checkpoint: checkpoints/easycom_local_b1_encoded_tf4576/av_seed0.pth
training summary: checkpoints/easycom_local_b1_encoded_tf4576/av_seed0.pth.json
/usr/local/lib/python3.11/site-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml d
irectly, please report this to the maintainers of the package that installed pynvml for you.
  import pynvml  # type: ignore[import]
device: cuda:0
loss: lstr-mce; output_space: three-class-softmax
sessions: Session_3, Session_2, Session_1
infer Session_3: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 40.61batch/s]
Session_3: saved pred (8400, 3, 10), causal-valid counts=[8399, 8398, 8397, 8396, 8395, 8394, 8393, 8392, 8391, 8390]
infer Session_2: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:00<00:00, 143.92batch/s]
Session_2: saved pred (7706, 3, 10), causal-valid counts=[7705, 7704, 7703, 7702, 7701, 7700, 7699, 7698, 7697, 7696]
infer Session_1: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:00<00:00, 160.27batch/s]
Session_1: saved pred (6942, 3, 10), causal-valid counts=[6941, 6940, 6939, 6938, 6937, 6936, 6935, 6934, 6933, 6932]

egospeak_full_timeline:
Action anticipation (0.20s) perframe mAP: 82.02415
  AP: background=68.93423, camera_wearer_speaking=85.08583, other_people_speaking=92.05239; n=23048
Action anticipation (0.40s) perframe mAP: 75.99169
  AP: background=60.58903, camera_wearer_speaking=78.83427, other_people_speaking=88.55177; n=23048
Action anticipation (0.60s) perframe mAP: 70.92665
  AP: background=53.84208, camera_wearer_speaking=73.45503, other_people_speaking=85.48283; n=23048
Action anticipation (0.80s) perframe mAP: 66.79615
  AP: background=49.21382, camera_wearer_speaking=68.56072, other_people_speaking=82.61390; n=23048
Action anticipation (1.00s) perframe mAP: 63.86856
  AP: background=45.62073, camera_wearer_speaking=65.27034, other_people_speaking=80.71461; n=23048
Action anticipation (1.20s) perframe mAP: 61.56280
  AP: background=43.46670, camera_wearer_speaking=62.05277, other_people_speaking=79.16893; n=23048
Action anticipation (1.40s) perframe mAP: 60.34070
  AP: background=42.54682, camera_wearer_speaking=60.20540, other_people_speaking=78.26988; n=23048
Action anticipation (1.60s) perframe mAP: 58.83407
  AP: background=41.15952, camera_wearer_speaking=58.18522, other_people_speaking=77.15747; n=23048
Action anticipation (1.80s) perframe mAP: 57.39446
  AP: background=39.94176, camera_wearer_speaking=55.99271, other_people_speaking=76.24890; n=23048
Action anticipation (2.00s) perframe mAP: 56.12449
  AP: background=38.87001, camera_wearer_speaking=53.82707, other_people_speaking=75.67639; n=23048
Action anticipation (mean) perframe mAP: 65.38637
