kuijiang94 / eegan Goto Github PK
View Code? Open in Web Editor NEWEdge Enhanced GAN For Remote Sensing Image Super-Resolution
Edge Enhanced GAN For Remote Sensing Image Super-Resolution
Does this has a pytorch implementation version?
The URL link shows that it is being maintained. Can you upload the data?
I am using this Dockerfile in case it is useful:
FROM tensorflow/tensorflow:1.1.0-devel-gpu-py3
RUN apt update -y && apt-get install python3-tk -y
RUN pip3 install --upgrade pip
RUN pip3 install Pillow
RUN pip3 install opencv-python
RUN pip3 install tqdm requests
Then python3 within
Please let me know if any of you have something better
requests.exception.connectionerror
Hello! When running train.py on the example image set the output are a series of single piexel width images. This is what I get in the console:
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:455: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:456: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:457: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:458: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:459: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/home/jovyan/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:462: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
(720, 720, 3)
(1, 720, 720, 3)
2021-02-16 18:24:44.719827: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2021-02-16 18:24:44.720286: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2021-02-16 18:24:44.720335: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2021-02-16 18:24:44.720356: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2021-02-16 18:24:44.720461: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
(720, 720, 3)
(1, 720, 720, 3)
(720, 720, 3)
(1, 720, 720, 3)
(720, 720, 3)
(1, 720, 720, 3)
(720, 720, 3)
(1, 720, 720, 3)
spent 410.88904190063477 s.
Any help hugely appreciated!
百度网盘密码不正确
When I use multiple images to test, execute test.py and it will appear:
Process finished with exit code -1073741676 (0xC0000094)
How can I solve this?
could you upload the pre-traing model again?
江师兄您好,您上传的VGG19预训练模型和训练好的两个模型 是不是少东西 少了meta...
I am trying to test out this code however, all pretained models (VGG/EGAN) are not accessible. can you update the URLs for them please or advise on how to get them.
Getting the following error on executing test.py
:
WARNING:tensorflow:From test.py:17: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.
WARNING:tensorflow:From test.py:20: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
(720, 720, 3)
(1, 720, 720, 3)
Traceback (most recent call last):
File "test.py", line 53, in <module>
model = Model(x, is_training, 1)#16
File "../TESTGAN.py", line 14, in __init__
n,w,h,c = input.get_shape().as_list()
AttributeError: 'builtin_function_or_method' object has no attribute 'get_shape'
When I tried with tf.shape(input).as_list()
instead of input.get_shape().as_list()
, I got the following error:
WARNING:tensorflow:From test.py:17: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.
WARNING:tensorflow:From test.py:20: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
(720, 720, 3)
(1, 720, 720, 3)
Traceback (most recent call last):
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/tensor_util.py", line 541, in make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/tensor_util.py", line 541, in <listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/util/compat.py", line 71, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got <built-in function input>
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "test.py", line 53, in <module>
model = Model(x, is_training, 1)#16
File "../TESTGAN.py", line 14, in __init__
n,w,h,c = tf.shape(input).as_list()
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/ops/array_ops.py", line 447, in shape
return shape_internal(input, name, optimize=True, out_type=out_type)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/ops/array_ops.py", line 471, in shape_internal
input_tensor = ops.convert_to_tensor(input)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 1184, in convert_to_tensor
return convert_to_tensor_v2(value, dtype, preferred_dtype, name)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 1242, in convert_to_tensor_v2
as_ref=False)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/ops.py", line 1297, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/constant_op.py", line 286, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/constant_op.py", line 227, in constant
allow_broadcast=True)
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/constant_op.py", line 265, in _constant_impl
allow_broadcast=allow_broadcast))
File "/home/navaneeth/anaconda3/envs/image-sr-tf/lib/python3.6/site-packages/tensorflow_core/python/framework/tensor_util.py", line 545, in make_tensor_proto
"supported type." % (type(values), values))
TypeError: Failed to convert object of type <class 'builtin_function_or_method'> to Tensor. Contents: <built-in function input>. Consider casting elements to a supported type.
Could you please suggest a workaround?
Please help with the pretrained VGG-19 model. I cannot find the model in either of the provided links. Thanks
Is there a new pretrained EEGAN weights file?
