export_predictions_and_labeled_video(
video_file=video_file,
cfg=cfg,
ckpt_file=best_ckpt,
prediction_csv_file=prediction_csv_file,
labeled_mp4_file=labeled_mp4_file,
trainer=trainer,
model=model,
data_module=data_module_pred,
save_heatmaps=cfg.eval.get(
"predict_vids_after_training_save_heatmaps", True
),
)
Error message:
Traceback (most recent call last):
File "/root/capsule/scratch/lightning-pose/scripts/train_hydra.py", line 297, in train
export_predictions_and_labeled_video(
File "/lightning-pose/lightning_pose/utils/scripts.py", line 675, in export_predictions_and_labeled_video
preds_df = predict_single_video(
File "/lightning-pose/lightning_pose/utils/predictions.py", line 397, in predict_single_video
keypoints, confidences, heatmaps = _predict_frames(
File "/lightning-pose/lightning_pose/utils/predictions.py", line 437, in _predict_frames
def _predict_frames(
File "/opt/conda/lib/python3.8/site-packages/typeguard/_functions.py", line 113, in check_argument_types
check_type_internal(value, expected_type, memo=memo)
File "/opt/conda/lib/python3.8/site-packages/typeguard/_checkers.py", line 680, in check_type_internal
raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}")
typeguard.TypeCheckError: argument "model" (lightning_pose.models.heatmap_tracker.HeatmapTracker) is not an instance of pytorch_lightning.core.module.LightningModule
Hi, thanks for releasing lightning-pose.
I got an error message when generating the heatmaps for the testing video by calling the export_predictions_and_labeled_video() function, from https://github.com/danbider/lightning-pose/blob/6135e5a50523d4a9d8f1ba986b76e28e3dcd0cf1/scripts/train_hydra.py. The error message is shown as below.
export_predictions_and_labeled_video( video_file=video_file, cfg=cfg, ckpt_file=best_ckpt, prediction_csv_file=prediction_csv_file, labeled_mp4_file=labeled_mp4_file, trainer=trainer, model=model, data_module=data_module_pred, save_heatmaps=cfg.eval.get( "predict_vids_after_training_save_heatmaps", True ), ) Error message: Traceback (most recent call last): File "/root/capsule/scratch/lightning-pose/scripts/train_hydra.py", line 297, in train export_predictions_and_labeled_video( File "/lightning-pose/lightning_pose/utils/scripts.py", line 675, in export_predictions_and_labeled_video preds_df = predict_single_video( File "/lightning-pose/lightning_pose/utils/predictions.py", line 397, in predict_single_video keypoints, confidences, heatmaps = _predict_frames( File "/lightning-pose/lightning_pose/utils/predictions.py", line 437, in _predict_frames def _predict_frames( File "/opt/conda/lib/python3.8/site-packages/typeguard/_functions.py", line 113, in check_argument_types check_type_internal(value, expected_type, memo=memo) File "/opt/conda/lib/python3.8/site-packages/typeguard/_checkers.py", line 680, in check_type_internal raise TypeCheckError(f"is not an instance of {qualified_name(origin_type)}") typeguard.TypeCheckError: argument "model" (lightning_pose.models.heatmap_tracker.HeatmapTracker) is not an instance of pytorch_lightning.core.module.LightningModule
Thanks, Di