def eval_te(conf):
"""
Evaluate against the entire test set of images.
Args:
conf: configuration dictionary
Returns:
psnr: psnr of entire test set
"""
path_te = conf["path_eval"]
iw = conf["iw"]
sr = conf["sr"]
cw = conf["cw"]
save = conf["save_sr_imgs"]
fns_te = preproc._get_filenames(path_te)
n = len(fns_te)
with tf.Graph().as_default(), tf.device("/cpu:0" if FLAGS.dev_assign else None):
# Placeholders
Xs = [tf.placeholder(tf.float32, [None, iw, iw, 1], name="X_%02d" % i) for i in range(FLAGS.num_gpus)]
y_splits = []
for i in range(FLAGS.num_gpus):
with tf.device(("/gpu:%d" % i) if FLAGS.dev_assign else None):
with tf.name_scope("%s_%02d" % (FLAGS.tower_name, i)) as scope:
y_split, _ = model.inference(Xs[i], conf)
y_splits.append(y_split)
tf.get_variable_scope().reuse_variables()
y = tf.concat(0, y_splits, name="y")
# Restore
saver = tf.train.Saver(tf.trainable_variables())
sess = tf.Session(
config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=FLAGS.log_device_placement)
)
ckpt = tf.train.get_checkpoint_state(conf["path_tmp"])
if ckpt:
ckpt = ckpt.model_checkpoint_path
print("checkpoint found: %s" % ckpt)
saver.restore(sess, ckpt)
else:
print("checkpoint not found!")
time.sleep(2)
# Iterate over each image, and calculate error
avg_psnr, avg_bl_psnr = 0.0, 0.0
for fn in fns_te:
lr, gt = preproc.lr_hr(sm.imread(fn), sr)
fn_ = fn.split("/")[-1].split(".")[0]
out_name = os.path.join("tmp", fn_ + "_HR.png") if save else None
hr = infer(lr, Xs, y, sess, conf, out_name)
# Evaluate
gt = gt[cw:, cw:]
gt = gt[: hr.shape[0], : hr.shape[1]]
diff = gt.astype(np.float32) - hr.astype(np.float32)
mse = np.mean(diff ** 2)
psnr = 20 * np.log10(255.0 / np.sqrt(mse))
avg_psnr += psnr
lr = lr[cw:, cw:]
lr = lr[: hr.shape[0], : hr.shape[1]]
bl_diff = gt.astype(np.float32) - lr.astype(np.float32)
bl_mse = np.mean(bl_diff ** 2)
bl_psnr = 20 * np.log10(255.0 / np.sqrt(bl_mse))
avg_bl_psnr += bl_psnr
print("hr PSNR: %.3f, lr PSNR % .3f for %s" % (psnr, bl_psnr, fn.split("/")[-1]))
avg_psnr /= len(fns_te)
avg_bl_psnr /= len(fns_te)
print("average test PSNR: %.3f" % avg_psnr)
print("average baseline PSNR: %.3f" % avg_bl_psnr)
return avg_psnr, avg_bl_psnr
def eval_te(conf):
"""
Evaluate against the entire test set of images.
Args:
conf: configuration dictionary
Returns:
psnr: psnr of entire test set
"""
path_te = conf['path_va']
iw = conf['iw']
sr = conf['sr']
cw = conf['cw']
save = conf['save_sr_imgs']
fns_te = preproc._get_filenames(path_te)
n = len(fns_te)
with tf.Graph().as_default(), tf.device('/cpu:0' if FLAGS.dev_assign else None):
# Placeholders
Xs = [tf.placeholder(tf.float32, [None, iw, iw, 1], name='X_%02d' % i) \
for i in range(FLAGS.num_gpus)]
y_splits = []
for i in range(FLAGS.num_gpus):
with tf.device(('/gpu:%d' % i) if FLAGS.dev_assign else None):
with tf.name_scope('%s_%02d' % (FLAGS.tower_name, i)) as scope:
y_split, _ = model.inference(Xs[i], conf)
y_splits.append(y_split)
tf.get_variable_scope().reuse_variables()
y = tf.concat(0, y_splits, name='y')
# Restore
saver = tf.train.Saver(tf.trainable_variables())
sess = tf.Session(config=tf.ConfigProto(
allow_soft_placement=True,
log_device_placement=FLAGS.log_device_placement))
ckpt = tf.train.get_checkpoint_state(conf['path_tmp'])
if ckpt:
ckpt = ckpt.model_checkpoint_path
print('checkpoint found: %s' % ckpt)
saver.restore(sess, ckpt)
else:
print('checkpoint not found!')
