search

facebookresearch / detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
https://detectron2.readthedocs.io/en/latest/
Apache License 2.0
30.48k stars 7.48k forks source link

ValueError: operands could not be broadcast together with shapes (70,) (17,) but num_keypoinst == len(cfg.TEST.KEYPOINT_OKS_SIGMAS) #1658

Closed ItamarSafriel closed 4 years ago

ItamarSafriel commented 4 years ago

Hello, I am using this code to evaluate a model which was trained on a custom dataset. OKS is setup to be zeros just to test if the code runs. The model looks for 70 keypoints. It works for prediction but I can't get an evaluation 


#Setup config:
cfg = get_cfg()
cfg.MODEL.DEVICE = "cpu"
cfg.merge_from_file(model_zoo.get_config_file("COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.MODEL.WEIGHTS = "../../../measure-kid-other/data/models/7.6.20_X/model_0077999.pth"
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5
cfg.MODEL.ROI_KEYPOINT_HEAD.NUM_KEYPOINTS = 70
cfg.OUTPUT_DIR = "./output"
os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)

#Load dataset json file:
register_coco_instances("Babies_Val"
                                , get_data_set_metadata("Babies", "keypoints_X")
                                , f"../../../measure-kid-other/data/keypoints_X/Babies/Babies_Annotations/Babies_keypoints_X_Val.json"
                               , f"../../../measure-kid-other/data/keypoints_X/Babies/Babies_Val/"
        )

register_coco_instances("Babies_Train"
                                , get_data_set_metadata("Babies", "keypoints_X")
                                , f"../../../measure-kid-other/data/keypoints_X/Babies/Babies_Annotations/Babies_keypoints_X_Train.json"
                               , f"../../../measure-kid-other/data/keypoints_X/Babies/Babies_Train/"
        )        

cfg.DATASETS.TRAIN = ("Babies_Train",)
cfg.DATASETS.TEST = ("Babies_Val",)

#Setup oks:
cfg.TEST.KEYPOINT_OKS_SIGMAS = np.ones((70,1), dtype=float).tolist()

trainer = DefaultTrainer(cfg) 
trainer.resume_or_load(resume=False)

from detectron2.evaluation import COCOEvaluator, inference_on_dataset
from detectron2.data import build_detection_test_loader
evaluator = COCOEvaluator("Babies_Val", cfg, False, output_dir="./output/")
val_loader = build_detection_test_loader(cfg, "Babies_Val")
inference_on_dataset(trainer.model, val_loader, evaluator)
  1. full code you wrote or full changes you made (git diff) git diff is empty (I did not change anything).
  2. what exact command you run: A custom command which tries to evaluate a model (same as in the colab notebook)
  3. full logs you observed: 
    
WARNING [06/22 14:26:22 d2.data.datasets.coco]: 
Category ids in annotations are not in [1, #categories]! We'll apply a mapping for you.
[06/22 14:26:22 d2.data.datasets.coco]: Loaded 190 images in COCO format from ../../../measure-kid-other/data/keypoints_X/Babies/Babies_Annotations/Babies_keypoints_X_Train.json [06/22 14:26:22 d2.data.build]: Removed 0 images with no usable annotations. 190 images left. [06/22 14:26:22 d2.data.build]: Removed 0 images with fewer than 1 keypoints. [06/22 14:26:22 d2.data.build]: Distribution of instances among all 1 categories: category #instances
bed 190

[06/22 14:26:22 d2.data.common]: Serializing 190 elements to byte tensors and concatenating them all ... [06/22 14:26:22 d2.data.common]: Serialized dataset takes 0.40 MiB [06/22 14:26:22 d2.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()] [06/22 14:26:22 d2.data.build]: Using training sampler TrainingSampler WARNING [06/22 14:26:23 d2.data.datasets.coco]: Category ids in annotations are not in [1, #categories]! We'll apply a mapping for you.

