🐞 <title>engine = Engine(max_epochs=10) is not work？？？

[wyk-study]

Describe the bug

set like this：engine = Engine(max_epochs=10)
still train 1 epoch

Dataset

N/A

Model

N/A

Steps to reproduce the behavior

all package is well done. but i con't change the max_epoch??

OS information

OS information:

• OS: [e.g. Ubuntu 20.04]
• Python version: [e.g. 3.10.0]
• Anomalib version: [e.g. 0.3.6]
• PyTorch version: [e.g. 1.9.0]
• CUDA/cuDNN version: [e.g. 11.1]
• GPU models and configuration: [e.g. 2x GeForce RTX 3090]
• Any other relevant information: [e.g. I'm using a custom dataset]

Expected behavior

change max_epoch

Screenshots

No response

Pip/GitHub

pip

What version/branch did you use?

2.1.0

Configuration YAML

none

Logs

from anomalib.models import Patchcore
from anomalib.engine import Engine
from anomalib.data import Folder
import torch

# 创建数据模块
datamodule = Folder(
    name="OCT",
    root="Dataset_Denoise/train",
    normal_dir="normal",
    abnormal_dir="abnormal",
)
datamodule.setup()

# 初始化模型
model = Patchcore()

# 初始化Engine时通过trainer_kwargs传递所有训练参数
engine = Engine(max_epochs=10)

# 训练模型
engine.fit(datamodule=datamodule, model=model)

output:

  | Name           | Type           | Params | Mode 
----------------------------------------------------------
0 | pre_processor  | PreProcessor   | 0      | train
1 | post_processor | PostProcessor  | 0      | train
2 | evaluator      | Evaluator      | 0      | train
3 | model          | PatchcoreModel | 24.9 M | train
----------------------------------------------------------
24.9 M    Trainable params
0         Non-trainable params
24.9 M    Total params
99.450    Total estimated model params size (MB)
19        Modules in train mode
174       Modules in eval mode
Selecting Coreset Indices.: 100%|████████████████| 15257/15257 [00:11<00:00, 1316.54it/s]
Epoch 0: 100%|█████████████████████████████████████████████████| 5/5 [00:14<00:00,  0.33it/s]`Trainer.fit` stopped: `max_epochs=1` reached.                                               
Epoch 0: 100%|█████████████████████████████████████████████████| 5/5 [00:15<00:00,  0.32it/s]
(OOD) wyk@bly-SYS-741GE-TNRT:~/OOD$

Code of Conduct

• I agree to follow this project's Code of Conduct

[github-actions[bot]]

Thanks for submitting this issue! It has been added to our triage queue. A maintainer will review it shortly.

[rajeshgangireddy]

Hi @wyk-study
PatchCore does not use epochs.
During the "training phase", it extracts features once for all the normal images. There is no loss computation involved.
Please read the readme.md of patchcore model for a summary : https://github.com/open-edge-platform/anomalib/blob/main/src/anomalib/models/image/patchcore/README.md