Learning-to-See-in-the-Dark
Learning-to-See-in-the-Dark copied to clipboard
Published
20 hours ago •
cchen156
cchen156
How to revise test_Sony.py to test your own images?
If you need to test your JPG images from another camera, that is not supported.
Hi, I wrote two methods to test my jpg image files using Sony pretrained model. But it not works perfectly. Just share my experiment code for someone interested. ^^
def _pack_rgb(self, rgb):
# Enlarge rgb before substract
im = rgb * 256
# Subtract the black level
im = np.maximum(im - 512, 0) / ((16383 - 512) )
# Multiply Amplification Factors
im = im * [0.2, 0.36, 0.2]
# Format image into RGBG 4 channels
g = im[:, :, 1]
g = np.expand_dims(g, axis=2)
out = np.concatenate((im, g), axis=2)
return out
def process_image(self, image):
input_full = np.expand_dims(self._pack_rgb(image), axis=0)
input_full = np.minimum(input_full, 1.0)
output = self._sess.run(self._out_image, feed_dict={self._in_image: input_full})
output = output[0, :, :, :]
output = np.minimum(np.maximum(output, 0), 1)
output = output * 255
output = output.astype(np.uint8)
h, w = output.shape[:2]
output = cv2.resize(output, (int(w/2), int(h/2)))
return output
Hi, I wrote two methods to test my jpg image files using Sony pretrained model. But it not works perfectly. Just share my experiment code for someone interested. ^^
def _pack_rgb(self, rgb): # Enlarge rgb before substract im = rgb * 256 # Subtract the black level im = np.maximum(im - 512, 0) / ((16383 - 512) ) # Multiply Amplification Factors im = im * [0.2, 0.36, 0.2] # Format image into RGBG 4 channels g = im[:, :, 1] g = np.expand_dims(g, axis=2) out = np.concatenate((im, g), axis=2) return out def process_image(self, image): input_full = np.expand_dims(self._pack_rgb(image), axis=0) input_full = np.minimum(input_full, 1.0) output = self._sess.run(self._out_image, feed_dict={self._in_image: input_full}) output = output[0, :, :, :] output = np.minimum(np.maximum(output, 0), 1) output = output * 255 output = output.astype(np.uint8) h, w = output.shape[:2] output = cv2.resize(output, (int(w/2), int(h/2))) return output
Hi could you tell me how to use it？
Hi, I wrote two methods to test my jpg image files using Sony pretrained model. But it not works perfectly. Just share my experiment code for someone interested. ^^
def _pack_rgb(self, rgb): # Enlarge rgb before substract im = rgb * 256 # Subtract the black level im = np.maximum(im - 512, 0) / ((16383 - 512) ) # Multiply Amplification Factors im = im * [0.2, 0.36, 0.2] # Format image into RGBG 4 channels g = im[:, :, 1] g = np.expand_dims(g, axis=2) out = np.concatenate((im, g), axis=2) return out def process_image(self, image): input_full = np.expand_dims(self._pack_rgb(image), axis=0) input_full = np.minimum(input_full, 1.0) output = self._sess.run(self._out_image, feed_dict={self._in_image: input_full}) output = output[0, :, :, :] output = np.minimum(np.maximum(output, 0), 1) output = output * 255 output = output.astype(np.uint8) h, w = output.shape[:2] output = cv2.resize(output, (int(w/2), int(h/2))) return outputHi could you tell me how to use it？
Hi, My original purpose is use this model to pre-process some dark images. So I wrote below class to do it. But result is not good ... orz.
from __future__ import division
import cv2
import numpy as np
import tensorflow as tf
import tensorflow.contrib.slim as slim
class SeeInDark:
"""A model wrapper of Learning to See in the Dark
Reference code:
https://github.com/cchen156/Learning-to-See-in-the-Dark/blob/master/test_Sony.py
"""
CHECKPOINT_FILE_PATH = './models/seeindark/Sony'
AMPLIFICATION_FACTORS = [0.53, 0.53, 0.381] # Default [0.85, 1.0, 0.7]
def __init__(self):
def lrelu(x):
return tf.maximum(x * 0.2, x)
def upsample_and_concat(x1, x2, output_channels, in_channels):
pool_size = 2
deconv_filter = tf.Variable(
tf.truncated_normal(
[pool_size, pool_size, output_channels, in_channels],
stddev=0.02
)
)
deconv = tf.nn.conv2d_transpose(
x1, deconv_filter, tf.shape(x2), strides=[1,
pool_size, pool_size, 1]
)
deconv_output = tf.concat([deconv, x2], 3)
deconv_output.set_shape([None, None, None, output_channels * 2])
return deconv_output
def network( input):
conv1 = slim.conv2d(
input, 32, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv1_1'
)
conv1 = slim.conv2d(
conv1, 32, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv1_2'
)
pool1 = slim.max_pool2d(conv1, [2, 2], padding='SAME')
conv2 = slim.conv2d(
pool1, 64, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv2_1'
)
conv2 = slim.conv2d(
conv2, 64, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv2_2'
)
pool2 = slim.max_pool2d(conv2, [2, 2], padding='SAME')
conv3 = slim.conv2d(
pool2, 128, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv3_1'
)
conv3 = slim.conv2d(
conv3, 128, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv3_2'
)
pool3 = slim.max_pool2d(conv3, [2, 2], padding='SAME')
conv4 = slim.conv2d(
pool3, 256, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv4_1'
)
conv4 = slim.conv2d(
conv4, 256, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv4_2'
)
pool4 = slim.max_pool2d(conv4, [2, 2], padding='SAME')
conv5 = slim.conv2d(
pool4, 512, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv5_1'
)
conv5 = slim.conv2d(
conv5, 512, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv5_2'
)
up6 = upsample_and_concat(conv5, conv4, 256, 512)
conv6 = slim.conv2d(
up6, 256, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv6_1'
)
conv6 = slim.conv2d(
conv6, 256, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv6_2'
)
up7 = upsample_and_concat(conv6, conv3, 128, 256)
conv7 = slim.conv2d(
up7, 128, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv7_1'
)
conv7 = slim.conv2d(
conv7, 128, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv7_2'
)
up8 = upsample_and_concat(conv7, conv2, 64, 128)
conv8 = slim.conv2d(
up8, 64, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv8_1'
)
conv8 = slim.conv2d(
conv8, 64, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv8_2'
)
up9 = upsample_and_concat(conv8, conv1, 32, 64)
conv9 = slim.conv2d(
up9, 32, [3, 3], rate=1, activation_fn=lrelu, scope='g_conv9_1')
conv9 = slim.conv2d(
conv9, 32, [3, 3], rate=1,
activation_fn=lrelu, scope='g_conv9_2'
)
conv10 = slim.conv2d(
conv9, 12, [1, 1], rate=1, activation_fn=None, scope='g_conv10')
out = tf.depth_to_space(conv10, 2)
return out
gpu_options = tf.GPUOptions(allow_growth=True)
sess_config = tf.ConfigProto(gpu_options=gpu_options)
g = tf.Graph()
with g.as_default():
self._sess = tf.Session(config=sess_config)
with self._sess.as_default():
self._in_image = tf.placeholder(tf.float32, [None, None, None, 4])
self._out_image = network(self._in_image)
saver = tf.train.Saver()
self._sess.run(tf.global_variables_initializer())
ckpt = tf.train.get_checkpoint_state(
SeeInDark.CHECKPOINT_FILE_PATH
)
if ckpt:
print('loaded ' + ckpt.model_checkpoint_path)
saver.restore(self._sess, ckpt.model_checkpoint_path)
else:
raise Exception('SeeInDark check point file not found!')
g.finalize()
def _pack_rgb(self, rgb):
im = rgb.astype(np.float32)
# Subtract the black level
black_threshold = 0.0
im = np.maximum(im - black_threshold, 0.0) / (255.0 - black_threshold)
# Multiply Amplification Factors
im = im * SeeInDark.AMPLIFICATION_FACTORS
# Format image into RGBG 4 channels
g = im[:, :, 1]
g = np.expand_dims(g, axis=2)
out = np.concatenate((im, g), axis=2)
return out
def process_image(self, image):
"""Brighten image
Args:
image (ndarray): rgb image
Returns:
(ndarray): brightened image
"""
input_full = np.expand_dims(self._pack_rgb(image), axis=0)
input_full = np.minimum(input_full, 1.0)
output = self._sess.run(
self._out_image,
feed_dict={self._in_image: input_full}
)
output = output[0, :, :, :]
output = np.minimum(np.maximum(output, 0), 1)
output = output * 255
output = output.astype(np.uint8)
# Model will output a double size image
# so resize back to original size
h, w = output.shape[:2]
output = cv2.resize(output, (int(w/2), int(h/2)))
return output
if __name__ == '__main__':
import time
import pandas as pd
# Setup experiment resource
FRAME_IMAGE = 'frame-1553563852-1.jpg'
FACE_IMAGE = 'frame-36-face-1.jpg'
# Init model
sid = SeeInDark()
# Measure processing frame speed
image = cv2.imread(FRAME_IMAGE)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# Warm up model
_ = sid.process_image(image)
time_list = []
for _ in range(20):
start_time = time.time()
_ = sid.process_image(image)
time_list.append(time.time() - start_time)
print('Average processing time on image size', image.shape)
print(pd.DataFrame(time_list).describe())
# Measure process face speed
image = cv2.imread(FACE_IMAGE)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# Warm up model
_ = sid.process_image(image)
time_list = []
for _ in range(20):
start_time = time.time()
_ = sid.process_image(image)
time_list.append(time.time() - start_time)
print('Average processing time on image size', image.shape)
print(pd.DataFrame(time_list).describe())
print('Done')