scortexio / patchcore-few-shot Goto Github PK
View Code? Open in Web Editor NEWImplementation of our paper "Optimizing PatchCore for Few/many-shot Anomaly Detection"
Home Page: https://arxiv.org/abs/2307.10792
Implementation of our paper "Optimizing PatchCore for Few/many-shot Anomaly Detection"
Home Page: https://arxiv.org/abs/2307.10792
I encountered issues when running run_shot_study_mvtec_coreset_augmentations.sh
. Any suggestion?
k-shot: 1
run: 0
category: bottle
Loading model antialiased_wide_resnet50_2 from antialias_cnn
Traceback (most recent call last):
File "scripts/few_shot_training.py", line 304, in <module>
train()
File "scripts/few_shot_training.py", line 284, in train
train_step(
File "scripts/few_shot_training.py", line 91, in train_step
model = get_model(config)
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/__init__.py", line 65, in get_model
model = getattr(module, f"{_snake_to_pascal_case(config.model.name)}Lightning")(config)
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/lightning_model.py", line 131, in __init__
super().__init__(
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/lightning_model.py", line 49, in __init__
self.model: PatchcoreModel = PatchcoreModel(
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/torch_model.py", line 62, in __init__
model = antialiased_cnns.wide_resnet50_2(pretrained=True)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/antialiased_cnns/resnet.py", line 406, in wide_resnet50_2
model.load_state_dict(model_zoo.load_url(model_urls['wide_resnet50_2_lpf4_finetune'], map_location='cpu', check_hash=True)['state_dict'])
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/torch/hub.py", line 766, in load_state_dict_from_url
download_url_to_file(url, cached_file, hash_prefix, progress=progress)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/torch/hub.py", line 620, in download_url_to_file
u = urlopen(req)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 531, in open
response = meth(req, response)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 640, in http_response
response = self.parent.error(
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 569, in error
return self._call_chain(*args)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 502, in _call_chain
result = func(*args)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 649, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden
/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/config/config.py:304: UserWarning: The seed value is now fixed to 0. Up to v0.3.7, the seed was not fixed when the seed value was set to 0. If you want to use the random seed, please select `None` for the seed value (`null` in the YAML file) or remove the `seed` key from the YAML file.
warn(
Global seed set to 0
2024-01-17 01:48:34,202 - anomalib - INFO - Doing category: bottle
2024-01-17 01:48:34,203 - anomalib.data - INFO - Loading the datamodule
2024-01-17 01:48:34,203 - anomalib.data.utils.transform - INFO - No config file has been provided. Using default transforms.
2024-01-17 01:48:34,203 - anomalib.data.utils.transform - INFO - No config file has been provided. Using default transforms.
2024-01-17 01:48:34,203 - anomalib.data.mvtec - INFO - Found the dataset.
2024-01-17 01:48:34,253 - anomalib - INFO - Training on 1 examples
2024-01-17 01:48:34,253 - anomalib - INFO - path split ... label_index mask_path
0 datasets/mvtec/bottle train ... 0
[1 rows x 6 columns]
2024-01-17 01:48:34,259 - anomalib.models - INFO - Loading the model.
2024-01-17 01:48:34,260 - anomalib.models.components.base.anomaly_module - INFO - Initializing PatchcoreLightning model.
/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/torchmetrics/utilities/prints.py:36: UserWarning: Metric `PrecisionRecallCurve` will save all targets and predictions in buffer. For large datasets this may lead to large memory footprint.
warnings.warn(*args, **kwargs)
Downloading: "https://antialiased-cnns.s3.us-east-2.amazonaws.com/weights_v0.1/wide_resnet50_2_lpf4_finetune-02a183f7.pth" to /home/tslab/longfei/.cache/torch/hub/checkpoints/wide_resnet50_2_lpf4_finetune-02a183f7.pth
[16, 4, 4, 1, 1]
[None, None, None, None, None]
k-shot: 1
run: 0
category: bottle
Loading model antialiased_wide_resnet50_2 from antialias_cnn
Traceback (most recent call last):
File "scripts/few_shot_training.py", line 304, in <module>
train()
File "scripts/few_shot_training.py", line 284, in train
train_step(
File "scripts/few_shot_training.py", line 91, in train_step
model = get_model(config)
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/__init__.py", line 65, in get_model
model = getattr(module, f"{_snake_to_pascal_case(config.model.name)}Lightning")(config)
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/lightning_model.py", line 131, in __init__
super().__init__(
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/lightning_model.py", line 49, in __init__
self.model: PatchcoreModel = PatchcoreModel(
File "/net/papilio/storage5/nedo-otsl/longfei/patchcore-few-shot/src/anomalib/models/patchcore/torch_model.py", line 62, in __init__
model = antialiased_cnns.wide_resnet50_2(pretrained=True)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/antialiased_cnns/resnet.py", line 406, in wide_resnet50_2
model.load_state_dict(model_zoo.load_url(model_urls['wide_resnet50_2_lpf4_finetune'], map_location='cpu', check_hash=True)['state_dict'])
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/torch/hub.py", line 766, in load_state_dict_from_url
download_url_to_file(url, cached_file, hash_prefix, progress=progress)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/site-packages/torch/hub.py", line 620, in download_url_to_file
u = urlopen(req)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 531, in open
response = meth(req, response)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 640, in http_response
response = self.parent.error(
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 569, in error
return self._call_chain(*args)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 502, in _call_chain
result = func(*args)
File "/net/papilio/storage6/longfei/anaconda3/envs/nedo-fewshot/lib/python3.8/urllib/request.py", line 649, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden
(image-auroc+px-auroc)/2= AUHPROC ?
It doesn't seem like that.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.