[06/22 14:26:23 d2.data.datasets.coco]: Loaded 10 images in COCO format from ../../../measure-kid-other/data/keypoints_X/Babies/Babies_Annotations/Babies_keypoints_X_Val.json [06/22 14:26:23 d2.data.build]: Distribution of instances among all 1 categories: category #instances
bed 10
[06/22 14:26:23 d2.data.common]: Serializing 10 elements to byte tensors and concatenating them all ... [06/22 14:26:23 d2.data.common]: Serialized dataset takes 0.02 MiB [06/22 14:26:23 d2.evaluation.evaluator]: Start inference on 10 images [06/22 14:26:30 d2.evaluation.evaluator]: Inference done 1/10. 6.9712 s / img. ETA=0:01:03 [06/22 14:26:37 d2.evaluation.evaluator]: Inference done 2/10. 6.9612 s / img. ETA=0:00:56 [06/22 14:26:45 d2.evaluation.evaluator]: Inference done 3/10. 7.1313 s / img. ETA=0:00:50 [06/22 14:26:53 d2.evaluation.evaluator]: Inference done 4/10. 7.2606 s / img. ETA=0:00:43 [06/22 14:26:59 d2.evaluation.evaluator]: Inference done 5/10. 7.1567 s / img. ETA=0:00:35 [06/22 14:27:07 d2.evaluation.evaluator]: Inference done 6/10. 7.5309 s / img. ETA=0:00:30 [06/22 14:27:15 d2.evaluation.evaluator]: Inference done 7/10. 7.6066 s / img. ETA=0:00:22 [06/22 14:27:21 d2.evaluation.evaluator]: Inference done 8/10. 7.3617 s / img. ETA=0:00:14 [06/22 14:27:27 d2.evaluation.evaluator]: Inference done 9/10. 6.8376 s / img. ETA=0:00:06 [06/22 14:27:35 d2.evaluation.evaluator]: Inference done 10/10. 7.1722 s / img. ETA=0:00:00 [06/22 14:27:35 d2.evaluation.evaluator]: Total inference time: 0:00:35.894103 (7.178821 s / img per device, on 1 devices) [06/22 14:27:35 d2.evaluation.evaluator]: Total inference pure compute time: 0:00:35 (7.172167 s / img per device, on 1 devices) [06/22 14:27:35 d2.evaluation.coco_evaluation]: Preparing results for COCO format ... [06/22 14:27:35 d2.evaluation.coco_evaluation]: Saving results to ./output/coco_instances_results.json [06/22 14:27:35 d2.evaluation.coco_evaluation]: Evaluating predictions ... Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type bbox DONE (t=0.01s). Accumulating evaluation results... DONE (t=0.00s). Average Precision (AP) @[ IoU=0.50:0.95 area= all maxDets=100 ] = 0.655 Average Precision (AP) @[ IoU=0.50 area= all maxDets=100 ] = 0.946 Average Precision (AP) @[ IoU=0.75 area= all maxDets=100 ] = 0.779 Average Precision (AP) @[ IoU=0.50:0.95 area= small maxDets=100 ] = 0.751 Average Precision (AP) @[ IoU=0.50:0.95 area=medium maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 area= large maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 area= all maxDets= 1 ] = 0.670 Average Recall (AR) @[ IoU=0.50:0.95 area= all maxDets= 10 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 area= all maxDets=100 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 area= small maxDets=100 ] = 0.750 Average Recall (AR) @[ IoU=0.50:0.95 area=medium maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 area= large maxDets=100 ] = -1.000 [06/22 14:27:35 d2.evaluation.coco_evaluation]: Evaluation results for bbox: AP AP50 AP75 APs APm APl
65.519 94.620 77.935 75.149 nan nan

[06/22 14:27:35 d2.evaluation.coco_evaluation]: Note that some metrics cannot be computed. Loading and preparing results... DONE (t=0.00s) creating index... index created! Running per image evaluation... Evaluate annotation type keypoints Traceback (most recent call last): File "eval.py", line 85, in inference_on_dataset(trainer.model, val_loader, evaluator) File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/evaluator.py", line 176, in inference_on_dataset results = evaluator.evaluate() File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 143, in evaluate self._eval_predictions(set(self._tasks), predictions) File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 186, in _eval_predictions if len(coco_results) > 0 File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 508, in _evaluate_predictions_on_coco coco_eval.evaluate() File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 150, in evaluate for imgId in p.imgIds File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 151, in for catId in catIds} File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 230, in computeOks e = (dx2 + dy2) / vars / (gt['area']+np.spacing(1)) / 2 ValueError: operands could not be broadcast together with shapes (70,) (17,) 


