-
This is an exciting work! When I follow the process to reproduce the code, I encounter the error:“/home/zh/anaconda3/envs/DHD1/lib/python3.8/site-packages/mmcv/ops/deform_conv.py", line 92, in forward…
-
Dear Dr.Song:
Hi! Thanks for your contribution. I'm trying to load your dataset and make (prob.map, facies models) as pairs to serve as training data . But after visulization, I found that the data i…
-
MCProb for 1D Michalewicz seems to return 0 for all candidates in certain situations.
Attaching the MWE.
```python
import sys
import random
from typing import Tuple
import numpy as np
import …
-
When I use the dips database for training, the run.py script reports an error: IndexError: too many indices for tensor of dimension 2.The position of the pt file obtained by gen_dips_datasets.py has o…
-
Hello, I very appreciate your work and try to train it on my own datas. But I get a confusion in Dataset process as follow:
 -> Result {
let cifar = candle_datasets::vision::cifar::load()?;
dbg!(&cifar.train_images); // Tensor[dims 50000, 3, 32, 32; u8]
dbg!(&cifar.train_labels); // Tenso…
-
Hi, I am using deepspeed zero3 to fine tune flux model using the script - flux_train_network.py.
```
flux = accelerator.unwrap_model(flux)
print(f"flux - {flux.state_dict()['single_blocks.7.linea…
-
### What happened?
It appears that somewhere between d7a4e73 and 13dbd21, masked training for Flux has stopped working when it tries to perform training steps (after initial sampling). Reverting back…
-
Hello, I just ran the program and entered my wandb API key, and the program stopped. From the error, the program seems to refuse to use 4D tensors, do you know where the problem is?
```
Passwo…
-
### System Info
`transformers` version 4.47.0.dev0
`accelerate` version 0.34.2
`timm` version 1.0.11
`supervision` version 0.25.0rc2
### Who can help?
@muellerzr @Arth
### Information
- [ …