Revert "Various tracker integration"

This reverts commit 6acda53.

plugins/track/deep_oc_sort/association.py

@@ -204,7 +204,7 @@ def linear_assignment(cost_matrix):
         import lap
 
         _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
-        return np.array([[y[i], i] for i in x])  #
+        return np.array([[y[i], i] for i in x if i >= 0])  #
     except ImportError:
         from scipy.optimize import linear_sum_assignment
 

tracklab/configs/config.yaml

@@ -4,13 +4,13 @@
 # to create the final config file. This item *must* be
 # the first element in the file.
 defaults:
-  - dataset: dancetrack
+  - dataset: soccernet_gs
   - eval: trackeval
   - engine: offline
   - state: no_save
   - visualization: save_videos
   - modules/bbox_detector: yolov8
-  - modules/pose_topdown: hrnet_posetrack18
+  - modules/pose_bottomup: openpifpaf
   - modules/reid: bpbreid
   - modules/track: oc_sort
   - _self_
@@ -21,6 +21,7 @@ defaults:
 # Use 'pipeline: []' for an empty pipeline
 pipeline:
   - bbox_detector
+  - reid
   - track
 
 # Experiment name

tracklab/configs/engine/video.yaml

@@ -1,6 +1,6 @@
 _target_: tracklab.engine.VideoOnlineTrackingEngine
 
-filename: "/path/to/video.mp4"
+filename: "/home/vjoosdeterb/Downloads/ilids/AVSS_AB_EVAL_divx.avi"
 target_fps: 1
 num_workers: ${num_cores}
 callbacks:

tracklab/configs/modules/bbox_detector/yolox.yaml

@@ -1,5 +1,4 @@
 _target_: tracklab.wrappers.bbox_detector.mmdetection_api.MMDetection
 config_name: yolox_x_8x8_300e_coco
 path_to_checkpoint: ${model_dir}/mmdet/${.config_name}.pth
-min_confidence: 0.4
-batch_size: 2
+min_confidence: 0.4

tracklab/configs/modules/reid/bpbreid.yaml

@@ -3,7 +3,7 @@ _target_: tracklab.wrappers.BPBReId
 defaults:
   - dataset: default
 
-batch_size: 32
+batch_size: 64
 job_id: "${oc.env:SLURM_JOBID,0}" # TODO
 save_path: reid
 use_keypoints_visibility_scores_for_reid: False

tracklab/engine/video.py

@@ -8,6 +8,7 @@
 import torch
 from lightning import Fabric
 
+from tracklab.engine import TrackingEngine
 from tracklab.engine.engine import merge_dataframes
 from tracklab.pipeline import Pipeline
 

tracklab/utils/__init__.py

@@ -90,10 +90,6 @@ def in_bbox_coord(self, bbox_ltwh):
             lambda x: keypoints_in_bbox_coord(x, bbox_ltwh)
         )
 
-    def keypoints_bbox_xyc(self):
-        """Converts from keypoints in image coordinates to keypoints in bbox coordinates"""
-        return self._obj.apply(
-            lambda r: keypoints_in_bbox_coord(r.keypoints_xyc, r.bbox_ltwh), axis=1)
 
 @pd.api.extensions.register_series_accessor("keypoints")
 class KeypointsSeriesAccessor:
@@ -124,7 +120,3 @@ def conf(self):
 
     def in_bbox_coord(self, bbox_ltwh):
         return keypoints_in_bbox_coord(self._obj.keypoints_xyc, bbox_ltwh)
-
-    def keypoints_bbox_xyc(self):
-        """Converts from keypoints in image coordinates to keypoints in bbox coordinates"""
-        return keypoints_in_bbox_coord(self._obj.keypoints_xyc, self._obj.bbox_ltwh)

tracklab/utils/cv2.py

@@ -1,10 +1,5 @@
-import colorsys
-
 import cv2
 from functools import lru_cache
-
-import matplotlib.cm as cm
-
 from .coordinates import *
 
 
@@ -67,7 +62,7 @@ def cv2_load_image(file_path):
             video_reader.set_filename(video_file)
         image = video_reader[int(frame_id)]
     else:
-        image = cv2.imread(file_path)
+        image = cv2.imread(str(file_path))
     image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
     return image
 