## Expected behavior:
Expected to get an evaluation of the loaded model.

## Environment:
sys.platform linux Python 3.6.9 Anaconda, Inc. (default, Jul 30 2019, 19:07:31) [GCC 7.3.0] numpy 1.17.4 detectron2 0.1.3 @/home/itamar/projects/measure-kid-server/detectron2/detectron2 Compiler GCC 7.5 CUDA compiler not available DETECTRON2_ENV_MODULE PyTorch 1.5.0 @/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/torch PyTorch debug build False GPU available False Pillow 6.2.1 torchvision 0.6.0a0+82fd1c8 @/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/torchvision fvcore 0.1.1.post20200615 cv2 4.1.1

PyTorch built with:

ppwwyyxx commented 4 years ago

I don't think this will happen with the provided code. However, we're not able to run the code since it requires a private dataset. Please double check and if it is indeed an issue, please provide a way for us to reproduce it. Also, it's worth checking that your dataset does have annotations for 70 keypoints

ItamarSafriel commented 4 years ago

Hey, Thank you very much for replying. I would much rather not to share my data and models publicly on github. Do you think I can email you the needed things over email?

ppwwyyxx commented 4 years ago

Also, cfg.TEST.KEYPOINT_OKS_SIGMAS is supposed to be a list of float, but it's not according to your code. However this will not lead to the error in your log.

If the reported error can still reproduce by running the above code in a shell (not colab or notebook), the best way to move forward is to simplify it until it does not depend on private dataset, e.g., remove training set, model file, and use a json file with only one random annotation.

ItamarSafriel commented 4 years ago

Ok, thanks! Is there any model which is trained to predict other keypoints than a person? (e.g have a number of cfg.TEST.KEYPOINT_OKS_SIGMAS which is not 17) if not, how could one reproduce this problem? Is the only option is to share my own?

regarding, the dtype of cfg.TEST.KEYPOINT_OKS_SIGMAS, at the beginning it was setup to float and still didn't work.

Thansk!

ppwwyyxx commented 4 years ago

cfg.TEST.KEYPOINT_OKS_SIGMAS should be a list of float, but yours is a list of list of float.

This code can run correctly with input.jpg == http://images.cocodataset.org/val2017/000000439715.jpg

from detectron2.config import get_cfg
import os
import shutil
from detectron2.evaluation import COCOEvaluator, inference_on_dataset
from detectron2.data import build_detection_test_loader
from detectron2.data import DatasetCatalog, MetadataCatalog
import numpy as np
from detectron2 import model_zoo
from detectron2.engine import DefaultTrainer
from detectron2.structures import BoxMode

cfg = get_cfg()
# cfg.MODEL.DEVICE = "cpu"
cfg.merge_from_file(model_zoo.get_config_file("COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5
cfg.MODEL.ROI_KEYPOINT_HEAD.NUM_KEYPOINTS = 70
cfg.OUTPUT_DIR = "./output"
try:
    shutil.rmtree(cfg.OUTPUT_DIR)
except:
    pass
os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)

def getdata():
    return [{
        "file_name": "input.jpg",
        "image_id": "0",
        "width": 640,
        "height": 480,
        "annotations": [{
            "bbox": [0, 0, 640,480],
            "bbox_mode": BoxMode.XYXY_ABS,
            "category_id": 0,
            "keypoints": (np.zeros((210,)) + 3).tolist()
        }]
    }]

DatasetCatalog.register("test_data", getdata)
MetadataCatalog.get("test_data").thing_classes = ["classname"]

#Setup oks:
cfg.TEST.KEYPOINT_OKS_SIGMAS = np.ones((70,), dtype=float).tolist()

trainer = DefaultTrainer(cfg)
trainer.resume_or_load(resume=False)

evaluator = COCOEvaluator("test_data", cfg, False, output_dir="./output/")
val_loader = build_detection_test_loader(cfg, "test_data")
inference_on_dataset(trainer.model, val_loader, evaluator)

So I think your annotation file does not actually have 70 keypoints.

