def interpret_signal(self, signal):
"""
Args:
signal:
Returns:
"""
output = signal.unsqueeze(0).to(self.device)
for i in self.modules:
layer = self.modules[i]
layer.eval().to(self.device)
output = layer(output)
output = torch.flatten(output,start_dim=1)
reduced_signal = self.pca.transform(output.detach())
example_index = self.__closest_point(reduced_signal)
example_signal = self.X[example_index]
signal_attribution = self.algo.attribute(signal.unsqueeze(0), target=0).detach().cpu().numpy()[0]
example_signal_attribution = self.algo.attribute(example_signal.unsqueeze(0), target=0).detach().cpu().numpy()[0]
signal_attribution = convert_to_grayscale(signal_attribution* signal.detach().numpy())
example_signal_attribution = convert_to_grayscale(example_signal_attribution* example_signal.detach().numpy())
# save_gradient_images(grayscale_guided_grads, result_dir + '_Guided_BP_gray')
return self.__plot_signals([signal, example_signal], [signal_attribution, example_signal_attribution]
, int(torch.round(torch.sigmoid(self.model(signal.unsqueeze(0).to(self.device)))).item())
, self.y[example_index].item(), self.channel_labels)
def vanilla_backprop_example(train,dataset,modeltype,dp):
f, axarr = plt.subplots(3,2)
f.set_figheight(10)
f.set_figwidth(10)
classes = train_models.get_classes(dataset)
pretrained_model = train_models.get_trained_model(train,dataset,modeltype,dp)
VBP = VanillaBackprop(pretrained_model)
print('model loaded, forwarding examples')
# show example index 0
example_index = 0
target_class = train_models.get_example_class_target(dataset,example_index)
original_image = train_models.get_example_input_image(dataset,example_index)
prep_img = train_models.get_example_preprocessed_image(dataset,example_index)
vanilla_grads = VBP.generate_gradients(prep_img, target_class)
grayscale_vanilla_grads = convert_to_grayscale(vanilla_grads)
axarr[example_index,0].imshow(original_image)
axarr[example_index,0].title.set_text(f'Original Image - {classes[target_class]}')
axarr[example_index,1].imshow(grayscale_vanilla_grads.squeeze(0))
axarr[example_index,1].title.set_text(f'Gradient Visualization Vanilla Backprop - {classes[target_class]}')
example_index = 1
target_class = train_models.get_example_class_target(dataset,example_index)
original_image = train_models.get_example_input_image(dataset,example_index)
prep_img = train_models.get_example_preprocessed_image(dataset,example_index)
vanilla_grads = VBP.generate_gradients(prep_img, target_class)
grayscale_vanilla_grads = convert_to_grayscale(vanilla_grads)
axarr[example_index,0].imshow(original_image)
axarr[example_index,0].title.set_text(f'Original Image - {classes[target_class]}')
axarr[example_index,1].imshow(grayscale_vanilla_grads.squeeze(0))
axarr[example_index,1].title.set_text(f'Gradient Visualization Vanilla Backprop - {classes[target_class]}')
example_index = 2
target_class = train_models.get_example_class_target(dataset,example_index)
original_image = train_models.get_example_input_image(dataset,example_index)
prep_img = train_models.get_example_preprocessed_image(dataset,example_index)
vanilla_grads = VBP.generate_gradients(prep_img, target_class)
grayscale_vanilla_grads = convert_to_grayscale(vanilla_grads)
axarr[example_index,0].imshow(original_image)
axarr[example_index,0].title.set_text(f'Original Image - {classes[target_class]}')
axarr[example_index,1].imshow(grayscale_vanilla_grads.squeeze(0))
axarr[example_index,1].title.set_text(f'Gradient Visualization Vanilla Backprop - {classes[target_class]}')
plt.show()
print('Vanilla backprop completed')
def vis_grad(model, class_index, layer, image_path, size=[224, 224]):
original_image = cv2.imread(image_path, 1)
#plt.imshow(original_image)
#plt.show()
prep_img = preprocess_image(original_image, size)
file_name_to_export = 'model' + '_classindex_' + str(
class_index) + '-layer_' + str(layer)
# Grad cam
gcv2 = GradCam(model, target_layer=layer)
# Generate cam mask
cam = gcv2.generate_cam(prep_img, class_index, size)
