automatisch inladen in 2.frocs.py en opschonen bestanden

requirements.txt

@@ -0,0 +1,17 @@
+gast==0.3.3
+h5py==2.10.0
+Keras-Preprocessing==1.1.0
+matplotlib==3.4.3
+numpy==1.17.3
+pandas==0.25.3
+Pillow==8.4.0
+pyparsing==3.0.4
+python-dateutil==2.8.2
+rsa==4.0
+scipy==1.4.1
+SimpleITK==2.0.2
+six==1.16.0
+tensorboard==2.2.1
+tensorboard-plugin-wit==1.6.0.post3
+tensorflow==2.2.0
+tensorflow-estimator==2.2.0

src/sfransen/DWI_exp/callbacks.py

@@ -1,6 +1,6 @@
 import numpy as np
 import SimpleITK as sitk
-from helpers import *
+from sfransen.DWI_exp.helpers import *
 import tensorflow.keras.backend as K
 import tensorflow as tf 
 from tensorflow.keras.callbacks import Callback

src/sfransen/Saliency/base.py

@@ -0,0 +1,81 @@
+import numpy as np
+import tensorflow as tf
+
+class SaliencyMap():
+    def __init__(self, model):
+        """Constructs a Vanilla Gradient Map by computing dy/dx.
+
+        Args:
+            model: The TensorFlow model used to evaluate Gradient Map.
+                model takes image as input and outputs probabilities vector.
+        """
+        self.model = model
+
+
+    def get_top_predicted_idx(self, image):
+        """Outputs top predicted class for the input image.
+
+        Args:
+            img_processed: numpy image array in NHWC format, pre-processed according
+                to the defined model standard.
+
+        Returns:
+            Index of the top predicted class for the input image.
+        """
+        preds = self.model.predict(image)
+        # top_pred_idx = tf.argmax(preds[0])
+        top_pred_idx = 1
+        return top_pred_idx
+
+
+    def get_gradients(self, image):
+        """Computes the gradients of outputs w.r.t input image.
+
+        Args:
+            image: numpy image array in NHWC format, pre-processed according
+                to the defined model standard.
+
+        Returns:
+            Gradients of the predictions w.r.t image (same shape as input image)
+        """
+        image = tf.convert_to_tensor(image)
+        top_pred_idx = self.get_top_predicted_idx(image)
+
+        with tf.GradientTape() as tape:
+            tape.watch(image)
+            preds = self.model(image)
+            print("get_gradients, size of preds",np.shape(preds))
+            top_class = preds[:]
+            print("get_gradients, size of top_class",np.shape(top_class))
+
+
+        grads = tape.gradient(top_class, image)
+        return grads
+
+
+    def norm_grad(self, grad_x):
+        """Normalizes gradient to the range between 0 and 1
+        (for visualization purposes).
+
+        Args:
+            grad_x: numpy gradients array.
+
+        Returns:
+            Gradients of the predictions w.r.t image (same shape as input image)
+        """
+        abs_grads = np.abs(grad_x)
+        grad_max_ = np.max(abs_grads, axis=3)[0]
+        arr_min, arr_max  = np.min(grad_max_), np.max(grad_max_)
+        normalized_grad = (grad_max_ - arr_min) / (arr_max - arr_min + 1e-18)
+        normalized_grad = normalized_grad.reshape(1,grad_x.shape[1],grad_x.shape[2],1)
+
+        return normalized_grad
+
+
+    def get_mask(self, image, tensor_format=False):
+        """Returns a saliency mask specific to each method.
+
+        Args:
+            image: input image in NHWC format, not batched.
+        """
+        raise NotImplementedError('A derived class should implement get_mask()')

src/sfransen/Saliency/integrated_gradients.py

@@ -0,0 +1,63 @@
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.applications import densenet
+
+from base import SaliencyMap
+
+class IntegratedGradients(SaliencyMap):
+
+    def get_mask(self, image, baseline=None, num_steps=2):
+        """Computes Integrated Gradients for a predicted label.
+
+        Args:
+            image (ndarray): Original image
+            top_pred_idx: Predicted label for the input image
+            baseline (ndarray): The baseline image to start with for interpolation
+            num_steps: Number of interpolation steps between the baseline
+                and the input used in the computation of integrated gradients. These
+                steps along determine the integral approximation error. By default,
+                num_steps is set to 50.
+
+        Returns:
+            Integrated gradients w.r.t input image
+        """
+        # If baseline is not provided, start with a black image
+        # having same size as the input image.
+        if baseline is None:
+            img_size = image.shape
+            baseline = np.zeros(img_size).astype(np.float32)
+        else:
+            baseline = baseline.astype(np.float32)
+        print(">>>> step ONE completed")
+
+        img_input = image
+        top_pred_idx = self.get_top_predicted_idx(image)
+        interpolated_image = [
+            baseline + (i / num_steps) * (img_input - baseline)
+            for i in range(num_steps + 1)
+            ]
+        interpolated_image = np.vstack(interpolated_image).astype(np.float32)
+        print(">>>> step TWO completed")
+
+        grads = []
+        for i, img in enumerate(interpolated_image):
+            print("number of image:",i)
+            print("size of image:",np.shape(img))
+            img = tf.expand_dims(img, axis=0)
+            grad = self.get_gradients(img)
+            print("size of grad is:",np.shape(grad))
+            grads.append(grad[0])
+        grads = tf.convert_to_tensor(grads, dtype=tf.float32)
+        print(">>>> step THREE completed")
+
+        # 4. Approximate the integral using the trapezoidal rule
+        grads = (grads[:-1] + grads[1:]) / 2.0
+        avg_grads = tf.reduce_mean(grads, axis=0)
+        # tf.reduce_mean(grads, axis=(0, 1, 2, 3))
+        print(">>>> step FOUR completed")
+
+        # 5. Calculate integrated gradients and return
+        integrated_grads = (img_input - baseline) * avg_grads
+        print(">>>> step FIVE completed")
+
+        return integrated_grads

src/sfransen/__init__.py

@@ -0,0 +1,6 @@
+# from .csv2graph import *
+# from .data_path_rename import *
+# from .dump_params import *
+# from .Make_overlay import *
+# from .pred_label_images import *
+# from .utils_quintin import *