Efficient AD train_batch_size problem

[Balporsugu21]

from anomalib.data import MVTec
from anomalib.models import EfficientAd
from anomalib.engine import Engine
from anomalib.models import Ganomaly
from anomalib.utils.normalization import NormalizationMethod
from anomalib.data import Folder
from anomalib.data.image.folder import FolderDataset
from anomalib.metrics import F1Score
from anomalib import TaskType

datamodule = MVTec()
model = EfficientAd()

engine = Engine(
normalization=NormalizationMethod.MIN_MAX,
threshold="F1AdaptiveThreshold",
task=TaskType.CLASSIFICATION,

accelerator="auto",
check_val_every_n_epoch=1,
limit_train_batches=1.0,
limit_val_batches=1.0,
limit_test_batches=1.0,
precision=32,
log_every_n_steps=20,
devices=1,
max_epochs=10,
num_sanity_val_steps=0,
val_check_interval=1.0,

)
engine.fit(datamodule=datamodule, model=model)

test_results = engine.test(
model=model,
datamodule=datamodule,
ckpt_path=engine.trainer.checkpoint_callback.best_model_path,
)
After writing this code, I get this error. What should I do?

ValueError: train_batch_size for EfficientAd should be 1.

[alexriedel1]

datamodule = MVTec(train_batch_size=1)

[alexriedel1]

Can you show the full error log and your full code?

[Balporsugu21]

Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/tqdm/std.py", line 1148, in del
self.close()
File "/usr/local/lib/python3.10/dist-packages/tqdm/std.py", line 1277, in close
if self.last_print_t < self.start_t + self.delay:
AttributeError: 'DownloadProgressBar' object has no attribute 'last_print_t'

RecursionError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/rich/console.py in print(self, sep, end, style, justify, overflow, no_wrap, emoji, markup, highlight, width, height, crop, soft_wrap, new_line_start, *objects)
1673 with self:
-> 1674 renderables = self._collect_renderables(
1675 objects,

37 frames
RecursionError: maximum recursion depth exceeded while calling a Python object

During handling of the above exception, another exception occurred:

RecursionError Traceback (most recent call last)
... last 10 frames repeated, from the frame below ...

/usr/local/lib/python3.10/dist-packages/rich/file_proxy.py in flush(self)
51 output = "".join(self.__buffer)
52 if output:
---> 53 self.__console.print(output)
54 del self.__buffer[:]
55

RecursionError: maximum recursion depth exceeded while calling a Python objcet. my full code. Link to my entire code: https://colab.research.google.com/drive/1VXajUhaZn88bur0ppDmLDuqxga8MT-8K#scrollTo=3Fvrqd2CbWpZ

[Balporsugu21]

I got the same error on the Cfa model

[alexriedel1]

Yeah you are probably using anomalib in a jupyter notebook? The issue is known #2145 and for now you would have to build yourself a workaround

[Balporsugu21]

Yeah you are probably using anomalib in a jupyter notebook? The issue is known #2145 and for now you would have to build yourself a workaround

I use Anomalybi from Google Colab. I was able to run it 3 months ago, but unfortunately it doesn't work now. What can I do? This is the colab link to run it. https://colab.research.google.com/drive/1VXajUhaZn88bur0ppDmLDuqxga8MT-8K#scrollTo=xTUkvyUbbapC