def main():
ckpt_filename = './ssd_300_kitti/ssd_model.ckpt'
isess = tf.InteractiveSession()
tensors = get_tenors(ckpt_filename, isess)
saver = tf.train.Saver()
saver.restore(isess, ckpt_filename)
# Load a sample image.
path = 'test_images/'
path = '../kitti/voc_format/VOC2012/JPEGImages/'
path = '../kitti/testing/image_2/'
#path = "../PhotographicImageSynthesis/result_512p/final/"
outpath = 'output_images/'
image_names = sorted(os.listdir(path))
for idx, name in enumerate(image_names):
idx += 7481
print("%06d.png" % idx)
img = imread_as_jpg(path + "%06d.png" % idx)
img = cv2.resize(img, (463, 150))
img = process_image(img,
tensors,
isess,
select_threshold=0.8,
nms_threshold=0.5)
def main():
#CUDA_VISIBLE_DEVICES=""
os.environ['CUDA_VISIBLE_DEVICES'] = ''
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
isess = tf.InteractiveSession()
ckpt_filename = './ssd_300_kitti/ssd_model.ckpt'
tensors = get_tenors(ckpt_filename, isess)
predictions, localisations, logits, end_points, img_input, ssd = tensors
rs = r".*\/conv[0-9]\/conv[0-9]_[0-9]/Relu$"
rc = re.compile(rs)
new_end_points = {}
for op in tf.get_default_graph().as_graph_def().node:
gr = rc.match(op.name)
if gr:
print(op.name)
new_end_points[op.name.split(
"/")[-2]] = tf.get_default_graph().get_tensor_by_name(op.name +
":0")
"""
for n in new_end_points:
print(n,new_end_points[n])
"""
path = '../kitti/voc_format/VOC2012/JPEGImages/'
outpath = 'output_images/'
image_names = sorted(os.listdir(path))
dimpkl = {}
for name in image_names:
img = imread_as_jpg(path + name)
img = cv2.resize(img, (993 // 2, 300))
print(img.shape, name)
#img = process_image(img, tensors,isess, select_threshold=0.8, nms_threshold=0.5)
img = process_image(img,
tensors,
isess,
select_threshold=0.8,
nms_threshold=0.5)
#mpimg.imsave(outpath + name, img, format='jpg')
for n in new_end_points:
val = isess.run([new_end_points[n]], feed_dict={img_input: img})[0]
print(n, val.shape[1:3])
dimpkl[n] = val.shape[1:3]
dill.dump(dimpkl, open("dim_300.pkl", "wb"))
assert (False)
mpimg.imsave(outpath + name, img, format='jpg')
def main():
nf = 256
zdim = 1024
filepath = "/workspace2/kitti/testing/image_2/007481.png"
filepath = "test/test0_2.jpg"
filepath = "test/test1_2.jpg"
filepath = "test/noise3.jpg"
filepath = "test/adversary.png"
filepath = "/workspace2/kitti/training/image_2/000003.png"
filepath = "/workspace2/kitti/testing/image_2/007597.png"
filepath = "/workspace2/kitti/testing/image_2/007662.png"
filepath = "/workspace2/kitti/testing/image_2/008001.png"
filepath = "/workspace2/kitti/testing/image_2/007618.png"
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)
images = tf.placeholder(tf.float32, [1, 150, 496, 3])
scdobj = scd.SCD(input=images)
rgan = eval_rgan.rgan(images=scdobj.end_points["pool5"],
z_dim=zdim,
nf=nf,
training=True)
imgsynth_from_feature = eval_imgsynth.ImageSynthesizer(rgan.rec_x_out)
scd_saver = scd.get_saver()
scd_saver.restore(sess, "/workspace/imgsynth/ssd_300_kitti/ssd_model.ckpt")
imgsynth_saver = eval_imgsynth.get_saver()
imgsynth_saver.restore(
sess, "/workspace/imgsynth/result_kitti256p_2/model.ckpt-89")
rgan_saver = eval_rgan.get_saver()
#rgan_saver.restore(sess,"models/model-99999")
rgan_saver.restore(sess, "models_doubleres_constr_x_rzx/model-80999")
image = cv2.resize(scd.imread_as_jpg(filepath), (496, 150))
image = np.expand_dims(image, 0)
reses = imgsynth_from_feature.generate_image_from_featuremap(
