kozistr / esrgan-tensorflow

Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

hey there

Hello! I'm Hyeongchan from Korea. I enjoy programming, working out, and bouldering.

• I'm currently building a ...
• Service many machine learning products in various domains, Audio & Speech, Vision, NLP, Recommendation Systems, and Tabular in many startups.
• Kaggle 2x Expert. the highest competition rank is top 0.1%.
• Here's my C.V. Feel free to contact me at the email [email protected] :)

previously...

• 2021 - 2023 : Joined Viva Republica (Toss). Developed and contributed to many products like BNPL, CSS, OCR, NPS, CDP, and in-house products.
• 2020 - 2021 : Joined Watcha to build a recommendation system with deep learning. Developed deep learning recommender that outperforms the previous algorithm, and contributed to other products like WatchaPedia, in-house applications.
• 2019 - 2020 : Joined Rainist (Banksalad). Developed a transaction classifier service to analyze the categories with low latency, high accuracy, and in real-time.
• 2019 : Joined VoyagerX. Developed a speaker diarization product that automatically recognizes the contents of the meeting.
• - 2019 : offensive security stuffs. Mainly researched and studied Linux kernel exploitation and reverse engineering.

Current Interests

• Kaggle Challenges
• Building something in Rust
• Bouldering

📊 this week i spent my time on:

I'm an Early 🐤

🌞 Morning                1090 commits        ██░░░░░░░░░░░░░░░░░░░░░░░   07.28 % 
🌆 Daytime                6429 commits        ███████████░░░░░░░░░░░░░░   42.95 % 
🌃 Evening                5445 commits        █████████░░░░░░░░░░░░░░░░   36.38 % 
🌙 Night                  2003 commits        ███░░░░░░░░░░░░░░░░░░░░░░   13.38 % 

Last Updated on 14/04/2024 21:25:36 UTC

📈 my github stats

esrgan-tensorflow's Issues

ESRGAN for Godot

I'm the developer of Tensorflow for Godot. https://github.com/godot-extended-libraries/godot-tensorflow-workspace

Do you know how difficult to make this model a Tensorflow2.0alpha lite model?

Error in loss

ESRGAN-tensorflow/losses.py

Lines 8 to 11 in b980f5e

	if use_ra:
	if not loss_func.__contains__("wgan"):
	real = real - tf.reduce_mean(fake)
	fake = fake - tf.reduce_mean(real)

            real = real - tf.reduce_mean(fake)
            fake = fake - tf.reduce_mean(real)

I presume that you want the original real variable and not the relativistic one when calculating fake?

No test code?

Hi, I think i can't find test code here.Could you please release the test code? Thank you!

could you provide pretrained model?

we want to check whether it can reach to pytorch version. could you provide your pretrained models

Is cpu ok?

no train.py, test.py and inference.py

rand_lr_w = (np.random.randint(0, x_hr_shape[0] - self.hr_patch_shape[0]) TypeError: unsupported operand type(s) for -: 'NoneType' and 'int'

Hello,I had some problem

is gpu necessary ?

is gpu necessary to run this or we can train network using cpu also?