Closed DaShenZi721 closed 7 months ago
Hello, thanks for releasing this code.
I'm running the Subject-driven Generation task. After setting i=0 and running ./train_dreambooth_oft.sh $i, I got such directory structure
i=0
./train_dreambooth_oft.sh $i
log_oft ├── backpack-0 │ ├── 0 │ │ ├── image_0.png │ │ ├── image_1.png │ │ ├── ... │ │ └── image_7.png │ ├── 1 │ │ ├── image_0.png │ │ ├── image_1.png │ │ ├── ... │ │ └── image_7.png │ └── ... ...
Then, I run the evaluation script python eval_ablation.py, but the result is dino mean_similarity nan.
python eval_ablation.py
dino mean_similarity nan
I found line 159 in oft-db/eval_ablation.py if re.search(prompt_token, subfolder): didn't match any of the subfolders.
if re.search(prompt_token, subfolder):
What is the use of prompt_token? And Is there a problem with my training process? Looking forward to your reply.
prompt_token
I see.
DaShenZi721
commented
7 months ago DaShenZi721
commented
7 months ago
Hello, thanks for releasing this code.
I'm running the Subject-driven Generation task. After setting
i=0and running./train_dreambooth_oft.sh $i, I got such directory structureThen, I run the evaluation script
python eval_ablation.py, but the result isdino mean_similarity nan.I found line 159 in oft-db/eval_ablation.py
if re.search(prompt_token, subfolder):didn't match any of the subfolders.What is the use of
prompt_token? And Is there a problem with my training process? Looking forward to your reply.