sess, image, images)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/single_generated.jpg", a)
def main():
filepath = "/workspace2/kitti/testing/image_2/007481.png"
filepath = "test/test0_2.jpg"
filepath = "test/test1_2.jpg"
filepath = "test/noise3.jpg"
filepath = "test/adversary.png"
filepath = "/workspace2/kitti/testing/image_2/007489.png"
filepath = "test/single_generated.jpg"
filepath = "test/valid_adv7.png"
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)
images = tf.placeholder(tf.float32, [1, 150, 496, 3])
scdobj = scd.SCD(input=images)
scd_saver = scd.get_saver()
scd_saver.restore(sess, "/workspace/imgsynth/ssd_300_kitti/ssd_model.ckpt")
image = cv2.resize(scd.imread_as_jpg(filepath), (496, 150))
image = np.expand_dims(image, 0)
reses = scdobj.get_image(sess, image)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/single_detected%d.jpg" % i, a)
def main():
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
sess = tf.Session(config=config)
#define tensors and models
zb = 6
nf = 256
zdim = 1024
images = tf.placeholder(tf.float32, [2, 150, 496, 3])
z = tf.placeholder(tf.float32, [zb, zdim])
scdobj = scd.SCD(input=images)
imgsynth = eval_imgsynth.ImageSynthesizer(scdobj.end_points["pool5"])
rgan = eval_rgan.rgan(images=scdobj.end_points["pool5"],
z_dim=zdim,
nf=nf,
training=True)
imgsynth_from_feature = eval_imgsynth.ImageSynthesizer(rgan.rec_x_out,
reuse=True)
rgan_from_z = eval_rgan.rgan(latent_vec=z,
nf=nf,
z_dim=zdim,
reuse=True,
training=True)
imgsynth_from_z = eval_imgsynth.ImageSynthesizer(rgan_from_z.rec_x_p_out,
reuse=True)
#load weights
scd_saver = scd.get_saver()
scd_saver.restore(sess, "/workspace/imgsynth/ssd_300_kitti/ssd_model.ckpt")
imgsynth_saver = eval_imgsynth.get_saver()
imgsynth_saver.restore(
sess, "/workspace/imgsynth/result_kitti256p_2/model.ckpt-89")
rgan_saver = eval_rgan.get_saver()
rgan_saver.restore(sess, "models/model-99999")
co = []
image = cv2.resize(
scd.imread_as_jpg("/workspace2/kitti/testing/image_2/007482.png"),
(496, 150))
co.append(image)
image = cv2.resize(
scd.imread_as_jpg("/workspace2/kitti/testing/image_2/007481.png"),
(496, 150))
co.append(image)
#reses = imgsynth.generate_image_from_featuremap(np.expand_dims(image,0),images)
image = np.array(co)
#simply get detection result
reses = scdobj.get_image(sess, image)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/detected%d.jpg" % i, a)
#model:image=>feature, image decoder:feature=>image_hat
reses = imgsynth.generate_image_from_featuremap(sess, image, images)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/test%d.jpg" % i, a)
#model:image=>feature, gan:feature=>latent vector=>feature_hat, image decoder:feature_hat=>image_hat
reses = imgsynth_from_feature.generate_image_from_featuremap(
sess, image, images)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/test%d_2.jpg" % i, a)
#get detection result thru gan and image decoder
reses = scdobj.get_image(sess, reses)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/gan_detected%d.jpg" % i, a)
return 0
#latent vector=>feature_hat, image decoder:feature_hat=>image_hat
np.random.seed(0)
zs = []
zsp = np.random.randn(zb, zdim) + 1
zs = np.array(zsp)
reses = imgsynth_from_z.generate_image_from_featuremap(sess, zs, z)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/noise%d.jpg" % i, a)
#noise interpolation
zsb = []
for i in range(0, zb):
#zs.append(zsp[0]*float(i)/(float(zb)-1.)+zsp[1]*(1.-float(i)/(float(zb)-1.)))