print('Grad cam completed')
# Guided backprop
GBP = GuidedBackprop(model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, class_index)
print('Guided backpropagation completed')
# Guided Grad cam
cam_gb = guided_grad_cam(cam, guided_grads)
#save_gradient_images(cam_gb, file_name_to_export + '_GGrad_Cam')
grayscale_cam_gb = convert_to_grayscale(cam_gb)
#save_gradient_images(grayscale_cam_gb, file_name_to_export + '_GGrad_Cam_gray')
print('Guided grad cam completed')
cam_gb = trans(cam_gb)
grayscale_cam_gb = trans(grayscale_cam_gb)
return cam_gb, grayscale_cam_gb
def guided_grad_cam(self,
numpy_img,
target_pspi,
file_name_to_export='test',
save=False):
# prep image for the network
prep_img = torch.from_numpy(
cv2.resize(numpy_img,
(200, 200))[None] / 255).float().unsqueeze_(0)
prep_img = prep_img.requires_grad_().cuda()
# Grad cam
# Generate cam mask
cam = generate_cam(self.pretrained_model, prep_img, target_pspi)
# Guided backprop
GBP = GuidedBackprop(self.pretrained_model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, target_pspi)
# Guided Grad cam
cam_gb = guided_grad_cam(cam, guided_grads)
grayscale_cam_gb = convert_to_grayscale(cam_gb)
if save:
save_gradient_images(cam_gb, file_name_to_export + '_GGrad_Cam')
save_gradient_images(grayscale_cam_gb,
file_name_to_export + '_GGrad_Cam_gray')
return cam_gb, grayscale_cam_gb
def generate_one_image_smooth_gradient(model_name,
image_name,
target_class,
full_image_path,
pretrain=True):
if model_name == 'denseNet':
pretrained_model = models.densenet121(pretrained=pretrain)
elif model_name == "resNet": # res net
pretrained_model = models.resnet18(pretrained=pretrain)
original_image = Image.open(full_image_path).convert('RGB')
prep_img = customPreProcessing(original_image)
save_image_name = image_name + model_name + '_SM_pretrained'
# save_image_name = image_name + model_name + '_SM_randomWeights'
# Vanilla backprop
VBP = VanillaBackprop(pretrained_model, _type=model_name)
param_n = 50
param_sigma_multiplier = 4
smooth_grad = generate_smooth_grad(
VBP, # ^This parameter
prep_img,
target_class,
param_n,
param_sigma_multiplier)
# Save colored gradients
save_gradient_images(smooth_grad, save_image_name + '_colored')
# Convert to grayscale
grayscale_smooth_grad = convert_to_grayscale(smooth_grad)
# Save grayscale gradients
save_gradient_images(grayscale_smooth_grad, save_image_name)
print('Smooth grad completed')
def interpret_image(self, image, target_class, result_dir):
# Get gradients
guided_grads = self.algo.attribute(
image, target_class).detach().cpu().numpy()[0]
print(guided_grads.shape)
# Save colored gradients
save_gradient_images(guided_grads, result_dir + '_Guided_BP_color')
# Convert to grayscale
grayscale_guided_grads = convert_to_grayscale(
guided_grads * image.detach().numpy()[0])
# Save grayscale gradients
save_gradient_images(grayscale_guided_grads,
result_dir + '_Guided_BP_gray')
# Positive and negative saliency maps
pos_sal, neg_sal = get_positive_negative_saliency(guided_grads)
save_gradient_images(pos_sal, result_dir + '_pos_sal')
save_gradient_images(neg_sal, result_dir + '_neg_sal')
print('Guided backprop completed')
one_hot_output[0][target_class] = 1
# Backward pass
model_output.backward(gradient=one_hot_output)
# Convert Pytorch variable to numpy array
# [0] to get rid of the first channel (1,3,224,224)
gradients_as_arr = self.gradients.data.numpy()[0]
return gradients_as_arr
if __name__ == '__main__':
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_example_params(target_example)
# Guided backprop
GBP = GuidedBackprop(pretrained_model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, target_class)
# Save colored gradients
save_gradient_images(guided_grads, file_name_to_export + '_Guided_BP_color')
print("exported to: " + str(os.getcwd()))
# Convert to grayscale
grayscale_guided_grads = convert_to_grayscale(guided_grads)
# Save grayscale gradients
save_gradient_images(grayscale_guided_grads, file_name_to_export + '_Guided_BP_gray')
