Merge branch 'pytorch_dlc' into niels/dlc3_diagram

n-poulsen · Jan 10, 2025 · Dec 19, 2024 · Dec 19, 2024 · Dec 19, 2024 · Dec 20, 2024
commit f0200fcc7edc74d66122d0b3dba4be71c32c0e7e
diff --git a/deeplabcut/pose_estimation_pytorch/README.md b/deeplabcut/pose_estimation_pytorch/README.md
@@ -421,7 +421,11 @@ train(
 ### Running Video Analysis outside a DeepLabCut Project
 
 DeepLabCut provides high-level APIs (via the GUI or the python package) to analyze your
+<<<<<<< HEAD
 data. The usage of this API assumes the existence of a DLC project (with `config.yaml`
+=======
+data. The usage of this API assumes the existance of a DLC project (with `config.yaml`
+>>>>>>> pytorch_dlc
 file, etc.).
 
 Sometimes it might be more convenient to just run a model on your data via a low-level
@@ -432,9 +436,6 @@ example below:
 from pathlib import Path
 
 import deeplabcut.pose_estimation_pytorch as pep
-from deeplabcut.pose_estimation_pytorch.apis.analyze_videos import video_inference
-from deeplabcut.pose_estimation_pytorch.config import read_config_as_dict
-from deeplabcut.pose_estimation_pytorch.task import Task
 
 train_dir = Path("/Users/Jaylen/my-dlc-models/train")
 pytorch_config_path = train_dir / "pytorch_config.yaml"
@@ -450,8 +451,8 @@ batch_size = 16
 detector_batch_size = 8
 
 # read model configuration
-model_cfg = read_config_as_dict(pytorch_config_path)
-pose_task = Task(model_cfg["method"])
+model_cfg = pep.config.read_config_as_dict(pytorch_config_path)
+pose_task = pep.Task(model_cfg["method"])
 pose_runner = pep.get_pose_inference_runner(
     model_config=model_cfg,
     snapshot_path=snapshot_path,
@@ -468,7 +469,7 @@ if pose_task == pep.Task.TOP_DOWN:
         batch_size=detector_batch_size,
     )
 
-predictions = video_inference(
+predictions = pep.video_inference(
     video=video_path,
     pose_runner=pose_runner,
     detector_runner=detector_runner,
@@ -491,13 +492,11 @@ You can easily do so by writing a bit of custom code, as shown in the example be
 from pathlib import Path
 
 import numpy as np
-from deeplabcut.pose_estimation_pytorch import get_inference_runners
-from deeplabcut.pose_estimation_pytorch.apis import VideoIterator
-from deeplabcut.pose_estimation_pytorch.config import read_config_as_dict
+import deeplabcut.pose_estimation_pytorch as pep
 from tqdm import tqdm
 
 # create an iterator for your video
-video = VideoIterator("/Users/Jayson/my-cool-video.mp4")
+video = pep.VideoIterator("/Users/Jayson/my-cool-video.mp4")
 
 # dummy bboxes - you can load yours from a file or in another way
 #  the bboxes should be in `xywh` format, i.e. (x_top_left, y_top_left, width, height)
@@ -517,8 +516,8 @@ video.set_context(bounding_boxes)
 max_individuals = np.max([len(context["bboxes"]) for context in bounding_boxes])
 
 # run inference!
-model_cfg = read_config_as_dict("/Users/Jayson/pytorch_config.yaml")
-pose_runner, _ = get_inference_runners(
+model_cfg = pep.config.read_config_as_dict("/Users/Jayson/pytorch_config.yaml")
+pose_runner = pep.get_pose_inference_runner(
     model_config=model_cfg,
     snapshot_path=Path("/Users/Jayson/model-snapshot.pt"),
     max_individuals=max_individuals,