zsb.append(zsp[i] * (1. - i / (zb - 1)))
zsb = np.array(zsb)
reses = imgsynth_from_z.generate_image_from_featuremap(sess, zsb, z)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/noise_interpolate%d.jpg" % i, a)
#model:images=>features, gan:features=>latent vectors=>features_hat, interpolate:features_hat=>features_interplated, image decoder:feature_interplated=>image_hat
zs = []
zsp = rgan.generate_noise_from_featuremap(sess, image, images)
for i in range(0, zb):
zs.append(zsp[0] * float(i) / zb + zsp[1] * (1 - float(i) / zb))
zs = np.array(zs)
reses = imgsynth_from_z.generate_image_from_featuremap(sess, zs, z)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/interpolate%d.jpg" % i, a)
zs = []
zsp = rgan.generate_noise_from_featuremap(sess, image, images)
for i in range(0, zb):
zs.append(zsp[0] * float(i) / zb + zsp[1] * (1 - float(i) / zb) + 3)
zs = np.array(zs)
reses = imgsynth_from_z.generate_image_from_featuremap(sess, zs, z)
for i, a in enumerate(reses):
print(i)
skimage.io.imsave("test/interpolate2%d.jpg" % i, a)
label_images = [None] * NUM_TRAINING_IMAGES
for epoch in range(1, 201):
if os.path.isdir("result_256p/%04d" % epoch):
continue
cnt = 0
for ind in np.random.permutation(NUM_TRAINING_IMAGES - 25) + 1:
st = time.time()
cnt += 1
if input_images[ind] is None:
#label_images[ind]=helper.get_semantic_map("data/cityscapes/Label256Full/%08d.png"%ind)#training label
#input_images[ind]=np.expand_dims(np.float32(scipy.misc.imread("data/cityscapes/RGB256Full/%08d.png"%ind)),axis=0)#training image
label_images[ind] = np.load("hmlabels/%06d.npz" %
ind)["arr_0"] #training label
path = '../kitti/voc_format/VOC2012/JPEGImages/%06d.png' % ind
img = imread_as_jpg(path)
#img = cv2.resize(img, (993,300))
img = cv2.resize(img, (512, 256))
input_images[ind] = np.expand_dims(np.float32(img),
axis=0) #training image
_, G_current, l0, l1, l2, l3, l4, l5 = sess.run(
[G_opt, G_loss, p0, p1, p2, p3, p4, p5],
feed_dict={
label:
np.concatenate(
(label_images[ind],
np.expand_dims(1 - np.sum(label_images[ind], axis=3),
axis=3)),
axis=3),
real_image:
input_images[ind],
parser.add_argument("--decay_factor",
type=float,
default=0.01,
help="exponential annealing decay rate [0.01]")
parser.add_argument("--doubleres",
type=bool,
default=False,
help="exponential annealing decay rate [0.01]")
parser.add_argument('--exdir', type=str, default='examples')
parser.add_argument('--mddir', type=str, default='models')
args = parser.parse_args()
fixed_images = np.zeros([8, args.input_h, args.input_w, args.input_c])
for i in range(8):
fixed_images[i, :, :, :] = cv2.resize(
scd.imread_as_jpg(
os.path.join(args.dataset_test_path, "%06d.png" % (i + 7481))),
(args.input_w, args.input_h))
mnistWganInv = pxhdgan(x_dim=784,
z_dim=args.z_dim,
w=args.input_w,
h=args.input_h,
c=args.input_c,
latent_dim=args.latent_dim,
nf=256,
batch_size=args.batch_size,
c_gp_x=args.c_gp_x,
lamda=args.lamda,
output_path=args.output_path,
args=args)
return x_p
def inv_fn(x):
z_p = rgan.generate_noise_from_featuremap(sess, x, images)
return z_p
if args.iterative:
search = iterative_search
else:
search = recursive_search
_, _, test_data = tflib.mnist.load_data()
i = 0
co = []
image = cv2.resize(scd.imread_as_jpg(path), (496, 150))
co.append(image)
image = np.array(co)
x = image
y = 1
adversary = search(gen_fn,
inv_fn,
cla_fn,
x,
y,
y_t=y_t,
h=upl,
nsamples=args.nsamples,
step=args.step,
verbose=args.verbose)
if args.iterative: