@@ -161,7 +161,6 @@ To enable the auto-downloading, set the parameter `--is_auto_download` (default:
161
161
### 5. Run the training script (for the development dataset)
162
162
163
163
Run the training script ` 01_train_2025t2.sh ` . Use the option -d for the development dataset ` data/dcase2025t2/dev_data/<machine_type>/raw/train/ ` .
164
- ` 01_train_2025t2.sh ` differs from ` 01_train_2025t2.sh ` only in dataset;
165
164
166
165
``` dotnetcli
167
166
# using DCASE2025 Task 2 Datasets
@@ -174,7 +173,6 @@ After the parameter update of the Autoencoder at the last epoch specified by eit
174
173
175
174
### 6.1. Testing with the Simple Autoencoder mode
176
175
Run the test script ` 02a_test_2025t2.sh ` . Use the option ` -d ` for the development dataset ` data/dcase2025t2/dev_data/<machine_type>/raw/test/ ` .
177
- ` 02a_test_2025t2.sh ` differs from ` 02a_test_2023t2.sh ` only in dataset;
178
176
179
177
``` dotnetcli
180
178
# using DCASE2025 Task 2 Datasets
@@ -187,7 +185,6 @@ A CSV file for each section, including the anomaly scores, will be stored in the
187
185
188
186
### 6.2. Testing with the Selective Mahalanobis mode
189
187
Run the test script ` 02b_test_2025t2.sh ` . Use the option ` -d ` for the development dataset ` data/dcase2025t2/dev_data/<machine_type>/raw/test/ ` .
190
- ` 02b_test_2025t2.sh ` differs from ` 02b_test_2023t2.sh ` only in dataset;
191
188
192
189
``` dotnetcli
193
190
# using DCASE2025 Task 2 Datasets
@@ -316,6 +313,14 @@ We developed and tested the source code on Ubuntu 22.04.5 LTS.
316
313
- fasteners >= 0.19
317
314
318
315
## Change Log
316
+
317
+ ### [ 4.0.1] ( https://github.com/nttcslab/dcase2023_task2_baseline_ae/releases/tag/v4.0.1 )
318
+
319
+ #### Previous DCASE Task2 scripts have been moved into legacy
320
+
321
+ - The DCASE2023 and DCASE2024 scripts have been removed from the top directory.
322
+ - You can continue to use the DCASE2020 through DCASE2024 scripts by using the scripts in the legacy directory.
323
+
319
324
### [ 4.0.0] ( https://github.com/nttcslab/dcase2023_task2_baseline_ae/releases/tag/v4.0.0 )
320
325
321
326
#### Added
0 commit comments