# Positive and negative saliency maps
pos_sal, neg_sal = get_positive_negative_saliency(guided_grads)
save_gradient_images(pos_sal, file_name_to_export + '_pos_sal')
save_gradient_images(neg_sal, file_name_to_export + '_neg_sal')
print('Guided backprop completed')
model_output = self.model(self.input_image)
# Zero grads
self.model.zero_grad()
# Target for backprop
one_hot_output = torch.FloatTensor(1, model_output.size()[-1]).zero_()
one_hot_output[0][self.target_class] = 1
# Backward pass
model_output.backward(gradient=one_hot_output)
# Convert Pytorch variable to numpy array
# [0] to get rid of the first channel (1,3,224,224)
gradients_as_arr = self.gradients.data.numpy()[0]
return gradients_as_arr
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_params(target_example)
# Vanilla backprop
VBP = VanillaBackprop(pretrained_model, prep_img, target_class)
# Generate gradients
vanilla_grads = VBP.generate_gradients()
# Save colored gradients
save_gradient_images(vanilla_grads, file_name_to_export + '_Vanilla_BP_color')
# Convert to grayscale
grayscale_vanilla_grads = convert_to_grayscale(vanilla_grads)
# Save grayscale gradients
save_gradient_images(grayscale_vanilla_grads, file_name_to_export + '_Vanilla_BP_gray')
print('Vanilla backprop completed')
"""
cam_gb = np.multiply(grad_cam_mask, guided_backprop_mask)
return cam_gb
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_example_params(target_example)
# Grad cam
# gcv2 = GradCam(pretrained_model, target_layer=11)
gcv2 = GradCam(pretrained_model, target_layer=7)
# Generate cam mask
cam = gcv2.generate_cam(prep_img, target_class)
print('Grad cam completed')
# Guided backprop
GBP = GuidedBackprop(pretrained_model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, target_class)
print('Guided backpropagation completed')
# Guided Grad cam
cam_gb = guided_grad_cam(cam, guided_grads)
save_gradient_images(cam_gb, file_name_to_export + '_GGrad_Cam')
grayscale_cam_gb = convert_to_grayscale(cam_gb)
save_gradient_images(grayscale_cam_gb,
file_name_to_export + '_GGrad_Cam_gray')
print('Guided grad cam completed')
convert_to_grayscale,
save_gradient_images,
get_positive_negative_saliency)
from captum.attr import GuidedBackprop
from parkinsonsNet import Network
model = torch.load("/home/anasa2/pre_trained/parkinsonsNet-rest_mpower-rest.pth", map_location="cpu")
algo = GuidedBackprop(model)
# %%
import numpy as np
input = torch.randn(1, 3, 4000, requires_grad=True)
attribution = algo.attribute(input, target=0).detach().cpu().numpy()[0]
attribution = np.round(convert_to_grayscale(attribution* input.detach().numpy()[0]))
save_gradient_images(attribution, 'signal_color')
# %%
import pandas as pd
import numpy as np
import os
from torch.utils.data import Dataset, DataLoader
import math
import json
import time
from matplotlib.pylab import plt
%matplotlib inline
import itertools
class testMotionData(Dataset):
# Generate xbar images
xbar_list = self.generate_images_on_linear_path(input_image, steps)
# Initialize an iamge composed of zeros
integrated_grads = np.zeros(input_image.size())
for xbar_image in xbar_list:
# Generate gradients from xbar images
single_integrated_grad = self.generate_gradients(
xbar_image, target_class)
# Add rescaled grads from xbar images
integrated_grads = integrated_grads + single_integrated_grad / steps
# [0] to get rid of the first channel (1,3,224,224)
return integrated_grads[0]
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_example_params(target_example)
# Vanilla backprop
IG = IntegratedGradients(pretrained_model)
# Generate gradients
integrated_grads = IG.generate_integrated_gradients(
prep_img, target_class, 100)
# Convert to grayscale
grayscale_integrated_grads = convert_to_grayscale(integrated_grads)
# Save grayscale gradients
save_gradient_images(grayscale_integrated_grads,
file_name_to_export + '_Integrated_G_gray')
print('Integrated gradients completed.')
