# Multi-structure Regions of Interest
#
# References :
# CNN structure based on VGG16, https://github.com/ry/tensorflow-vgg16/blob/master/vgg16.py
# Channel independent feature maps (3D features) using https://www.tensorflow.org/versions/r0.11/api_docs/python/nn.html#depthwise_conv2d_native
# GAP based on https://github.com/jazzsaxmafia/Weakly_detector/blob/master/src/detector.py
# Conv2d layer based on https://github.com/carpedm20/DCGAN-tensorflow/blob/master/ops.py
import tensorflow as tf
import numpy as np
import cPickle
from params import CNNParams, HyperParams
hyper = HyperParams(verbose=False)
cnn_param = CNNParams(verbose=False)
def print_model_params(verbose=True):
total_parameters = 0
for variable in tf.trainable_variables():
shape = variable.get_shape()
if verbose:
print("name: " + str(variable.name) + " - shape:" + str(shape))
variable_parametes = 1
for dim in shape:
variable_parametes *= dim.value
if verbose: print("variable parameters: ", variable_parametes)
total_parameters += variable_parametes
if verbose: print("total params: ", total_parameters)
return total_parameters
import math
import os
#import tensorflow as tf
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import numpy as np
import pandas as pd
from time import time
from model import CNN
from util import load_image, chunker
from params import TrainingParams, HyperParams, CNNParams
tparam = TrainingParams(verbose=True)
hyper = HyperParams(verbose=True)
cparam = CNNParams(verbose=True)
data_train = pd.read_pickle(tparam.data_train_path)
data_test = pd.read_pickle(tparam.data_test_path)
len_train = len(data_train)
len_test = len(data_train)
train_b_num = int(math.ceil(len_train / tparam.batch_size))
test_b_num = int(math.ceil(len_train / tparam.batch_size))
images_tf = tf.placeholder(tf.float32,
[None, hyper.image_h, hyper.image_w, hyper.image_c],
name="images")
if hyper.sparse:
labels_tf = tf.placeholder(tf.int64, [None], name='labels')
else:
labels_tf = tf.placeholder(tf.int64, [None, hyper.n_labels], name='labels')
def compressImage(imagePath):
"""
Generates and save the heatmaps and MS-ROI
Parameters
----------
imagePath : str
original image path
Returns
-------
str, str
Heatmap path, MS-ROI path
"""
image = load_single_image(imagePath)
hyper = HyperParams(verbose=False)
images_tf = tf.placeholder(
tf.float32, [None, hyper.image_h, hyper.image_w, hyper.image_c],
name="images")
class_tf = tf.placeholder(tf.int64, [None], name='class')
conv_last, gap, class_prob = ResNet50(images_tf)
classmap = get_classmap(class_tf, conv_last)
with tf.Session() as sess:
tf.train.Saver().restore(sess, hyper.model_path)
conv_last_val, class_prob_val = sess.run([conv_last, class_prob],
feed_dict={images_tf: image})
# use argsort instead of argmax to get all the classes
class_predictions_all = class_prob_val.argsort(axis=1)
print(class_predictions_all)
roi_map = None
for i in range(-1 * hyper.top_k, 0):
current_class = class_predictions_all[:, i]
classmap_vals = sess.run(classmap,
feed_dict={
class_tf: current_class,
conv_last: conv_last_val
})
normalized_classmap = normalize(classmap_vals[0])
if roi_map is None:
roi_map = 1.2 * normalized_classmap
else:
# simple exponential ranking
roi_map = (roi_map + normalized_classmap) / 2
roi_map = normalize(roi_map)
# Plot the heatmap on top of image
fig, ax = plt.subplots(1, 1, figsize=(12, 9))
ax.margins(0)
plt.axis('off')
plt.imshow(roi_map, cmap=plt.cm.jet, interpolation='nearest')
plt.imshow(image[0], alpha=0.4)
# save the plot and the map
if not os.path.exists('output'):
os.makedirs('output')
os.sep = '\\'
hmPath = os.sep.join(['static', 'overlayed_heatmap.png'])
plt.savefig(hmPath)
outPath = os.sep.join(['static', imagePath])
skimage.io.imsave(outPath, roi_map)
return hmPath, outPath
def compression_engine(img):
image = load_single_image(img)
#print("INPUT IMAGE ARRAY ",image.shape)
hyper = HyperParams(verbose=False)
images_tf = tf.placeholder(
tf.float32, [None, hyper.image_h, hyper.image_w, hyper.image_c],
name="images")
class_tf = tf.placeholder(tf.int64, [None], name='class')
cnn = CNN()
if hyper.fine_tuning:
cnn.load_vgg_weights()
conv_last, gap, class_prob = cnn.build(images_tf)
classmap = cnn.get_classmap(class_tf, conv_last)
with tf.Session() as sess:
tf.train.Saver().restore(sess, hyper.model_path)
conv_last_val, class_prob_val = sess.run([conv_last, class_prob],
feed_dict={images_tf: image})
# use argsort instead of argmax to get all the classes
class_predictions_all = class_prob_val.argsort(axis=1)
roi_map = None
for i in range(-1 * hyper.top_k, 0):
current_class = class_predictions_all[:, i]
classmap_vals = sess.run(classmap,
feed_dict={
class_tf: current_class,
conv_last: conv_last_val
})
normalized_classmap = normalize(classmap_vals[0])
if roi_map is None:
roi_map = 1.2 * normalized_classmap
else:
# simple exponential ranking
roi_map = (roi_map + normalized_classmap) / 2
roi_map = normalize(roi_map)
# Plot the heatmap on top of image
fig, ax = plt.subplots(1, 1, figsize=(12, 9))
ax.margins(0)
plt.axis('off')
plt.imshow(roi_map, cmap=plt.cm.jet, interpolation='nearest')
plt.imshow(image[0], alpha=0.4)
# save the plot and the map
if not os.path.exists('output'):
os.makedirs('output')
plt.savefig('output/overlayed_heatmap.png')
skimage.io.imsave('msroi_map.jpg', roi_map)
plt.clf()
print("MSROI TYPE : ", type(roi_map))
plt.close()
from glob import glob
# make the output directory to store the Q level images,
if not os.path.exists(output_directory):
os.makedirs(output_directory)
original = Image.open(img)
#print("ORIGINAL : ",original)
sal = Image.open('msroi_map.jpg')
out_name = make_quality_compression(original, sal, img, original)
# modified from source https://github.com/jazzsaxmafia/Weakly_detector/blob/master/src/train.caltech.py#L27
import numpy as np
import os
import pandas as pd
from params import TrainingParams, HyperParams, CNNParams
hparams = HyperParams(verbose=False)
tparam = TrainingParams(verbose=False)
image_dir_list = os.listdir(tparam.images_path)
label_pairs = map(lambda x: x.split('.'), image_dir_list)
labels, label_names = zip(*label_pairs)
labels = map(lambda x: int(x), labels)
# label_pairs = [x.split('.') for x in image_dir_list]
# labels, label_names = list(zip(*label_pairs))
# labels = [int(x) for x in labels]
label_dict = pd.Series(labels, index=label_names) - 1
image_paths_per_label = map(
lambda one_dir: map(
lambda one_file: os.path.join(tparam.images, one_dir, one_file),
os.listdir(os.path.join(tparam.images, one_dir))), image_dir_list)
image_paths_train = np.hstack(
map(lambda one_class: one_class[:-10], image_paths_per_label))
# image_paths_per_label = [
# [os.path.join(tparam.images, one_dir, one_file) for one_file in os.listdir(os.path.join(tparam.images, one_dir))]
# for one_dir in image_dir_list]