@@ -370,41 +365,3 @@ def draw_text(
         lineType=lineType,
     )
     return text_size
-
-
-def scale_lightness(rgb, scale_l=1.4):
-    # convert rgb to hls
-    h, l, s = colorsys.rgb_to_hls(*rgb)
-    # manipulate h, l, s values and return as rgb
-    return colorsys.hls_to_rgb(h, min(1, l * scale_l), s = s)
-
-def colored_body_parts_overlay(img, masks, clip=True, interpolation=cv2.INTER_CUBIC, alpha=0.28, mask_threshold=0.0, weight_scale=1, rgb=False):
-    width, height = img.shape[1], img.shape[0]
-    white_bckg = np.ones_like(img) * 255
-    for i in range(masks.shape[0]):
-        mask = cv2.resize(masks[i], dsize=(width, height), interpolation=interpolation)
-        if clip:
-            mask = np.clip(mask, 0, 1)
-        else:
-            mask = np.interp(mask, (mask.min(), mask.max()), (0, 255)).astype(np.uint8)
-        weight = mask
-        mask_alpha = np.ones_like(weight)
-        mask_alpha[mask < mask_threshold] = 0
-        mask_alpha = np.expand_dims(mask_alpha, 2)
-        weight = np.expand_dims(weight, 2) / weight_scale
-        color_img = np.zeros_like(img)
-        color = scale_lightness(cm.gist_rainbow(i / (len(masks)-1))[0:-1])
-        color_img[:] = np.flip(np.array(color)*255).astype(np.uint8)
-        white_bckg = white_bckg * (1 - mask_alpha * weight) + color_img * mask_alpha * weight
-    heatmap = masks.sum(axis=0).clip(0, 1)
-    heatmap = cv2.resize(heatmap, dsize=(width, height), interpolation=interpolation)
-    mask_alpha = heatmap
-    mask_alpha[heatmap < mask_threshold] = 0
-    mask_alpha = np.repeat(np.expand_dims(mask_alpha, 2), 3, 2)
-    white_bckg = white_bckg.astype(img.dtype)
-    if rgb:
-        white_bckg = cv2.cvtColor(white_bckg, cv2.COLOR_BGR2RGB)
-    masked_img = (
-            img * (1 - mask_alpha * alpha) + white_bckg * mask_alpha * alpha
-    )
-    return masked_img

tracklab/wrappers/datasets/external_video.py

@@ -115,7 +115,7 @@ def __init__(self, dataset_path: str, video_path: str, *args, **kwargs):
             video_metadata,
             image_metadata,
             None,
-            image_metadata,
+            image_metadata
         )
 
         super().__init__(dataset_path,  dict(val=val_set), *args, **kwargs)

tracklab/wrappers/reid/bpbreid_dataset.py

@@ -18,6 +18,7 @@
 from tracklab.utils.coordinates import rescale_keypoints
 
 from tracklab.utils.cv2 import overlay_heatmap
+import tracklab
 
 from torchreid.data import ImageDataset
 from torchreid.utils.imagetools import (

tracklab/wrappers/track/__init__.py

@@ -3,4 +3,4 @@
 from .byte_track_api import ByteTrack
 from .oc_sort_api import OCSORT
 from .deep_oc_sort_api import DeepOCSORT
-from .bpbreid_strong_sort_api import BPBReIDStrongSORT
+from .bpbreid_strong_sort_api import BPBReIDStrongSORT

tracklab/wrappers/track/bot_sort_api.py

@@ -9,8 +9,6 @@
 
 import logging
 
-from tracklab.utils.cv2 import cv2_load_image
-
 log = logging.getLogger(__name__)
 
 
@@ -22,10 +20,9 @@ class BotSORT(ImageLevelModule):
     ]
     output_columns = ["track_id", "track_bbox_ltwh", "track_bbox_conf"]
 
-    def __init__(self, cfg, device, **kwargs):
-        super().__init__(batch_size=1)
+    def __init__(self, cfg, device, batch_size):
+        super().__init__(cfg, device, batch_size)
         self.cfg = cfg
-        self.device = device
         self.reset()
 
     def reset(self):
@@ -38,29 +35,21 @@ def reset(self):
         )
 
