-
Notifications
You must be signed in to change notification settings - Fork 267
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Requirements #23
Comments
Could you specify what error you got? I tested this with TF backend, Keras 2.1.3 and Python 3.5 |
I ran python main.py input_images/testme.jpg and got |
@titu1994 error above |
Open cv is a requirement for this. Try conda install opencv |
@titu1994 Still no luck I reinstalled everything to make sure I'm running correctly: Using TensorFlow backend. CV installed through conda I checked it and it's there. I ran import cv2 |
On Windows, opencv has many problems during installation. It should be import cv2. Even then, there can be some internal import problems from open cv itself. |
@titu1994 Hi I got it working I was having problems with my cv. One file was set to "import cv" once I fixed that it worked. When I scale to 5 it gives this error: File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper running this: python main.py input_images/testme.jpg --scale=5 any ideas? |
That's because there are no pretrained models for scale 5. You'll have to train your own, or pass the scale 2 model 3 (8x scale) times and then downscale. |
I'm confused on this one: model 3. These are the options: python main.py "imgpath" --model="type", where type = sr, esr, dsr, ddsr |
@titu1994 I am having the same issue, as I am new to this I am unable to process your recommendations of March 16 , Thank you so much for uploading source code It helps me understanding a few details. Thank you again for helping. |
Hi is there any doc on requirements? I'm running tensor flow with keras and I get errors on both python 2.7 and python 3.5.
Any help would be appreciated, thank you!
The text was updated successfully, but these errors were encountered: