def gen_gcam(imgs,
model,
target_layer='layer4',
target_index=1,
classes=get_imagenet_classes(),
device='cuda',
prep=True):
"""
Visualize model responses given multiple images
"""
# Get model and forward pass
gcam, probs, ids, images = gen_model_forward(imgs,
model,
device=device,
prep=prep,
type='gcam')
for i in range(target_index):
# Grad-CAM
gcam.backward(ids=ids[:, [i]])
regions = gcam.generate(target_layer=target_layer)
masks = []
for j in range(len(images)):
print("\t#{}: {} ({:.5f})".format(j, classes[ids[j, i]], probs[j,
i]))
# Grad-CAM
mask = save_gradcam(gcam=regions[j, 0])
masks += [mask]
if len(masks) == 1:
return masks[0]
gcam.remove_hook()
return masks
def gen_grounding_lime_batch(imgs,
model='resnet18',
label_name='explanation',
from_saved=True,
target_index=1,
layer='layer4',
device=0,
topk=True,
classes=get_imagenet_classes(),
save=True,
save_path='./results/gradcam_examples/',
show=True):
#CUDA_VISIBLE_DEVICES=str(device)
# Create result directory if it doesn't exist; all explanations should
# be stored in a folder that is the predicted class
if not os.path.exists(save_path):
os.makedirs(save_path)
if save:
print('result path: {0}'.format(save_path))
if isinstance(model, str):
model_name = model
model, classes, target_layer = get_model_info(model, device=device)
else:
model_name = 'custom'
# Generate the explanations
masks = generate_lime_explanation_batch(imgs,
model,
pred_rank=1,
positive_only=True,
show=show,
device='cuda:' + str(device))
cams = []
for mask, img in zip(masks, imgs):
cams += [get_cam(img, mask)]
if save:
for i in range(len(imgs)):
res_path = save_path + str(target_index[i].cpu().numpy()) + '/'
if not os.path.exists(res_path):
os.makedirs(res_path)
#print("saving explanation mask....\n")
cv2.imwrite(res_path + 'original_img.png', get_displ_img(imgs[i]))
np.save(res_path + "lime_mask.npy", masks[i])
#just in case
torch.cuda.empty_cache()
return masks
def gen_grounding_bp_batch(imgs,
model='resnet18',
label_name='explanation',
from_saved=True,
target_index=1,
layer='layer4',
device=0,
topk=True,
classes=get_imagenet_classes(),
save=True,
save_path='./results/gradcam_examples/',
show=True):
#CUDA_VISIBLE_DEVICES=str(device)
# Create result directory if it doesn't exist; all explanations should
# be stored in a folder that is the predicted class
dateTimeObj = datetime.now()
timestampStr = dateTimeObj.strftime("%d-%b-%Y_%H")
if not os.path.exists(save_path):
os.makedirs(save_path)
if save:
print('result path: {0}'.format(save_path))
if isinstance(model, str):
model_name = model
model, classes, target_layer = get_model_info(model, device=device)
else:
model_name = 'custom'
# Generate the explanations
if topk:
masks = gen_bp(imgs,
model,
target_index=target_index,
target_layer=layer,
device=device,
single=False,
prep=False,
classes=classes)
else:
masks = gen_bp_target(imgs,
model,
target_index=target_index,
device=device,
single=False,
prep=False,
classes=classes)
cams = []
for mask, img in zip(masks, imgs):
cams += [get_cam(img, mask)]
if show:
#plot heatmaps
fig = plt.figure(figsize=(10, 10))
grid = ImageGrid(
fig,
111, # similar to subplot(111)
nrows_ncols=(2, 2),
axes_pad=0.35, # pad between axes in inch.
)
for ax, im in zip(grid, cams[:4]):
ax.axis('off')
# Iterating over the grid returns the Axes.
ax.imshow(im)
if save:
for i in range(len(imgs)):
res_path = save_path + str(target_index[i].cpu().numpy()) + '/'
if not os.path.exists(res_path):
os.makedirs(res_path)
#print("saving explanation mask....\n")
cv2.imwrite(res_path + 'original_img.png', get_displ_img(imgs[i]))
cv2.imwrite(res_path + "bp_mask.png", np.uint8(cams[i] * 255))
np.save(res_path + "bp_mask.npy", masks[i])
#just in case
torch.cuda.empty_cache()
return masks
'/work/lisabdunlap/explain-eval/data/imagenet_class_index.json',
'r') as f:
labels = json.load(f)
for key in labels:
index, label = labels[key]
if index == target:
return label, key
preprocess = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
# Normalization for ImageNet
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
])
classes = get_imagenet_classes()
dataset = datasets.ImageFolder(datadir, preprocess)
model = models.vgg19(pretrained=True)
indicies = [800, 1300, 2000, 2600, 3200, 3800, 4500, 5100, 5500, 6200]
names = [121, 207, 249, 251, 275, 291, 310, 359, 454, 519]
#indicies = [0, 800, 1300, 3200, 5100, 5500, 6200]
#names = [111, 121, 207, 275, 359, 454, 519]
#indicies = [5100, 5500, 6200]
#names = [359, 454, 519]
for start, label in zip(indicies, names):
print('---------------- ' + str(label) + ' ----------------------')
for i in range(50):
img, _ = dataset[start + i]
patch, idx, adv_idx = gen_adversarial_patch(
img,