def test_guided_backprop():
# placeholder for input image
image = tf.placeholder(tf.float32, shape=[None, None, None, 3])
# initialize input dataflow
# change '.png' to other image types if other types of images are used
input_im = ImageFromFile('.png', data_dir=IMPATH,
num_channel=3, shuffle=False)
# batch size has to be one
input_im.set_batch_size(1)
# initialize guided back propagation class
# use VGG19 as an example
# images will be rescaled to smallest side = 224 is is_rescale=True
model = GuideBackPro(vis_model=VGG19_FCN(is_load=False,
is_rescale=True))
# get op to compute guided back propagation map
# final output respect to input image
back_pro_op = model.get_visualization(image)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
im = input_im.next_batch()[0]
guided_backpro, label, o_im =\
sess.run([back_pro_op, model.pre_label,
model.input_im],
feed_dict={image: im})
print(label)
tf.reset_default_graph()
def test_gradcam():
# merge several output images in one large image
merge_im = 1
grid_size = np.ceil(merge_im**0.5).astype(int)
# class label for Grad-CAM generation
# 355 llama 543 dumbbell 605 iPod 515 hat 99 groose 283 tiger cat
# 282 tabby cat 233 border collie 242 boxer
# class_id = [355, 543, 605, 515]
class_id = [283, 242]
# initialize Grad-CAM
# using VGG19
gcam = ClassifyGradCAM(vis_model=VGG19_FCN(is_load=False, is_rescale=True))
gbackprob = GuideBackPro(
vis_model=VGG19_FCN(is_load=False, is_rescale=True))
# placeholder for input image
image = tf.placeholder(tf.float32, shape=[None, None, None, 3])
# create VGG19 model
gcam.create_model(image)
gcam.setup_graph()
# generate class map and prediction label ops
map_op = gcam.get_visualization(class_id=class_id)
label_op = gcam.pre_label
back_pro_op = gbackprob.get_visualization(image)
# initialize input dataflow
# change '.png' to other image types if other types of images are used
input_im = ImageFromFile('.png',
data_dir=IMPATH,
num_channel=3,
shuffle=False)
input_im.set_batch_size(1)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
cnt = 0
merge_cnt = 0
o_im_list = []
im = input_im.next_batch()[0]
gcam_map, b_map, label, o_im =\
sess.run([map_op, back_pro_op, label_op, gcam.input_im],
feed_dict={image: im})
print(label)
o_im_list.extend(o_im)
for idx, cid, cmap in zip(count(), gcam_map[1], gcam_map[0]):
overlay_im = image_overlay(cmap, o_im)
weight_im = image_weight_mask(b_map[0], cmap)
try:
weight_im_list[idx].append(weight_im)
overlay_im_list[idx].append(overlay_im)
except NameError:
gcam_class_id = gcam_map[1]
weight_im_list = [[] for i in range(len(gcam_class_id))]
overlay_im_list = [[] for i in range(len(gcam_class_id))]
weight_im_list[idx].append(weight_im)
overlay_im_list[idx].append(overlay_im)
tf.reset_default_graph()
num_channel=3)
display_data(test_data, 'test_data')
word_dict = get_word_list('../data/imageNetLabel.txt')
model.create_model([image, 1])
test_op = tf.nn.top_k(tf.nn.softmax(model.layer['output']),
k=5,
sorted=True)
input_op = model.layer['input']
writer = tf.summary.FileWriter(conf.SAVE_DIR)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
writer.add_graph(sess.graph)
for k in range(0, 50):
if test_data.epochs_completed < 1:
batch_data = test_data.next_batch()
im = batch_data[0]
im = resize_image_with_smallest_side(im, 224)
# im = center_crop_image(im, 224, 224)
# scipy.misc.imsave('{}test_{}.png'.format(conf.SAVE_DIR, k),
# np.squeeze(im))
result = sess.run(test_op, feed_dict={image: im})
for val, ind in zip(result.values, result.indices):
print(val)
print(ind)
print(word_dict[ind[0]])
back_pro_op[0]: list中每個值，是激活值對輸入圖片透過導向反向傳播求導值，
為和輸入一樣大的矩陣，分別為激活值對每個像素的導數
back_pro_op[1]: list中每個值，是該輸入圖所對應的類別，
有指定class_id: 是該class_id
沒指定class_id: 分類的結果
"""
back_pro_op = model.get_visualization(image)
#writer = tf.summary.FileWriter(config.save_path)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
#writer.add_graph(sess.graph)
cnt = 0
while input_im.epochs_completed < 1:
im = input_im.next_batch()[0]
guided_backpro, label, o_im =\
sess.run([back_pro_op, model.pre_label, model.input_im],
feed_dict={image: im})
print("\n第%d張影像前%d類分類結果："%(cnt, len(label[0][0])))
for i in range(len(label[0][0])):
print("置信度:%5.2f%% 類別(%3d):%s"%(label[0][0][i]*100, label[1][0][i], C.class_name[label[1][0][i]]))
for cid, guided_map in zip(guided_backpro[1], guided_backpro[0]):
scipy.misc.imsave(
'{}map_{}_class_{}.png'.format(config.save_path_guided + 'guided/', cnt, cid),
np.squeeze(guided_map))
scipy.misc.imsave('{}im_{}.png'.format(config.save_path_guided + 'org/', cnt),
np.squeeze(o_im))