ItamarSafriel commented 4 years ago

I ran the your code and I got the same error. Here is the full log: 

[06/23 12:29:38 d2.data.datasets.coco]: Loading datasets/coco/annotations/person_keypoints_train2017.json takes 9.82 seconds.
[06/23 12:29:39 d2.data.datasets.coco]: Loaded 118287 images in COCO format from datasets/coco/annotations/person_keypoints_train2017.json
[06/23 12:29:43 d2.data.build]: Removed 54172 images with no usable annotations. 64115 images left.
[06/23 12:29:44 d2.data.build]: Removed 7516 images with fewer than 1 keypoints.
[06/23 12:29:46 d2.data.build]: Distribution of instances among all 1 categories:
|  category  | #instances   |
|:----------:|:-------------|
|   person   | 224840       |
|            |              |
[06/23 12:29:46 d2.data.common]: Serializing 56599 elements to byte tensors and concatenating them all ...
[06/23 12:29:48 d2.data.common]: Serialized dataset takes 242.71 MiB
[06/23 12:29:48 d2.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()]
[06/23 12:29:48 d2.data.build]: Using training sampler TrainingSampler
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: Remapping C2 weights ......
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.bias            loaded from res2_0_branch2a_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.running_mean    loaded from res2_0_branch2a_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.running_var     loaded from res2_0_branch2a_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.weight          loaded from res2_0_branch2a_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.weight               loaded from res2_0_branch2a_w                 of shape (64, 64, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv2.norm.bias            loaded from res2_0_branch2b_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv2.norm.running_mean    loaded from res2_0_branch2b_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv2.norm.running_var     loaded from res2_0_branch2b_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv2.norm.weight          loaded from res2_0_branch2b_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv2.weight               loaded from res2_0_branch2b_w                 of shape (64, 64, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv3.norm.bias            loaded from res2_0_branch2c_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv3.norm.running_mean    loaded from res2_0_branch2c_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv3.norm.running_var     loaded from res2_0_branch2c_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv3.norm.weight          loaded from res2_0_branch2c_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv3.weight               loaded from res2_0_branch2c_w                 of shape (256, 64, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.shortcut.norm.bias         loaded from res2_0_branch1_bn_beta            of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.shortcut.norm.running_var  loaded from res2_0_branch1_bn_running_var     of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.shortcut.norm.weight       loaded from res2_0_branch1_bn_gamma           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.shortcut.weight            loaded from res2_0_branch1_w                  of shape (256, 64, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv1.norm.bias            loaded from res2_1_branch2a_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv1.norm.running_mean    loaded from res2_1_branch2a_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv1.norm.running_var     loaded from res2_1_branch2a_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv1.norm.weight          loaded from res2_1_branch2a_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv1.weight               loaded from res2_1_branch2a_w                 of shape (64, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv2.norm.bias            loaded from res2_1_branch2b_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv2.norm.running_mean    loaded from res2_1_branch2b_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv2.norm.running_var     loaded from res2_1_branch2b_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv2.norm.weight          loaded from res2_1_branch2b_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv2.weight               loaded from res2_1_branch2b_w                 of shape (64, 64, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv3.norm.bias            loaded from res2_1_branch2c_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv3.norm.running_mean    loaded from res2_1_branch2c_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv3.norm.running_var     loaded from res2_1_branch2c_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv3.norm.weight          loaded from res2_1_branch2c_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.1.conv3.weight               loaded from res2_1_branch2c_w                 of shape (256, 64, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv1.norm.bias            loaded from res2_2_branch2a_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv1.norm.running_mean    loaded from res2_2_branch2a_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv1.norm.running_var     loaded from res2_2_branch2a_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv1.norm.weight          loaded from res2_2_branch2a_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv1.weight               loaded from res2_2_branch2a_w                 of shape (64, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv2.norm.bias            loaded from res2_2_branch2b_bn_beta           of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv2.norm.running_mean    loaded from res2_2_branch2b_bn_running_mean   of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv2.norm.running_var     loaded from res2_2_branch2b_bn_running_var    of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv2.norm.weight          loaded from res2_2_branch2b_bn_gamma          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv2.weight               loaded from res2_2_branch2b_w                 of shape (64, 64, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv3.norm.bias            loaded from res2_2_branch2c_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv3.norm.running_mean    loaded from res2_2_branch2c_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv3.norm.running_var     loaded from res2_2_branch2c_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv3.norm.weight          loaded from res2_2_branch2c_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.2.conv3.weight               loaded from res2_2_branch2c_w                 of