thelethargicowl / single-image-de-raining-keras Goto Github PK
View Code? Open in Web Editor NEWImplemented Image De-raining Using a Conditional Generative Adversarial Network using Keras
License: MIT License
Implemented Image De-raining Using a Conditional Generative Adversarial Network using Keras
License: MIT License
I am training it on a custom dataset that has about 6000 images. I tried to train it with default parameters like batch_size=1 and used one GPU but the process gets killed after some epochs. Upon searching on the internet I found that this is out of memory issue. When I monitored the process found that the model is using too much RAM. My computer has 32 GBs but models exhaust all. Do you have any suggestions on how to reduce usage?
May be due to the version of libraries. Please provide let me know what version of TensorFlow and Keras worked for you.
TypeError Traceback (most recent call last)
<ipython-input-13-9d2508c65abb> in <module>()
2 gan=IDGAN()
3 ## Train the model
----> 4 gan.train(epochs=150, batch_size=1, sample_interval=25)
10 frames
<ipython-input-11-1eb02c7249cd> in train(self, epochs, batch_size, sample_interval)
214 self.CGAN_model.trainable = True # Train the Combined model
215 self.discriminator.trainable = False
--> 216 g_loss = self.CGAN_model.train_on_batch(imgs_B, [imgs_A,imgs_A,valid])
217
218 elapsed_time = datetime.datetime.now() - start_time
TypeError: in user code:
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:855 train_function *
return step_function(self, iterator)
<ipython-input-9-f7cd4eb02f86>:183 perceptual_loss *
loss_block1 = Model(input=vgg.input, outputs = vgg.get_layer('block1_conv2').output)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py:522 _method_wrapper **
result = method(self, *args, **kwargs)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:268 __init__
'trainable', 'dtype', 'dynamic', 'name', 'autocast', 'inputs', 'outputs'
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/utils/generic_utils.py:1137 validate_kwargs
raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'input')
Adding more to ReadME Doc.
I am getting the following error when i try to execute the code
Traceback (most recent call last):
File "C:\Users......\anaconda3\envs\AI\lib\runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "C:\Users......\anaconda3\envs\AI\lib\runpy.py", line 85, in run_code
exec(code, run_globals)
File "c:\Users......vscode\extensions\ms-python.python-2020.8.108011\pythonFiles\lib\python\debugpy_main.py", line 45, in
cli.main()
File "c:\Users......vscode\extensions\ms-python.python-2020.8.108011\pythonFiles\lib\python\debugpy/..\debugpy\server\cli.py", line 430, in main
run()
File "c:\Users.......vscode\extensions\ms-python.python-2020.8.108011\pythonFiles\lib\python\debugpy/..\debugpy\server\cli.py", line 267, in run_file
runpy.run_path(options.target, run_name=compat.force_str("main"))
File "C:\Users.......\anaconda3\envs\AI\lib\runpy.py", line 261, in run_path
code, fname = _get_code_from_file(run_name, path_name)
File "C:\Users.......\anaconda3\envs\AI\lib\runpy.py", line 236, in _get_code_from_file
code = compile(f.read(), fname, 'exec')
File "d:\Single-Image-De-Raining-Keras-master\ID-CGAN.py", line 323
img_b = np.array([img_B])/127.5 - 1
^
SyntaxError: invalid syntax
hello, your google link cannot be accessed. How do i get the file of 'gen_model.h5?' i would appreciate it if you can help me
There is an undefined variable in line 219.
Hello, thank you for your work!
Can you share the pre-trained weights so that I can run a quick demo before training the network?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.