heat map not working

models/version1/keras_metadata.pb

+
+Rroot"_tf_keras_sequential*R{"name": "sequential", "trainable": true, "expects_training_arg": true, "dtype": "float32", "batch_input_shape": null, "must_restore_from_config": false, "class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "rescaling_1_input"}}, {"class_name": "Rescaling", "config": {"name": "rescaling_1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "dtype": "float32", "scale": 0.00392156862745098, "offset": 0.0}}, {"class_name": "Conv2D", "config": {"name": "conv2d", "trainable": true, "dtype": "float32", "filters": 16, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}}, {"class_name": "Conv2D", "config": {"name": "conv2d_1", "trainable": true, "dtype": "float32", "filters": 32, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d_1", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}}, {"class_name": "Conv2D", "config": {"name": "conv2d_2", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "MaxPooling2D", "config": {"name": "maxPool2", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [1, 1]}, "data_format": "channels_last"}}, {"class_name": "Flatten", "config": {"name": "flatten", "trainable": true, "dtype": "float32", "data_format": "channels_last"}}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 128, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "dtype": "float32", "units": 3, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}]}, "shared_object_id": 21, "build_input_shape": {"class_name": "TensorShape", "items": [null, 180, 180, 3]}, "is_graph_network": true, "full_save_spec": {"class_name": "__tuple__", "items": [[{"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, 180, 180, 3]}, "float32", "rescaling_1_input"]}], {}]}, "save_spec": {"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, 180, 180, 3]}, "float32", "rescaling_1_input"]}, "keras_version": "2.6.0", "backend": "tensorflow", "model_config": {"class_name": "Sequential", "config": {"name": "sequential", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "rescaling_1_input"}, "shared_object_id": 0}, {"class_name": "Rescaling", "config": {"name": "rescaling_1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "dtype": "float32", "scale": 0.00392156862745098, "offset": 0.0}, "shared_object_id": 1}, {"class_name": "Conv2D", "config": {"name": "conv2d", "trainable": true, "dtype": "float32", "filters": 16, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 2}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 3}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 4}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}, "shared_object_id": 5}, {"class_name": "Conv2D", "config": {"name": "conv2d_1", "trainable": true, "dtype": "float32", "filters": 32, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 6}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 7}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 8}, {"class_name": "MaxPooling2D", "config": {"name": "max_pooling2d_1", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}, "shared_object_id": 9}, {"class_name": "Conv2D", "config": {"name": "conv2d_2", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 10}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 11}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 12}, {"class_name": "MaxPooling2D", "config": {"name": "maxPool2", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [1, 1]}, "data_format": "channels_last"}, "shared_object_id": 13}, {"class_name": "Flatten", "config": {"name": "flatten", "trainable": true, "dtype": "float32", "data_format": "channels_last"}, "shared_object_id": 14}, {"class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 128, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 15}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 16}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 17}, {"class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "dtype": "float32", "units": 3, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 18}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 19}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 20}]}}, "training_config": {"loss": {"class_name": "SparseCategoricalCrossentropy", "config": {"reduction": "auto", "name": "sparse_categorical_crossentropy", "from_logits": true}, "shared_object_id": 22}, "metrics": [[{"class_name": "MeanMetricWrapper", "config": {"name": "accuracy", "dtype": "float32", "fn": "sparse_categorical_accuracy"}, "shared_object_id": 23}]], "weighted_metrics": null, "loss_weights": null, "optimizer_config": {"class_name": "Adam", "config": {"name": "Adam", "learning_rate": 0.0010000000474974513, "decay": 0.0, "beta_1": 0.8999999761581421, "beta_2": 0.9990000128746033, "epsilon": 1e-07, "amsgrad": false}}}}2

+
root.layer-0"_tf_keras_layer*{"name": "rescaling_1", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "stateful": false, "must_restore_from_config": false, "class_name": "Rescaling", "config": {"name": "rescaling_1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 180, 180, 3]}, "dtype": "float32", "scale": 0.00392156862745098, "offset": 0.0}, "shared_object_id": 1}2

+	root.layer_with_weights-0"_tf_keras_layer*	{"name": "conv2d", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Conv2D", "config": {"name": "conv2d", "trainable": true, "dtype": "float32", "filters": 16, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 2}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 3}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 4, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 4, "axes": {"-1": 3}}, "shared_object_id": 24}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 180, 180, 3]}}2

+root.layer-2"_tf_keras_layer*{"name": "max_pooling2d", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "MaxPooling2D", "config": {"name": "max_pooling2d", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}, "shared_object_id": 5, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": 4, "max_ndim": null, "min_ndim": null, "axes": {}}, "shared_object_id": 25}}2

+	root.layer_with_weights-1"_tf_keras_layer*	{"name": "conv2d_1", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Conv2D", "config": {"name": "conv2d_1", "trainable": true, "dtype": "float32", "filters": 32, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 6}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 7}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 8, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 4, "axes": {"-1": 16}}, "shared_object_id": 26}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 90, 90, 16]}}2