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_example_params(target_example)
VBP = VanillaBackprop(pretrained_model)
# GBP = GuidedBackprop(pretrained_model) # if you want to use GBP dont forget to
# change the parametre in generate_smooth_grad
param_n = 50
param_sigma_multiplier = 4
smooth_grad = generate_smooth_grad(
VBP, # ^This parameter
prep_img,
target_class,
param_n,
param_sigma_multiplier)
# Save colored gradients
save_gradient_images(smooth_grad,
file_name_to_export + '_SmoothGrad_color')
# Convert to grayscale
grayscale_smooth_grad = convert_to_grayscale(smooth_grad)
# Save grayscale gradients
save_gradient_images(grayscale_smooth_grad,
file_name_to_export + '_SmoothGrad_gray')
print('Smooth grad completed')
one_hot_output = torch.FloatTensor(1, model_output.size()[-1]).zero_()
one_hot_output[0][target_class] = 1
# Backward pass
model_output.backward(gradient=one_hot_output)
# Convert Pytorch variable to numpy array
# [0] to get rid of the first channel (1,3,224,224)
gradients_as_arr = self.gradients.data.numpy()[0]
return gradients_as_arr
if __name__ == '__main__':
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_params(target_example)
# Guided backprop
GBP = GuidedBackprop(pretrained_model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, target_class)
# Save colored gradients
save_gradient_images(guided_grads, file_name_to_export + '_Guided_BP_color')
# Convert to grayscale
grayscale_guided_grads = convert_to_grayscale(guided_grads)
# Save grayscale gradients
save_gradient_images(grayscale_guided_grads, file_name_to_export + '_Guided_BP_gray')
# Positive and negative saliency maps
pos_sal, neg_sal = get_positive_negative_saliency(guided_grads)
save_gradient_images(pos_sal, file_name_to_export + '_pos_sal')
save_gradient_images(neg_sal, file_name_to_export + '_neg_sal')
print('Guided backprop completed')
"""
Created on Wed Jun 19 17:12:04 2019
@author: Utku Ozbulak - github.com/utkuozbulak
"""
from misc_functions import (get_example_params, convert_to_grayscale,
save_gradient_images)
from vanilla_backprop import VanillaBackprop
# from guided_backprop import GuidedBackprop # To use with guided backprop
# from integrated_gradients import IntegratedGradients # To use with integrated grads
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_example_params(target_example)
# Vanilla backprop
VBP = VanillaBackprop(pretrained_model)
# Generate gradients
vanilla_grads = VBP.generate_gradients(prep_img, target_class)
# Make sure dimensions add up!
grad_times_image = vanilla_grads * prep_img.detach().numpy()[0]
# Convert to grayscale
grayscale_vanilla_grads = convert_to_grayscale(grad_times_image)
# Save grayscale gradients
save_gradient_images(
grayscale_vanilla_grads,
file_name_to_export + '_Vanilla_grad_times_image_gray')
print('Grad times image completed.')
# Average it out
smooth_grad = smooth_grad / param_n
return smooth_grad
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_params(target_example)
VBP = VanillaBackprop(pretrained_model)
# GBP = GuidedBackprop(pretrained_model) # if you want to use GBP dont forget to
# change the parametre in generate_smooth_grad
param_n = 50
param_sigma_multiplier = 4
smooth_grad = generate_smooth_grad(VBP, # ^This parameter
prep_img,
target_class,
param_n,
param_sigma_multiplier)
# Save colored gradients
save_gradient_images(smooth_grad, file_name_to_export + '_SmoothGrad_color')
# Convert to grayscale
grayscale_smooth_grad = convert_to_grayscale(smooth_grad)
# Save grayscale gradients
save_gradient_images(grayscale_smooth_grad, file_name_to_export + '_SmoothGrad_gray')
print('Smooth grad completed')
guided_backprop_mask (np_arr):Guided backprop mask
"""
cam_gb = np.multiply(grad_cam_mask, guided_backprop_mask)
return cam_gb
if __name__ == '__main__':
# Get params
target_example = 0 # Snake
(original_image, prep_img, target_class, file_name_to_export, pretrained_model) =\
get_params(target_example)
# Grad cam
gcv2 = GradCam(pretrained_model, target_layer=11)
# Generate cam mask
cam = gcv2.generate_cam(prep_img, target_class)
print('Grad cam completed')
# Guided backprop
GBP = GuidedBackprop(pretrained_model)
# Get gradients
guided_grads = GBP.generate_gradients(prep_img, target_class)
print('Guided backpropagation completed')
# Guided Grad cam
cam_gb = guided_grad_cam(cam, guided_grads)
save_gradient_images(cam_gb, file_name_to_export + '_GGrad_Cam')
grayscale_cam_gb = convert_to_grayscale(cam_gb)
save_gradient_images(grayscale_cam_gb, file_name_to_export + '_GGrad_Cam_gray')
print('Guided grad cam completed')