Xander Steenbrugge

icon indicating a website link http://eden.art/ icon indicating an email [email protected]

icon company co-Founder Eden.art icon location Ghent, Belgium

Results 20 comments of Xander Steenbrugge

create web directory ./checkpoints/target/web... End of epoch 1 / 40 Time Taken: 898 sec Traceback (most recent call last): File "train_pose2vid.py", line 127, in <module> main() File "train_pose2vid.py", line 84, in main errors = {k: v.data[0] if not isinstance(v, int) else v for k, v in loss_dict.items()} File "train_pose2vid.py", line 84, in <dictcomp> errors = {k: v.data[0] if not isinstance(v, int) else v for k, v in loss_dict.items()} IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Did anybody find the quick-fix for this? Having the same error

create web directory ./checkpoints/target/web... End of epoch 1 / 40 Time Taken: 898 sec Traceback (most recent call last): File "train_pose2vid.py", line 127, in <module> main() File "train_pose2vid.py", line 84, in main errors = {k: v.data[0] if not isinstance(v, int) else v for k, v in loss_dict.items()} File "train_pose2vid.py", line 84, in <dictcomp> errors = {k: v.data[0] if not isinstance(v, int) else v for k, v in loss_dict.items()} IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Ait so aparantly, batch_size is set to 1 in src/config/train_opt.py, therefore v.data[0] does not work and you have to: - Either set the batch_size to a value different from 1...

The wrong dimension in discriminator function

Had the same bug, thx for posting, didn't feel like debugging dimension mismatches today ;p

The wrong dimension in discriminator function

One extra thing: for people that are running Linux on Windows 10 (using developer mode): To be able to execute the show_result function you can install something like [Xming ](https://sourceforge.net/projects/xming/)and...

correlation with Facebook ESM's log_likelihood

@avilella I was wondering if you have any further updates on this as I've been trying to do similar stuff (see [here](https://github.com/salesforce/progen/issues/7)). In my personal experiments, using the LM to...

correlation with Facebook ESM's log_likelihood

The weirdest result for me so far is that, if you keep sampling the "most likely" mutations at randomly sampled indices, you eventually end up with sequences that look very...

correlation with Facebook ESM's log_likelihood

This [example script](https://storage.googleapis.com/public-assets-xander/Random/remove/ML_guided_sequence_mutation.py) shows the explained behavior (just put in base progen dir and run from terminal): start from a random init seq and then: - sample a random residue...

This and BirdNET-Pi

You're very welcome, glad you find it valuable :)

Show problems

Other people have also replied that the GUI does not show on Mac/Windows... (You can still use the live FFT features in headless mode though, just set the visualize flag...

Unable to use create_from_images_raw in training

Minimal code to reproduce this error: ``` import tensorflow as tf import cv2 import numpy as np shape = (3, 1024, 1024) img = np.random.random((1024, 1024,3)) * 255 img =...