+root.layer-4"_tf_keras_layer*{"name": "max_pooling2d_1", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "MaxPooling2D", "config": {"name": "max_pooling2d_1", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [2, 2]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [2, 2]}, "data_format": "channels_last"}, "shared_object_id": 9, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": 4, "max_ndim": null, "min_ndim": null, "axes": {}}, "shared_object_id": 27}}2

+	root.layer_with_weights-2"_tf_keras_layer*	{"name": "conv2d_2", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Conv2D", "config": {"name": "conv2d_2", "trainable": true, "dtype": "float32", "filters": 64, "kernel_size": {"class_name": "__tuple__", "items": [3, 3]}, "strides": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "same", "data_format": "channels_last", "dilation_rate": {"class_name": "__tuple__", "items": [1, 1]}, "groups": 1, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 10}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 11}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 12, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 4, "axes": {"-1": 32}}, "shared_object_id": 28}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 45, 45, 32]}}2

+root.layer-6"_tf_keras_layer*{"name": "maxPool2", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "MaxPooling2D", "config": {"name": "maxPool2", "trainable": true, "dtype": "float32", "pool_size": {"class_name": "__tuple__", "items": [1, 1]}, "padding": "valid", "strides": {"class_name": "__tuple__", "items": [1, 1]}, "data_format": "channels_last"}, "shared_object_id": 13, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": 4, "max_ndim": null, "min_ndim": null, "axes": {}}, "shared_object_id": 29}}2

+root.layer-7"_tf_keras_layer*{"name": "flatten", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Flatten", "config": {"name": "flatten", "trainable": true, "dtype": "float32", "data_format": "channels_last"}, "shared_object_id": 14, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 1, "axes": {}}, "shared_object_id": 30}}2

+	root.layer_with_weights-3"_tf_keras_layer*{"name": "dense", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 128, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 15}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 16}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 17, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 129600}}, "shared_object_id": 31}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 129600]}}2

+
+root.layer_with_weights-4"_tf_keras_layer*{"name": "dense_1", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "dtype": "float32", "units": 3, "activation": "linear", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 18}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 19}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 20, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 128}}, "shared_object_id": 32}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 128]}}2

+
root.keras_api.metrics.0"_tf_keras_metric*
{"class_name": "Mean", "name": "loss", "dtype": "float32", "config": {"name": "loss", "dtype": "float32"}, "shared_object_id": 33}2

+

root.keras_api.metrics.1"_tf_keras_metric*
{"class_name": "MeanMetricWrapper", "name": "accuracy", "dtype": "float32", "config": {"name": "accuracy", "dtype": "float32", "fn": "sparse_categorical_accuracy"}, "shared_object_id": 23}2

\ No newline at end of file

src/models/train_model.py

@@ -70,6 +70,8 @@ print(np.min(first_image), np.max(first_image))
 
 num_classes = 3
 
+
+
 model = Sequential([
     layers.Rescaling(1./255, input_shape=(img_height, img_width, 3)),
     layers.Conv2D(16, 3, padding='same', activation='relu'),
@@ -77,23 +79,26 @@ model = Sequential([
     layers.Conv2D(32, 3, padding='same', activation='relu'),
     layers.MaxPooling2D(),
     layers.Conv2D(64, 3, padding='same', activation='relu'),
-    layers.MaxPooling2D(),
+    layers.MaxPooling2D(1, name='maxPool2'),
     layers.Flatten(),
     layers.Dense(128, activation='relu'),
     layers.Dense(num_classes)
 ])
 
+
 model.compile(optimizer='adam',
               loss=tf.keras.losses.SparseCategoricalCrossentropy(
                   from_logits=True),
               metrics=['accuracy'])
 
+
 epochs = 10
 history = model.fit(
     train_ds,
     validation_data=val_ds,
     epochs=epochs
 )
+outputs = [layer.output for layer in model.layers]  
 
 model.save("../../models/version1")
 

src/visualization/heatMap.py

+from keras_preprocessing import image
 import numpy as np
 import tensorflow as tf
 from tensorflow import keras
+from keras.preprocessing.image import load_img
 
 # Display
 from IPython.display import Image, display
 import matplotlib.pyplot as plt
 import matplotlib.cm as cm
+import matplotlib.image as mpimg
 
+import pathlib
+data_dir = pathlib.Path("../../data/")
 
 model_builder = keras.applications.xception.Xception
 img_size = (299, 299)
@@ -15,9 +20,72 @@ decode_predictions = keras.applications.xception.decode_predictions
 
 last_conv_layer_name = "block14_sepconv2_act"
 
-# The local path to our target image
-img_path = keras.utils.get_file(
-    "test-tree.jpg",
-)
+img = mpimg.imread(data_dir/"test-tree.jpg")
+img_path = img
 
