Alexander Suslov commited on
Commit
351ee24
β€’
1 Parent(s): e983036

typo: sftmp -> stfpm

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  license: apache-2.0
3
  ---
4
- [SFTPM](https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/stfpm) model from [Anomalib](https://github.com/openvinotoolkit/anomalib) fine-tuned for capsule category of the [MVTec dataset](https://www.mvtec.com/company/research/datasets/mvtec-ad). Checkpoint trained using the following [notebook](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/000_getting_started/001_getting_started.ipynb).
5
 
6
  ```
7
  ──────────────────────────────────────────────────
@@ -16,7 +16,7 @@ license: apache-2.0
16
 
17
  The main intent is to use it in samples and demos for model optimization. Here is the advantages:
18
  - MVTec dataset can automatically downloaded and is quite small.
19
- - The model from the anomaly detection domain such as SFTPM is sensitive to the optimization methods to allows demonstrate methods with accuracy controll.
20
 
21
  Here is the code to test the checkpoint:
22
 
@@ -32,7 +32,7 @@ CHECKPOINT_PATH = '~/pytorch_model.bin'
32
 
33
  #Download CHECKPOINT_URL to CHECKPOINT_PATH
34
 
35
- config = get_configurable_parameters(config_path="./anomalib/models/sftpm/config.yaml")
36
  config["dataset"]["path"] = <path_to_dataset>
37
  config['dataset']['category'] = 'capsule'
38
 
@@ -48,4 +48,4 @@ callbacks.insert(0, load_model_callback)
48
 
49
  trainer = Trainer(**config.trainer, callbacks=callbacks)
50
  trainer.test(model=model, datamodule=datamodule)
51
- ```
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+ [STFPM](https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/stfpm) model from [Anomalib](https://github.com/openvinotoolkit/anomalib) fine-tuned for capsule category of the [MVTec dataset](https://www.mvtec.com/company/research/datasets/mvtec-ad). Checkpoint trained using the following [notebook](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/000_getting_started/001_getting_started.ipynb).
5
 
6
  ```
7
  ──────────────────────────────────────────────────
 
16
 
17
  The main intent is to use it in samples and demos for model optimization. Here is the advantages:
18
  - MVTec dataset can automatically downloaded and is quite small.
19
+ - The model from the anomaly detection domain such as STFPM is sensitive to the optimization methods to allows demonstrate methods with accuracy controll.
20
 
21
  Here is the code to test the checkpoint:
22
 
 
32
 
33
  #Download CHECKPOINT_URL to CHECKPOINT_PATH
34
 
35
+ config = get_configurable_parameters(config_path="./anomalib/models/stfpm/config.yaml")
36
  config["dataset"]["path"] = <path_to_dataset>
37
  config['dataset']['category'] = 'capsule'
38
 
 
48
 
49
  trainer = Trainer(**config.trainer, callbacks=callbacks)
50
  trainer.test(model=model, datamodule=datamodule)
51
+ ```
openvino_model.tar CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f48fa14e47dbbc1684d4ae68c16c035bb221b09d06d3e33475862ce2aa7e247f
3
  size 22374400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f34de5901584a8fa14dd1ed9814d37aa2b23896a5af6f8578590b9501b753d
3
  size 22374400
sftpm_capsule.onnx β†’ stfpm_capsule.onnx RENAMED
File without changes