KyonP

error during Visualizing attention in tutorial

1

I'm tutorial myself with your seq2seq tutorial code. error pop out this lines `output_words, attentions = evaluate("je suis trop froid .") plt.matshow(attentions.numpy())` `--------------------------------------------------------------------------- KeyError Traceback (most recent call last) in...

trying to follow the nmt tutorial, cannot run the training step

12

I'm following the tutorial (https://google.github.io/seq2seq/nmt/), but can't run the code. Actually, I'm not understanding the code explained in the tutorial. Do I have to type all those arguments in the...

can this code be used for finetuning?

1

I am trying to train stable-diffusion models for my custom text2img dataset. Still struggling to fit into my 3090 24GB VRAM; maybe this code is the solution. Example config YAML...

.half call to fix?

2

I am sorry that I cannot provide my python Traceback log (already reverted my code, sadly). I was trying to update my previous code based on SD v1, I faced...

UnpicklingError from ffhq config file

6

I was following the instructions for training the FFHQ dataset. And I've faced this error ``` (ldm) user99@fd5a72f3f***:/home/user99/stable-diffusion# CUDA_VISIBLE_DEVICES=0 python main.py --base configs/latent-diffusion/ffhq-ldm-vq-4.yaml -t --gpus 0 Global seed set to...

I am trying to finetune the code with my custom dataset (50000 images with text descriptions). and it stops during the training phase. It seems it happens whenever the code...

Hello, I hope your research goes well. 😀 I am trying to evaluate the metrics that you proposed for my model. I have read your paper. However, I am asking...

best performing pretrained weight

3

To author, First of all, on behalf of our lab member who published the original Pororo dataset (K.M. Kim), we very much appreciated that this dataset is still alive and...

PrefixTuningDalle not exist

4

I am trying to gather generated images from your best-performing checkpoint, and I faced this error. ``` (ldm) root@2157b047841c:/home/my/storydalle/story-dalle# bash infer_story.sh pororo Evaluating on Pororo ╭─────────────────────────────── Traceback (most recent call...

resulting checkpoint can be compatible with clip.load()?

1

This repo greatly helped my finetuning process. Thanks. I am wondering if these resulting checkpoints, which are produced by this code in `lightning_logs/version_#/checkpoints/~~~.ckpt,` are compatible with `clip.load`? I could `torch.load`...