meta-prompts

meta-prompts copied to clipboard

ValueError

3

I followed up all the instruction as it has been written. I am trying to run the segmentation part of the model in 1 GPU; unfortunately, unlike the depth I...

mnazari123

Faced some errors in validation part.

3

Faced some errors in validation part. ``` Traceback (most recent call last): File "train.py", line 432, in main() File "train.py", line 173, in main results_dict, loss_val = validate(val_loader, model, criterion_d,...

LT1st

could you share the environments you used? for instance, the spec of hardware, cuda, cudnn, and so on.

k-jh623

您好 请问八卡跑ade20k训练80k大概要多长时间

1

yan-hao-tian

Some questions on the paper

3

1. Why do the features and the meta prompts share the same D? Meta prompts need to have the same dimension as ordinary text encoder embeddings, but the dimension of...

Darkbblue

Nan loss on the half way to train the model.

2

I am using your framework on image translation task. The loss was fine at the very begining, but was changed into **Nan** in Epoch 006. Have you ever solved this...

LT1st

May I ask how much VRAM is required to train the segmentation model?

3

I tried this model with 3080TI, but I've faced OOM problem. Even with 3080TI with 3060TI with Deepspeed + zero 3 approach, I've faced OOM issue again. So how much...

JKL-uxf

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.

2

This error appeared when I was running `sh install.sh`, which are ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is...

EDGE-qy