-display(Image(img_path))
\ No newline at end of file
+imgPlot = plt.imshow(img)
+plt.show()
+
+def get_img_array(img_path, size):
+    # `img` is a PIL image of size 299x299
+    img = keras.preprocessing.image.load_img(img_path, target_size=size)
+    # `array` is a float32 Numpy array of shape (299, 299, 3)
+    array = keras.preprocessing.image.img_to_array(img)
+    # We add a dimension to transform our array into a "batch"
+    # of size (1, 299, 299, 3)
+    array = np.expand_dims(array, axis=0)
+    return array
+
+def make_gradcam_heatmap(img_array, model, last_conv_layer_name, pred_index=None):
+    # First, we create a model that maps the input image to the activations
+    # of the last conv layer as well as the output predictions
+    grad_model = tf.keras.models.Model(
+        [model.inputs], [model.get_layer(last_conv_layer_name).output, model.output]
+    )
+
+    # Then, we compute the gradient of the top predicted class for our input image
+    # with respect to the activations of the last conv layer
+    with tf.GradientTape() as tape:
+        last_conv_layer_output, preds = grad_model(img_array)
+        if pred_index is None:
+            pred_index = tf.argmax(preds[0])
+        class_channel = preds[:, pred_index]
+
+    # This is the gradient of the output neuron (top predicted or chosen)
+    # with regard to the output feature map of the last conv layer
+    grads = tape.gradient(class_channel, last_conv_layer_output)
+
+    # This is a vector where each entry is the mean intensity of the gradient
+    # over a specific feature map channel
+    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
+
+    # We multiply each channel in the feature map array
+    # by "how important this channel is" with regard to the top predicted class
+    # then sum all the channels to obtain the heatmap class activation
+    last_conv_layer_output = last_conv_layer_output[0]
+    heatmap = last_conv_layer_output @ pooled_grads[..., tf.newaxis]
+    heatmap = tf.squeeze(heatmap)
+
+    # For visualization purpose, we will also normalize the heatmap between 0 & 1
+    heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
+    return heatmap.numpy()
+
+# Prepare image
+img_array = preprocess_input(get_img_array(img_path, size=img_size))
+
+# Make model
+model = model_builder(weights="imagenet")
+
+# Remove last layer's softmax
+model.layers[-1].activation = None
+
+# Print what the top predicted class is
+preds = model.predict(img_array)
+print("Predicted:", decode_predictions(preds, top=1)[0])
+
+# Generate class activation heatmap
+heatmap = make_gradcam_heatmap(img_array, model, last_conv_layer_name)
+
+# Display heatmap
+plt.matshow(heatmap)
+plt.show()
\ No newline at end of file

src/visualization/heatMapGet.py

+import tensorflow as tf
+import tensorflow.keras.backend as K
+from tensorflow import keras
+from tensorflow.keras.applications.inception_v3 import InceptionV3
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.applications.inception_v3 import preprocess_input, decode_predictions
+import numpy as np
+import os
+import matplotlib.pyplot as plt
+import cv2
+
+
+import pathlib
+model_dir = pathlib.Path("../../models/version1")
+data_dir = pathlib.Path("../../data/")
+
+model = model_dir
+
+ORIGINAL = (data_dir/"test-tree.jpg")
+
+DIM = 299
+
+img = image.load_img(ORIGINAL, target_size=(DIM, DIM))
+
+imgPlot = plt.imshow(img)
+plt.show()
+
+x = image.img_to_array(img)
+x = np.expand_dims(x, axis=0)
+x = preprocess_input(x)
+
+
+with tf.GradientTape() as tape:
+  last_conv_layer = model.get_layer('conv2d_93')
+  iterate = tf.keras.models.Model([model.inputs], [model.output, last_conv_layer.output])
+  model_out, last_conv_layer = iterate(x)
+  class_out = model_out[:, np.argmax(model_out[0])]
+  grads = tape.gradient(class_out, last_conv_layer)
+  pooled_grads = K.mean(grads, axis=(0, 1, 2))
+
+
+heatmap = tf.reduce_mean(tf.multiply(pooled_grads, last_conv_layer), axis=-1)
+
+heatmap = np.maximum(heatmap, 0)
+
+heatmap /= np.max(heatmap)
+print(heatmap.shape)
+heatmap = heatmap.reshape((8, 8))
+plt.matshow(heatmap)
+plt.show()
+img = plt.imread(ORIGINAL)
+
+
+INTENSITY = 0.5
+
+heatmap = cv2.resize(heatmap, (img.shape[1], img.shape[0]))
+
+heatmap = cv2.applyColorMap(np.uint8(255*heatmap), cv2.COLORMAP_JET)
+
+img = heatmap * INTENSITY + img
+
+
+imgPlot = plt.imshow(img)
+plt.show()
+
+
+