Saving mota output #180
Saving mota output #180
Conversation
nikk-nikaznan
commented
Jun 4, 2024
•
nikk-nikaznan
commented
- mota return all the metrics and save to csv
- adding some plot functions to visualise the tracking result
Signed-off-by: nikk-nikaznan <[email protected]>
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #180 +/- ##
==========================================
- Coverage 46.13% 45.67% -0.46%
==========================================
Files 24 24
Lines 1461 1526 +65
==========================================
+ Hits 674 697 +23
- Misses 787 829 +42 ☔ View full report in Codecov by Sentry. |
…entre/crabs-exploration into nikkna/eval_track_dev
Signed-off-by: nikk-nikaznan <[email protected]>
Signed-off-by: nikk-nikaznan <[email protected]>
…ration into nikkna/eval_track_dev
…entre/crabs-exploration into nikkna/eval_track_dev
| @@ -299,7 +307,15 @@ def evaluate_mota( | |||
| mota = ( | |||
| 1 - (missed_detections + false_positive + num_switches) / total_gt | |||
| ) | |||
| return mota, gt_to_tracked_id_current_frame | |||
| return ( | |||
| mota, | |||
There was a problem hiding this comment.
Returning a long tuple is sometimes considered a code smell.
Maybe we can pass mota and its components as a dict to reduce this?
| "Missed Detections": [], | ||
| "False Positives": [], | ||
| "Number of Switches": [], | ||
| "Mota": [], |
There was a problem hiding this comment.
| "Mota": [], | |
| "MOTA": [], |
| gt_data_frame, | ||
| pred_data_frame, | ||
| self.iou_threshold, | ||
| prev_frame_id_map, | ||
| ) | ||
| mota_values.append(mota) | ||
| results["Frame Number"].append(frame_number) |
There was a problem hiding this comment.
If we make evaluate_mota return a dict for the MOTA and its components (called for example mota_dict), then we can make results have the same keys. That way we can make this bit smaller:
for key in results.keys():
results[key].append(mota_dict[key])| @@ -154,6 +156,7 @@ def save_required_output( | |||
| frame_copy = frame.copy() | |||
| for bbox in tracked_boxes: | |||
| xmin, ymin, xmax, ymax, id = bbox | |||
| print(f"Calling draw_bbox with {bbox}") | |||
There was a problem hiding this comment.
| print(f"Calling draw_bbox with {bbox}") | |
| mota_value_list.append(float(row["Mota"])) | ||
|
|
||
| return ( | ||
| true_positives_list, |
There was a problem hiding this comment.
maybe this tuple can be a dict instead? It's a bit less of a code smell
There was a problem hiding this comment.
I think if we read the csv as a pandas dataframe instead we can extract the columns more efficiently (that is, without explicit looping).
There is also a dataframe .to_dict() method, so we may be able to get the output dictionary in one go this way.
| plot_name = filepath.name | ||
|
|
||
| num_frames = len(true_positives_list) | ||
| frames = range(1, num_frames + 1) |
There was a problem hiding this comment.
| frames = range(1, num_frames + 1) | |
| frame_numbers = range(1, num_frames + 1) |
| track_results: dict[str, Any], | ||
| ) -> None: | ||
| track_df = pd.DataFrame(track_results) | ||
| output_filename = f"{tracking_output_dir}/tracking_metrics_output.csv" |
There was a problem hiding this comment.
Just to follow our usual convention, could we timestamp the output directory? We would need to ensure it goes in the same directory as the video output if requested (or other outputs that may be requested)
