mkeid
Style transfer algo gpu
Sure we can make it configurable. I just was making it specific to what I was doing. I'm new to this Tensorflow stuff so I have been just trying to figure out the code.
I want to use this with my NVIDIA gpu and also be able to set the quality of the image - such as turning off compression among other things.
I like your results. Great job!
On Thu, Sep 23, 2021 at 1:10 AM Mo @.***> wrote:
@.**** commented on this pull request.
In src/utilsV2.py https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#discussion_r714475061 :
if save:
Image.fromarray(np.reshape(img, shape[1:])).save(out_path)
Image.fromarray(np.reshape(img, shape[1:])).resize((1200, 1200)).save(out_path)Why are we resizing to 1200x1200? If this is arbitrary, can we make this configurable via flag arg?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#pullrequestreview-761594250, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACZ3XKJP4L6QKCF5BT6PLELUDKZDFANCNFSM5ESO7KEA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
Can you give me insight into what parameters/variables affect the outcome of the model? Point me in the right direction if you have the time....
thanks
On Thu, Sep 23, 2021 at 1:38 PM Joao Brasil @.***> wrote:
Sure we can make it configurable. I just was making it specific to what I was doing. I'm new to this Tensorflow stuff so I have been just trying to figure out the code.
I want to use this with my NVIDIA gpu and also be able to set the quality of the image - such as turning off compression among other things.
I like your results. Great job!
On Thu, Sep 23, 2021 at 1:10 AM Mo @.***> wrote:
@.**** commented on this pull request.
In src/utilsV2.py https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#discussion_r714475061 :
if save:
Image.fromarray(np.reshape(img, shape[1:])).save(out_path)
Image.fromarray(np.reshape(img, shape[1:])).resize((1200, 1200)).save(out_path)Why are we resizing to 1200x1200? If this is arbitrary, can we make this configurable via flag arg?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#pullrequestreview-761594250, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACZ3XKJP4L6QKCF5BT6PLELUDKZDFANCNFSM5ESO7KEA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
I see the parameters but I was just wondering from your experience what they do to the results?
Also, have you run this using tensorflow-gpu?
On Thu, Sep 23, 2021 at 4:59 PM Joao Brasil @.***> wrote:
Can you give me insight into what parameters/variables affect the outcome of the model? Point me in the right direction if you have the time....
thanks
On Thu, Sep 23, 2021 at 1:38 PM Joao Brasil @.***> wrote:
Sure we can make it configurable. I just was making it specific to what I was doing. I'm new to this Tensorflow stuff so I have been just trying to figure out the code.
I want to use this with my NVIDIA gpu and also be able to set the quality of the image - such as turning off compression among other things.
I like your results. Great job!
On Thu, Sep 23, 2021 at 1:10 AM Mo @.***> wrote:
@.**** commented on this pull request.
In src/utilsV2.py https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#discussion_r714475061 :
if save:
Image.fromarray(np.reshape(img, shape[1:])).save(out_path)
Image.fromarray(np.reshape(img, shape[1:])).resize((1200, 1200)).save(out_path)Why are we resizing to 1200x1200? If this is arbitrary, can we make this configurable via flag arg?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#pullrequestreview-761594250, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACZ3XKJP4L6QKCF5BT6PLELUDKZDFANCNFSM5ESO7KEA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
I cannot get this to run with GPU support? Is there something in this repository code that specifies CPU only?
On Thu, Sep 23, 2021 at 5:23 PM Joao Brasil @.***> wrote:
I see the parameters but I was just wondering from your experience what they do to the results?
Also, have you run this using tensorflow-gpu?
On Thu, Sep 23, 2021 at 4:59 PM Joao Brasil @.***> wrote:
Can you give me insight into what parameters/variables affect the outcome of the model? Point me in the right direction if you have the time....
thanks
On Thu, Sep 23, 2021 at 1:38 PM Joao Brasil @.***> wrote:
Sure we can make it configurable. I just was making it specific to what I was doing. I'm new to this Tensorflow stuff so I have been just trying to figure out the code.
I want to use this with my NVIDIA gpu and also be able to set the quality of the image - such as turning off compression among other things.
I like your results. Great job!
On Thu, Sep 23, 2021 at 1:10 AM Mo @.***> wrote:
@.**** commented on this pull request.
In src/utilsV2.py https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#discussion_r714475061 :
if save:
Image.fromarray(np.reshape(img, shape[1:])).save(out_path)
Image.fromarray(np.reshape(img, shape[1:])).resize((1200, 1200)).save(out_path)Why are we resizing to 1200x1200? If this is arbitrary, can we make this configurable via flag arg?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/mohamedkeid/Style-Transfer-Algorithm/pull/6#pullrequestreview-761594250, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACZ3XKJP4L6QKCF5BT6PLELUDKZDFANCNFSM5ESO7KEA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.