I got the following error message>
Key generator/conv_m2/weight not found in checkpoint
System:
tensorflow 1.10.0
python 3.6
Hello, thanks for your wonderful work!
İn the test.py, I met this problem, the model does not have contribute 'model.ZConv_VDSR'. I checked in the TESTGAN.py file, there is no definition. May I ask what does it mean by 'model.ZConv_VDSR'?
fake = sess.run(
[model.ZConv_VDSR],
feed_dict={x: input_, is_training: False})
为什么我训练出来的模型测试时,测试图片分辨率没有变化,反而增加了很多黑色的噪声点
我前几天看到一篇EESRGAN做小目标检测的, 生成器部分引用的你的论文的网络结构。
When i try to run your python train.py code i get the error that says 'TypeError: object of type 'NoneType' has no len()'. I have looked a lot of platforms and it seems that ''The “TypeError: object of type 'NoneType' has no len() ” error is caused when you try to use the len() method on an object whose value is None. To solve this error, make sure that you are not assigning the responses of any built-in list methods, like sort() , to a variable.''. How do i figure this out. The code im getting the problem is below in line 38.
import numpy as np
import tensorflow as tf
from tqdm import tqdm
import argparse
import sys
sys.path.append('../utils')
from vgg19 import VGG19
import load
import augment
learning_rate = 1e-3
batch_size = 128
def train():
x = tf.placeholder(tf.float32, [None, 96, 96, 3])
t = tf.placeholder(tf.int32, [None])
is_training = tf.placeholder(tf.bool, [])
model = VGG19(x, t, is_training)
sess = tf.Session()
with tf.variable_scope('vgg19'):
global_step = tf.Variable(0, name='global_step', trainable=False)
opt = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = opt.minimize(model.loss, global_step=global_step)
init = tf.global_variables_initializer()
sess.run(init)
# Restore the latest model
if tf.train.get_checkpoint_state('backup/'):
saver = tf.train.Saver()
saver.restore(sess, 'backup/latest')
# Load the dataset
x_train, t_train, x_test, t_test = load.load()
# Train
while True:
epoch = int(sess.run(global_step) / np.ceil(len(x_train)/batch_size)) + 1
print('epoch:', epoch)
perm = np.random.permutation(len(x_train))
x_train = x_train[perm]
t_train = t_train[perm]
sum_loss_value = 0
for i in tqdm(range(0, len(x_train), batch_size)):
x_batch = augment.augment(x_train[i:i+batch_size])
t_batch = t_train[i:i+batch_size]
_, loss_value = sess.run(
[train_op, model.loss],
feed_dict={x: x_batch, t: t_batch, is_training: True})
sum_loss_value += loss_value
print('loss:', sum_loss_value)
saver = tf.train.Saver()
saver.save(sess, 'backup/latest', write_meta_graph=False)
prediction = np.array([])
answer = np.array([])
for i in range(0, len(x_test), batch_size):
x_batch = augment.augment(x_test[i:i+batch_size])
t_batch = t_test[i:i+batch_size]
output = model.out.eval(
feed_dict={x: x_batch, is_training: False}, session=sess)
prediction = np.concatenate([prediction, np.argmax(output, 1)])
answer = np.concatenate([answer, t_batch])
correct_prediction = np.equal(prediction, answer)
accuracy = np.mean(correct_prediction)
print('accuracy:', accuracy)
if name == 'main':
train()
出现ValueError: Trying to share variable vgg19/fc1/weight, but specified shape (4608, 4096) and found shape (180224, 4096).
错误,能修改吗
Running test.py outputs 720x3 size images rather than 720x720x3.
What I did to fix that is to change this line
im = np.uint8(np.clip((img[0]+1)*127.5,0,255.0))
To this:
im = np.uint8(np.clip((img+1)*127.5,0,255.0))
I hope this is the correct fix, it seems to work
I just downloaded the pre-trained weight and tried the code but got this error:
tensorflow.python.framework.errors_impl.NotFoundError: Key generator/conv_m2/weight not found in checkpoint
I wonder how could I solved it.
My environment:
Python 3.6
tensorflow 1.1
Correct me if I'm wrong but I see that you getting the d_loss and doing nothing with it. I mean the it goes like vgg19 >> generator >> output. Is this right?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.