     @torch.no_grad()
-    def preprocess(self, image, detections: pd.DataFrame, metadata: pd.Series):
-        processed_detections = []
-        if len(detections) == 0:
-            return {"input": []}
-        for det_id, detection in detections.iterrows():
-            ltrb = detection.bbox.ltrb()
-            conf = detection.bbox.conf()
-            cls = detection.category_id
-            tracklab_id = int(detection.name)
-            processed_detections.append(
-                np.array([*ltrb, conf, cls, tracklab_id])
-            )
+    def preprocess(self, detection: pd.Series, metadata: pd.Series):
+        ltrb = detection.bbox.ltrb()
+        conf = detection.bbox.conf()
+        cls = detection.category_id
+        tracklab_id = detection.name
         return {
-            "input": np.stack(processed_detections)
+            "input": np.array(
+                [ltrb[0], ltrb[1], ltrb[2], ltrb[3], conf, cls, tracklab_id]
+            ),
         }
 
     @torch.no_grad()
-    def process(self, batch, detections: pd.DataFrame, metadatas: pd.DataFrame):
-        if len(detections) == 0:
-            return []
-        inputs = batch["input"][0]  # Nx7 [l,t,r,b,conf,class,tracklab_id]
+    def process(self, batch, image, detections: pd.DataFrame):
+        inputs = batch["input"]  # Nx7 [l,t,r,b,conf,class,tracklab_id]
         inputs = inputs[inputs[:, 4] > self.cfg.min_confidence]
-        image = cv2_load_image(metadatas['file_path'].values[0])
         results = self.model.update(inputs, image)
         results = np.asarray(results)  # N'x8 [l,t,r,b,track_id,class,conf,idx]
         if results.size:

tracklab/wrappers/track/byte_track_api.py

@@ -19,38 +19,30 @@ class ByteTrack(ImageLevelModule):
     ]
     output_columns = ["track_id", "track_bbox_ltwh", "track_bbox_conf"]
 
-    def __init__(self, cfg, device, **kwargs):
-        super().__init__(batch_size=1)
+    def __init__(self, cfg, device, batch_size):
+        super().__init__(cfg, device, batch_size)
         self.cfg = cfg
-        self.device = device
         self.reset()
 
     def reset(self):
         """Reset the tracker state to start tracking in a new video."""
         self.model = byte_tracker.BYTETracker(**self.cfg.hyperparams)
 
     @torch.no_grad()
-    def preprocess(self, image, detections: pd.DataFrame, metadata: pd.Series):
-        processed_detections = []
-        if len(detections) == 0:
-            return {"input": []}
-        for det_id, detection in detections.iterrows():
-            ltrb = detection.bbox.ltrb()
-            conf = detection.bbox.conf()
-            cls = detection.category_id
-            tracklab_id = int(detection.name)
-            processed_detections.append(
-                np.array([*ltrb, conf, cls, tracklab_id])
-            )
+    def preprocess(self, detection: pd.Series, metadata: pd.Series):
+        ltrb = detection.bbox.ltrb()
+        conf = detection.bbox.conf()
+        cls = detection.category_id
+        tracklab_id = detection.name
         return {
-            "input": np.stack(processed_detections)
+            "input": np.array(
+                [ltrb[0], ltrb[1], ltrb[2], ltrb[3], conf, cls, tracklab_id]
+            ),
         }
 
     @torch.no_grad()
-    def process(self, batch, detections: pd.DataFrame, metadatas: pd.DataFrame):
-        if len(detections) == 0:
-            return []
-        inputs = batch["input"][0]  # Nx7 [l,t,r,b,conf,class,tracklab_id]
+    def process(self, batch, image, detections: pd.DataFrame):
+        inputs = batch["input"]  # Nx7 [l,t,r,b,conf,class,tracklab_id]
         inputs = inputs[inputs[:, 4] > self.cfg.min_confidence]
         results = self.model.update(inputs, None)
         results = np.asarray(results)  # N'x8 [l,t,r,b,track_id,class,conf,idx]