saafke / edsr_tensorflow Goto Github PK

Hi There,
I am trying to use your code to test up-scaling of a cropped image. i am on anaconda python 3.5 cuda 10 cudnn 7.4 with tensorflow-gpu==1.15.0. I am getting. can you help to identify the exact version or procedure that i have to use?

Traceback (most recent call last):
File "main_1.py", line 73, in
run.upscaleFromPb(args.image)
File "C:\Users\ASUS\Downloads\EDSR_Tensorflow-master\EDSR_Tensorflow-master\run.py", line 298, in upscaleFromPb
output = sess.run(HR_tensor, feed_dict={LR_tensor: LR_input_})
File "C:\Users\ASUS\Anaconda3\envs\tengpu\lib\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "C:\Users\ASUS\Anaconda3\envs\tengpu\lib\site-packages\tensorflow_core\python\client\session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\ASUS\Anaconda3\envs\tengpu\lib\site-packages\tensorflow_core\python\client\session.py", line 1359, in _do_run
run_metadata)
File "C:\Users\ASUS\Anaconda3\envs\tengpu\lib\site-packages\tensorflow_core\python\client\session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'Dequantize' used by node resFilter_three (defined at C:\Users\ASUS\Anaconda3\envs\tengpu\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) with these attrs: [mode="MIN_FIRST", T=DT_QUINT8]
Registered devices: [CPU, GPU]
Registered kernels:

     [[resFilter_three]]

Originally posted by @seli07 in #1 (comment)

It doesn't work for me with Python 3.9 on macOS.

First, the following packages are required:
• pillow
• scikit-image
• tensorflow-transform
but even with that, I get the error 'ModuleNotFoundError: No module named 'tensorflow.tools.graph_transforms'

Hi! I'm very glad to read your codes, but I have a problem, that is how to test my test_file after training.
as you know, Testing a single image in your code.

Especially these two lines of code, if there is a folder test picture, is it necessary to change？

LR_tensor = graph_def.get_tensor_by_name("IteratorGetNext:0")
HR_tensor = graph_def.get_tensor_by_name("NHWC_output:0")

Thanks!

python main.py --upscale --scale 4 --image FILEPATH

Traceback (most recent call last):
  File "/home/mb/scripts/EDSR_Tensorflow/main.py", line 3, in <module>
    import run
  File "/home/mb/scripts/EDSR_Tensorflow/run.py", line 13, in <module>
    from tensorflow.tools.graph_transforms import TransformGraph
ModuleNotFoundError: No module named 'tensorflow.tools.graph_transforms'

I'm Manjaro, and Tensorflow 2.5

Thanks for sharing the code. I'm studying with you code.
I try to run the model with my dataset, but the number of steps only increases to 51. When I train the DVI2K dataset, it goes up to over 10000 steps. What should I do?
I modified the main.py file by calculating the calcmean in the data_utils.py.
In my data set, the images are 158 x 158. Is the number of steps not going up because of this? If so, should line 104 of run.py be modified differently? line 104 is (step% 1000 = : 0). should I change the number 1000 to 10?
Please help me.

Hi! I have the last problem, I can't find the valid dataset, could you please tell me, how working when running the train code?
Thanks!

Hi,
I was using your code to test up-scaling of some png or jpeg images and I got this issue below.
Traceback (most recent call last):
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call
return fn(*args)
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1348, in _run_fn
self._extend_graph()
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1388, in _extend_graph
tf_session.ExtendSession(self._session)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'Dequantize' used by {{node resFilter_three}}with these attrs: [mode="MIN_FIRST", T=DT_QUINT8]
Registered devices: [CPU, GPU]
Registered kernels:

     [[resFilter_three]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 71, in
run.testFromPb(args.image)
File "***\Python\VSR\EDSR_Tensorflow-master\run.py", line 253, in testFromPb
output = sess.run(HR_tensor, feed_dict={LR_tensor: LR_input_})
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1359, in _do_run
run_metadata)
File "###\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\client\session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'Dequantize' used by node resFilter_three (defined at E:\Applications\anaconda3\envs\tensorflow\lib\site-packages\tensorflow_core\python\framework\ops.py:1748) with these attrs: [mode="MIN_FIRST", T=DT_QUINT8]
Registered devices: [CPU, GPU]
Registered kernels:

     [[resFilter_three]] 

I'm on windows 10, using vs2019, suda 11.0 anaconda 3 and a specially created py 3.7.11 with tensorflow-gpu 1.15.0 for this project.

It's quite weird. Or say even mysterious to me now. 'cause in the same VS project I tested your fsrcnn codes and it ran successfully. Same OpError happened before to fsrcnn and I downgraded cuda to 10.0 as some suggested, which didn't help. So later I changed back to cuda 11.0 and fsrcnn went well. When I tried EDSR I met this

Hi,
I hope you're fine.
We have tried to apply your Super-Resolution models on our own images; however, it seems we missed prototxt files.
Could you please kindly let me know how I can find the prototxt file for the ".pb" files.

Hello my friend,
Your project is so helpful.i have got many ideas from the way you have written it.I would want to ask you some questions.When we find the mean rgb value of div2k dataset , are we using the Low resolution images of train dataset(800 images) or are we using the low resolution images of train,validation and testing to find the mean rgb value(all the low resolution images of the dataset)?This mean value is this value we must subtract from our data when we pass them in the network

Hi
I am not sure you are familiar with Deephi Tools which is doing quantization.
But this makes below error when I compile your code to use Alveo Card( from Xilinx )

Traceback (most recent call last):
File "run.py", line 130, in
**get_default_compiler_args()
File "/opt/ml-suite/xfdnn/rt/xdnn_rt_tf.py", line 50, in init
super(TFxdnnRT, self).init(TFFrontend, args, **kwargs)
File "/opt/ml-suite/xfdnn/rt/xdnn_rt_base.py", line 212, in init
= compiler.compile()
File "./xfdnn/tools/compile/bin/xfdnn_compiler_tensorflow.py", line 191, in compile
File "./xfdnn/tools/compile/network/tensor_tools.py", line 2007, in from_tfgraph_to_fpga_code
File "./xfdnn/tools/compile/bin/xfdnn_compiler_base.py", line 729, in GraphMassage
File "./xfdnn/tools/compile/graph/dagtools.py", line 3667, in convert_offline
File "./xfdnn/tools/compile/quantz/deephi_quant_info.py", line 556, in process
TypeError: unsupported operand type(s) for /: 'float' and 'NoneType'

Do you have any idea how to solve this issue?

FYI. We are using this code to compare performance of Alveo vs nVidia GPU.

Hi again Saafke,
i wanted to ask you how much memory you have spent for storing the sub-images in the train dataset .When are you do the training process the amount of memory is raising?