_2_mbox_loc)
conv10_2_mbox_loc_reshape = Reshape((-1, 4), name='conv10_2_mbox_loc_reshape')(conv10_2_mbox_loc)
# Reshape the anchor box tensors, yielding 3D tensors of shape `(batch, height * width * n_boxes, 8)`
conv4_3_norm_mbox_priorbox_reshape = Reshape((-1, 8), name='conv4_3_norm_mbox_priorbox_reshape')(conv4_3_norm_mbox_priorbox)
fc7_mbox_priorbox_reshape = Reshape((-1, 8), name='fc7_mbox_priorbox_reshape')(fc7_mbox_priorbox)
conv6_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv6_2_mbox_priorbox_reshape')(conv6_2_mbox_priorbox)
conv7_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv7_2_mbox_priorbox_reshape')(conv7_2_mbox_priorbox)
conv8_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv8_2_mbox_priorbox_reshape')(conv8_2_mbox_priorbox)
conv9_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv9_2_mbox_priorbox_reshape')(conv9_2_mbox_priorbox)
conv10_2_mbox_priorbox_reshape = Reshape((-1, 8), name='conv10_2_mbox_priorbox_reshape')(conv10_2_mbox_priorbox)

### Concatenate the predictions from the different layers

# Axis 0 (batch) and axis 2 (n_classes or 4, respectively) are identical for all layer predictions,
# so we want to concatenate along axis 1, the number of boxes per layer
# Output shape of `mbox_conf`: (batch, n_boxes_total, n_classes)
mbox_conf = Concatenate(axis=1, name='mbox_conf')([conv4_3_norm_mbox_conf_reshape,
                                                   fc7_mbox_conf_reshape,
                                                   conv6_2_mbox_conf_reshape,
                                                   conv7_2_mbox_conf_reshape,
                                                   conv8_2_mbox_conf_reshape,
                                                   conv9_2_mbox_conf_reshape,
                                                   conv10_2_mbox_conf_reshape])

# Output shape of `mbox_loc`: (batch, n_boxes_total, 4)
mbox_loc = Concatenate(axis=1, name='mbox_loc')([conv4_3_norm_mbox_loc_reshape,
                                                 fc7_mbox_loc_reshape,
                                                 conv6_2_mbox_loc_reshape,
                                                 conv7_2_mbox_loc_reshape,
                                                 conv8_2_mbox_loc_reshape,
                                                 conv9_2_mbox_loc_reshape,
                                                 conv10_2_mbox_loc_reshape])

# Output shape of `mbox_priorbox`: (batch, n_boxes_total, 8)
mbox_priorbox = Concatenate(axis=1, name='mbox_priorbox')([conv4_3_norm_mbox_priorbox_reshape,
                                                           fc7_mbox_priorbox_reshape,
                                                           conv6_2_mbox_priorbox_reshape,
                                                           conv7_2_mbox_priorbox_reshape,
                                                           conv8_2_mbox_priorbox_reshape,
                                                           conv9_2_mbox_priorbox_reshape,
                                                           conv10_2_mbox_priorbox_reshape])

# The box coordinate predictions will go into the loss function just the way they are,
# but for the class predictions, we'll apply a softmax activation layer first
mbox_conf_softmax = Activation('softmax', name='mbox_conf_softmax')(mbox_conf)

# Concatenate the class and box predictions and the anchors to one large predictions vector
# Output shape of `predictions`: (batch, n_boxes_total, n_classes + 4 + 8)
predictions = Concatenate(axis=2, name='predictions')([mbox_conf_softmax, mbox_loc, mbox_priorbox])

end_model = Model(inputs = [conv4_3_input,fc7_input,conv6_2_input,conv7_2_input,conv8_2_input,conv9_2_input,conv10_2_input], outputs = predictions)

return end_model

因此，当我尝试训练模型时，会出现以下错误：

^{pr2}$

因为'end_model'有7个输入，所以我将传递一个生成器，它将适当地生成7个输入数据。在

我哪里出错了？请帮忙！在

谢谢。在

Answer 1

您没有将x = Input(shape=(img_height, img_width, img_channels))作为Model的输入，这就是技术上您的模型没有输入的原因。其他输入是从x计算的，因为您指定了tensor参数，例如在Input(tensor = conv4_3, name = 'conv4_3_input')中，conv4_3是根据{}计算的。在

因此，创建模型时需要指定原始输入：

end_model = Model(x, predictions)