【Keras】自作モデルを使ったGrad-camを実装したいがエラーが出ます

Question

前提・実現したいこと

https://teratail.com/questions/102908の質問内容とほぼ被ってますが質問させていただきます。
２種類の画像分類を行うようなモデルを作成しました。その際、Resnet-50を使った転移学習によってモデルを構築しました。このモデルの中間層で行われている特徴量計算を可視化したいと考え、Grad-camを実装することとしました。

発生している問題・エラーメッセージ

Traceback (most recent call last):
  File "mygrad_cam.py", line 131, in <module>
    cam, heatmap = grad_cam(model, preprocessed_input, predicted_class, "activation_48")
  File "mygrad_cam.py", line 92, in grad_cam
    output_shape = target_category_loss_output_shape))
  File "C:\Users\Public.MYCOMPUTER\Anaconda3\envs\tensor_copy\lib\site-packages\tensorflow\python\training\checkpointable\base.py", line 474, in _method_wrapper
    method(self, *args, **kwargs)
  File "C:\Users\Public.MYCOMPUTER\Anaconda3\envs\tensor_copy\lib\site-packages\tensorflow\python\keras\engine\sequential.py", line 140, in add
    'Found: ' + str(layer))
TypeError: The added layer must be an instance of class Layer. Found: <keras.layers.core.Lambda object at 0x000002445C0646A0>

該当のソースコード

from keras.preprocessing import image
from keras.layers.core import Lambda
from tensorflow.python.keras.models import Sequential ,load_model
from tensorflow.python.framework import ops
import keras.backend as K
import tensorflow as tf
import numpy as np
import keras
import sys
import cv2

def target_category_loss(x, category_index, nb_classes):
    return tf.multiply(x, K.one_hot([category_index], nb_classes))

def target_category_loss_output_shape(input_shape):
    return input_shape

def normalize(x):
    # utility function to normalize a tensor by its L2 norm
    return x / (K.sqrt(K.mean(K.square(x))) + 1e-5)

def load_image(path):
    img_path = path
    img = image.load_img(img_path, target_size=(224,224))
    x = image.img_to_array(img)
    x = np.expand_dims(x, axis=0)
    return x

def register_gradient():
    if "GuidedBackProp" not in ops._gradient_registry._registry:
        @ops.RegisterGradient("GuidedBackProp")
        def _GuidedBackProp(op, grad):
            dtype = op.inputs[0].dtype
            return grad * tf.cast(grad > 0., dtype) * \
                tf.cast(op.inputs[0] > 0., dtype)

def compile_saliency_function(model, activation_layer='conv2d_3'):
    input_img = model.input
    layer_dict = dict([(layer.name, layer) for layer in model.layers[1:]])
    layer_output = layer_dict[activation_layer].output
    max_output = K.max(layer_output, axis=3)
    saliency = K.gradients(K.sum(max_output), input_img)[0]
    return K.function([input_img, K.learning_phase()], [saliency])

def modify_backprop(model, name):
    g = tf.get_default_graph()
    with g.gradient_override_map({'Relu': name}):

        # get layers that have an activation
        layer_dict = [layer for layer in model.layers[1:]
                      if hasattr(layer, 'activation')]

        # replace relu activation
        for layer in layer_dict:
            if layer.activation == keras.activations.relu:
                layer.activation = tf.nn.relu

        # re-instanciate a new model
        new_model = model
    return new_model

def deprocess_image(x):
    '''
    Same normalization as in:
    https://github.com/fchollet/keras/blob/master/examples/conv_filter_visualization.py
    '''
    if np.ndim(x) > 3:
        x = np.squeeze(x)
    # normalize tensor: center on 0., ensure std is 0.1
    x -= x.mean()
    x /= (x.std() + 1e-5)
    x *= 0.1

    # clip to [0, 1]
    x += 0.5
    x = np.clip(x, 0, 1)

    # convert to RGB array
    x *= 255
    if K.image_dim_ordering() == 'th':
        x = x.transpose((1, 2, 0))
    x = np.clip(x, 0, 255).astype('uint8')
    return x

def grad_cam(input_model, image, category_index, layer_name):
    model = Sequential()
    model.add(input_model)

    nb_classes = 2
    target_layer = lambda x: target_category_loss(x, category_index, nb_classes)
    model.add(Lambda(target_layer,
                     output_shape = target_category_loss_output_shape))

    loss = K.sum(model.layers[-1].output)
    conv_output =  [l for l in model.layers[0].layers if l.name == layer_name][0].output
    grads = normalize(K.gradients(loss, conv_output)[0])
    gradient_function = K.function([model.layers[0].input], [conv_output, grads])

    output, grads_val = gradient_function([image])
    output, grads_val = output[0, :], grads_val[0, :, :, :]

    weights = np.mean(grads_val, axis = (0, 1))
    cam = np.ones(output.shape[0 : 2], dtype = np.float32)

    for i, w in enumerate(weights):
        cam += w * output[:, :, i]

    cam = cv2.resize(cam, (64, 64))
    cam = np.maximum(cam, 0)
    heatmap = cam / np.max(cam)

