Is there an existing issue for this?
Operating System
linux(EMBL BAND)
DeepLabCut version
3.0.1
What engine are you using?
pytorch
DeepLabCut mode
single animal
Device type
Nvidia Tesla V100
Bug description 🐛
during evalation process ,plotting cant be done when kept true, but working fine when its kept False, when the multianimal feature is kept at False, and im using RESnet -50, not DLCRNET
Steps To Reproduce
(DEEPLABCUT) bash-4.2$ python -c "
import deeplabcut
deeplabcut.evaluate_network(
'config.yaml',
Shuffles=[3],
plotting= True
)
"
Relevant log output
(DEEPLABCUT) bash-4.2$ python -c "import deeplabcut; print(deeplabcut.__version__)"
3.0.1
(DEEPLABCUT) bash-4.2$ python -c "
import deeplabcut
deeplabcut.evaluate_network(
'config.yaml',
Shuffles=[3],
plotting= False
)
"
Evaluation scorer: DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20
100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 469/469 [00:15<00:00, 31.13it/s]
100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 53/53 [00:01<00:00, 34.13it/s]
Evaluation results file: DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20-results.csv
Evaluation results for DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20-results.csv (pcutoff: 0.6):
train rmse 6.15
train rmse_pcutoff 3.93
train mAP 98.46
train mAR 99.32
test rmse 3.97
test rmse_pcutoff 3.29
test mAP 100.00
test mAR 100.00
Name: (0.9, 3, 20, -1, 0.6), dtype: float64
(DEEPLABCUT) bash-4.2$
(DEEPLABCUT) bash-4.2$ python -c "
import deeplabcut
deeplabcut.evaluate_network(
'config.yaml',
Shuffles=[3],
plotting= True
)
"
Evaluation scorer: DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20
100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 469/469 [00:15<00:00, 31.17it/s]
100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 53/53 [00:01<00:00, 35.11it/s]
Evaluation results file: DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20-results.csv
Evaluation results for DLC_Resnet50_OFTAug3shuffle3_snapshot_best-20-results.csv (pcutoff: 0.6):
train rmse 6.15
train rmse_pcutoff 3.93
train mAP 98.46
train mAR 99.32
test rmse 3.97
test rmse_pcutoff 3.29
test mAP 100.00
test mAR 100.00
Name: (0.9, 3, 20, -1, 0.6), dtype: float64
Warning: DataFrame reshape failed for img10359.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img00264.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img03469.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img13766.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img05289.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img00543.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Warning: DataFrame reshape failed for img05787.png
Expected: 2 individuals, 13 bodyparts
Ground truth: 26 elements (expected 52)
Predictions: 39 elements (expected 78)
Skipping visualization for this image
Anything else?
No response
Code of Conduct
Is there an existing issue for this?
Operating System
linux(EMBL BAND)
DeepLabCut version
3.0.1
What engine are you using?
pytorch
DeepLabCut mode
single animal
Device type
Nvidia Tesla V100
Bug description 🐛
during evalation process ,plotting cant be done when kept true, but working fine when its kept False, when the multianimal feature is kept at False, and im using RESnet -50, not DLCRNET
Steps To Reproduce
(DEEPLABCUT) bash-4.2$ python -c "
import deeplabcut
deeplabcut.evaluate_network(
'config.yaml',
Shuffles=[3],
plotting= True
)
"
Relevant log output
Anything else?
No response
Code of Conduct