How to generate CNN heatmaps using built-in Keras in TF2.0 (tf.keras)

Question

I used to generate heatmaps for my Convolutional Neural Networks, based on the stand-alone Keras library on top of TensorFlow 1. That worked fine, however, after my switch to TF2.0 and built-in tf.keras implementation (with eager execution) I cannot use my old heatmap generation code any longer.

So I re-wrote parts of my code for TF2.0 and ended up with the following:

from tensorflow.keras.applications.vgg16 import preprocess_input
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.models import load_model

from tensorflow.keras import preprocessing
from tensorflow.keras import backend as K
from tensorflow.keras import models

import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np

image_size = 150
image_path = "/tmp/images/test-image.jpg"
model_path = "/tmp/models/prototype/basic_vgg16.h5"

# Load pre-trained Keras model and the image to classify
model = load_model(model_path)  # VGG16 CNN with custom classifier head
image = load_img(image_path, target_size=(image_size, image_size))
img_tensor = preprocessing.image.img_to_array(image)
img_tensor = np.expand_dims(img_tensor, axis=0)
img_tensor = preprocess_input(img_tensor)

input_layer = model.get_layer("model_input")
conv_layer = model.get_layer("block5_conv3")
heatmap_model = models.Model([model.inputs], [conv_layer.output, model.output])

# Get gradient of the winner class w.r.t. the output of the (last) conv. layer
with tf.GradientTape() as gtape:
    conv_output, predictions = heatmap_model(img_tensor)
    loss = predictions[:, np.argmax(predictions[0])]
    grads = gtape.gradient(loss, conv_output)
    pooled_grads = K.mean(grads, axis=(0, 1, 2))

# Get values of pooled grads and model conv. layer output as Numpy arrays
iterate = K.function([model.inputs], [pooled_grads, conv_layer.output[0]])
pooled_grads_value, conv_layer_output_value = iterate([img_tensor])

# Multiply each channel in the feature-map array by "how important it is"
for i in range(pooled_grads_value.shape[0]):
    conv_layer_output_value[:, :, i] *= pooled_grads_value[i]

# Channel-wise mean of resulting feature-map is the heatmap of class activation
heatmap = np.mean(conv_layer_output_value, axis=-1)
heatmap = np.maximum(heatmap, 0)
max_heat = np.max(heatmap)
if max_heat == 0:
    max_heat = 1e-10
heatmap /= max_heat

# Render heatmap via pyplot
plt.matshow(heatmap)
plt.show()

But now the following line:

iterate = K.function([model.inputs], [pooled_grads, conv_layer.output[0]])

leads to this error message:

AttributeError: Tensor.op is meaningless when eager execution is enabled.

I always used Keras and did not work with TF directly, so I am bit lost here.
Any ideas what could be the problem here?

---

PS: If you want to c&p this code, you can create the VGG16-based model like so:

# Create Keras model from pre-trained VGG16 and custom classifier
input_layer = layers.Input(shape=(image_size, image_size, 3), name="model_input")
vgg16_model = VGG16(weights="imagenet", include_top=False, input_tensor=input_layer)
model_head = vgg16_model.output
model_head = layers.Flatten(name="model_head_flatten")(model_head)
model_head = layers.Dense(256, activation="relu")(model_head)
model_head = layers.Dense(3, activation="softmax")(model_head)
model = models.Model(inputs=input_layer, outputs=model_head)
model.compile(loss="categorical_crossentropy", optimizer=optimizers.Adam(), metrics=["accuracy"])

Answer 1

At the end of the GradientTape loop, conv_output and grads already holds the value. The iterate function is no longer need to compute the values.

Working example below:

from tensorflow.keras.applications.vgg16 import preprocess_input
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.models import load_model

from tensorflow.keras import preprocessing
from tensorflow.keras import backend as K
from tensorflow.keras import models

import tensorflow as tf
import numpy as np

image_size = 224

# Load pre-trained Keras model and the image to classify
model = tf.keras.applications.vgg16.VGG16()
image = np.random.random((image_size, image_size, 3))
img_tensor = preprocessing.image.img_to_array(image)
img_tensor = np.expand_dims(img_tensor, axis=0)
img_tensor = preprocess_input(img_tensor)

conv_layer = model.get_layer("block5_conv3")
heatmap_model = models.Model([model.inputs], [conv_layer.output, model.output])

# Get gradient of the winner class w.r.t. the output of the (last) conv. layer
with tf.GradientTape() as gtape:
    conv_output, predictions = heatmap_model(img_tensor)
    loss = predictions[:, np.argmax(predictions[0])]
    grads = gtape.gradient(loss, conv_output)
    pooled_grads = K.mean(grads, axis=(0, 1, 2))

heatmap = tf.reduce_mean(tf.multiply(pooled_grads, conv_output), axis=-1)
heatmap = np.maximum(heatmap, 0)
max_heat = np.max(heatmap)
if max_heat == 0:
    max_heat = 1e-10
heatmap /= max_heat

print(heatmap.shape)