time.sleep(2)
# Iterate over each image, and calculate error
tmse = 0
bl_tmse = 0
for fn in fns_te:
lr, gt = preproc.lr_hr(sm.imread(fn), sr)
fn_ = fn.split('/')[-1].split('.')[0]
out_name = os.path.join('tmp', fn_ + '_HR.png') if save else None
hr = infer(lr, Xs, y, sess, conf, out_name)
# Evaluate
gt = gt[cw:, cw:]
gt = gt[:hr.shape[0], :hr.shape[1]]
diff = gt.astype(np.float32) - hr.astype(np.float32)
mse = np.mean(diff ** 2)
tmse += mse
psnr = 20 * np.log10(255.0 / np.sqrt(mse))
lr = lr[cw:, cw:]
lr = lr[:hr.shape[0], :hr.shape[1]]
bl_diff = gt.astype(np.float32) - lr.astype(np.float32)
bl_mse = np.mean(bl_diff ** 2)
bl_tmse += bl_mse
bl_psnr = 20 * np.log10(255.0 / np.sqrt(bl_mse))
print('hr PSNR: %.3f, lr PSNR % .3f for %s' % \
(psnr, bl_psnr, fn.split('/')[-1]))
rmse = np.sqrt(tmse / n)
psnr = 20 * np.log10(255. / rmse)
bl_rmse = np.sqrt(bl_tmse / n)
bl_psnr = 20 * np.log10(255. / bl_rmse)
print('total test PSNR: %.3f' % psnr)
print('total baseline PSNR: %.3f' % bl_psnr)
return psnr, bl_psnr
def eval_te(conf):
"""
Evaluate against the entire test set of images.
Args:
conf: configuration dictionary
Returns:
psnr: psnr of entire test set
"""
path_te = conf['path_eval']
iw = conf['iw']
sr = conf['sr']
cw = conf['cw']
save = conf['save_sr_imgs']
fns_te = preproc._get_filenames(path_te)
n = len(fns_te)
with tf.Graph().as_default(), tf.device('/cpu:0' if FLAGS.dev_assign else None):
# Placeholders
Xs = [tf.placeholder(tf.float32, [None, iw, iw, 1], name='X_%02d' % i) \
for i in range(FLAGS.num_gpus)]
y_splits = []
for i in range(FLAGS.num_gpus):
with tf.device(('/gpu:%d' % i) if FLAGS.dev_assign else None):
with tf.name_scope('%s_%02d' % (FLAGS.tower_name, i)) as scope:
y_split, _ = model.inference(Xs[i], conf)
y_splits.append(y_split)
tf.get_variable_scope().reuse_variables()
y = tf.concat(0, y_splits, name='y')
# Restore
saver = tf.train.Saver(tf.trainable_variables())
sess = tf.Session(config=tf.ConfigProto(
allow_soft_placement=True,
log_device_placement=FLAGS.log_device_placement))
ckpt = tf.train.get_checkpoint_state(conf['path_tmp'])
if ckpt:
ckpt = ckpt.model_checkpoint_path
print('checkpoint found: %s' % ckpt)
saver.restore(sess, ckpt)
else:
print('checkpoint not found!')
time.sleep(2)
# Iterate over each image, and calculate error
avg_psnr, avg_bl_psnr = 0., 0.
for fn in fns_te:
lr, gt = preproc.lr_hr(sm.imread(fn), sr)
fn_ = fn.split('/')[-1].split('.')[0]
out_name = os.path.join('tmp', fn_ + '_HR.png') if save else None
hr = infer(lr, Xs, y, sess, conf, out_name)
# Evaluate
gt = gt[cw:, cw:]
gt = gt[:hr.shape[0], :hr.shape[1]]
diff = gt.astype(np.float32) - hr.astype(np.float32)
mse = np.mean(diff ** 2)
psnr = 20 * np.log10(255.0 / np.sqrt(mse))
avg_psnr += psnr
lr = lr[cw:, cw:]
lr = lr[:hr.shape[0], :hr.shape[1]]
bl_diff = gt.astype(np.float32) - lr.astype(np.float32)
bl_mse = np.mean(bl_diff ** 2)
bl_psnr = 20 * np.log10(255.0 / np.sqrt(bl_mse))
avg_bl_psnr += bl_psnr
print('hr PSNR: %.3f, lr PSNR % .3f for %s' % \
(psnr, bl_psnr, fn.split('/')[-1]))
avg_psnr /= len(fns_te)
avg_bl_psnr /= len(fns_te)
print('average test PSNR: %.3f' % avg_psnr)
print('average baseline PSNR: %.3f' % avg_bl_psnr)
return avg_psnr, avg_bl_psnr