    #Return to BGR [0..255] from the preprocessed image
    image = image[0, :]
    image -= np.min(image)
    image = np.minimum(image, 255)

    cam = cv2.applyColorMap(np.uint8(255*heatmap), cv2.COLORMAP_JET)
    cam = np.float32(cam) + np.float32(image)
    cam = 255 * cam / np.max(cam)
    return np.uint8(cam), heatmap

# 判定画像の読み込み
preprocessed_input = load_image('F6.jpg')

model = load_model('allnet.h5')
model.summary()

predictions = model.predict(preprocessed_input)

predicted_class = np.argmax(predictions)
cam, heatmap = grad_cam(model, preprocessed_input, predicted_class, "activation_48")
cv2.imwrite("gradcam.jpg", cam)

register_gradient()
guided_model = modify_backprop(model, 'GuidedBackProp')
saliency_fn = compile_saliency_function(guided_model)
saliency = saliency_fn([preprocessed_input, 0])
gradcam = saliency[0] * heatmap[..., np.newaxis]
cv2.imwrite("guided_gradcam.jpg", deprocess_image(gradcam))

試したこと

複数のサイトを参考にしながら色々と試してはみたのですが、どれを使ってもうまく実装することができませんでした。
ご教授のほどよろしくお願いいたします。

補足情報（FW/ツールのバージョンなど）

実行環境
Window10
AnacondaNavigator
Keras2.2.4
Tensorflow1.12.0

Answer 1

下記にモデル構造貼ってあります
※字数制限で途中略してあります

---

Layer (type) Output Shape Param # Connected to

input_1 (InputLayer) (None, 224, 224, 3) 0

---

conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 input_1[0][0]

---

conv1 (Conv2D) (None, 112, 112, 64) 9472 conv1_pad[0][0]

---

bn_conv1 (BatchNormalization) (None, 112, 112, 64) 256 conv1[0][0]

---

activation (Activation) (None, 112, 112, 64) 0 bn_conv1[0][0]

---

pool1_pad (ZeroPadding2D) (None, 114, 114, 64) 0 activation[0][0]

---

max_pooling2d (MaxPooling2D) (None, 56, 56, 64) 0 pool1_pad[0][0]

---

res2a_branch2a (Conv2D) (None, 56, 56, 64) 4160 max_pooling2d[0][0]

---

bn2a_branch2a (BatchNormalizati (None, 56, 56, 64) 256 res2a_branch2a[0][0]

---

activation_1 (Activation) (None, 56, 56, 64) 0 bn2a_branch2a[0][0]

---

res2a_branch2b (Conv2D) (None, 56, 56, 64) 36928 activation_1[0][0]

activation_46 (Activation)      (None, 7, 7, 512)    0           bn5c_branch2a[0][0]
__________________________________________________________________________________________________
res5c_branch2b (Conv2D)         (None, 7, 7, 512)    2359808     activation_46[0][0]
__________________________________________________________________________________________________
bn5c_branch2b (BatchNormalizati (None, 7, 7, 512)    2048        res5c_branch2b[0][0]
__________________________________________________________________________________________________
activation_47 (Activation)      (None, 7, 7, 512)    0           bn5c_branch2b[0][0]
__________________________________________________________________________________________________
res5c_branch2c (Conv2D)         (None, 7, 7, 2048)   1050624     activation_47[0][0]
__________________________________________________________________________________________________
bn5c_branch2c (BatchNormalizati (None, 7, 7, 2048)   8192        res5c_branch2c[0][0]
__________________________________________________________________________________________________
add_15 (Add)                    (None, 7, 7, 2048)   0           bn5c_branch2c[0][0]
                                                                 activation_45[0][0]
__________________________________________________________________________________________________
activation_48 (Activation)      (None, 7, 7, 2048)   0           add_15[0][0]
__________________________________________________________________________________________________
sequential (Sequential)         (None, 1)            25690625    activation_48[0][0]
==================================================================================================
Total params: 49,278,337
Trainable params: 49,225,217
Non-trainable params: 53,120
__________________________________________________________________________________________________