shape (256, 64, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv1.norm.bias            loaded from res3_0_branch2a_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv1.norm.running_mean    loaded from res3_0_branch2a_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv1.norm.running_var     loaded from res3_0_branch2a_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv1.norm.weight          loaded from res3_0_branch2a_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv1.weight               loaded from res3_0_branch2a_w                 of shape (128, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv2.norm.bias            loaded from res3_0_branch2b_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv2.norm.running_mean    loaded from res3_0_branch2b_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv2.norm.running_var     loaded from res3_0_branch2b_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv2.norm.weight          loaded from res3_0_branch2b_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv2.weight               loaded from res3_0_branch2b_w                 of shape (128, 128, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv3.norm.bias            loaded from res3_0_branch2c_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv3.norm.running_mean    loaded from res3_0_branch2c_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv3.norm.running_var     loaded from res3_0_branch2c_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv3.norm.weight          loaded from res3_0_branch2c_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.conv3.weight               loaded from res3_0_branch2c_w                 of shape (512, 128, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.shortcut.norm.bias         loaded from res3_0_branch1_bn_beta            of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.shortcut.norm.running_var  loaded from res3_0_branch1_bn_running_var     of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.shortcut.norm.weight       loaded from res3_0_branch1_bn_gamma           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.0.shortcut.weight            loaded from res3_0_branch1_w                  of shape (512, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv1.norm.bias            loaded from res3_1_branch2a_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv1.norm.running_mean    loaded from res3_1_branch2a_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv1.norm.running_var     loaded from res3_1_branch2a_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv1.norm.weight          loaded from res3_1_branch2a_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv1.weight               loaded from res3_1_branch2a_w                 of shape (128, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv2.norm.bias            loaded from res3_1_branch2b_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv2.norm.running_mean    loaded from res3_1_branch2b_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv2.norm.running_var     loaded from res3_1_branch2b_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv2.norm.weight          loaded from res3_1_branch2b_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv2.weight               loaded from res3_1_branch2b_w                 of shape (128, 128, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv3.norm.bias            loaded from res3_1_branch2c_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv3.norm.running_mean    loaded from res3_1_branch2c_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv3.norm.running_var     loaded from res3_1_branch2c_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv3.norm.weight          loaded from res3_1_branch2c_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.1.conv3.weight               loaded from res3_1_branch2c_w                 of shape (512, 128, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv1.norm.bias            loaded from res3_2_branch2a_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv1.norm.running_mean    loaded from res3_2_branch2a_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv1.norm.running_var     loaded from res3_2_branch2a_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv1.norm.weight          loaded from res3_2_branch2a_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv1.weight               loaded from res3_2_branch2a_w                 of shape (128, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv2.norm.bias            loaded from res3_2_branch2b_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv2.norm.running_mean    loaded from res3_2_branch2b_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv2.norm.running_var     loaded from res3_2_branch2b_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv2.norm.weight          loaded from res3_2_branch2b_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv2.weight               loaded from res3_2_branch2b_w                 of shape (128, 128, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv3.norm.bias            loaded from res3_2_branch2c_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv3.norm.running_mean    loaded from res3_2_branch2c_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv3.norm.running_var     loaded from res3_2_branch2c_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv3.norm.weight          loaded from res3_2_branch2c_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.2.conv3.weight               loaded from res3_2_branch2c_w                 of shape (512, 128, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv1.norm.bias            loaded from res3_3_branch2a_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv1.norm.running_mean    loaded from res3_3_branch2a_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv1.norm.running_var     loaded from res3_3_branch2a_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv1.norm.weight          loaded from res3_3_branch2a_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv1.weight               loaded from res3_3_branch2a_w                 of shape (128, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv2.norm.bias            loaded from res3_3_branch2b_bn_beta           of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv2.norm.running_mean    loaded from res3_3_branch2b_bn_running_mean   of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv2.norm.running_var     loaded from res3_3_branch2b_bn_running_var    of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv2.norm.weight          loaded from res3_3_branch2b_bn_gamma          of shape (128,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv2.weight               loaded from res3_3_branch2b_w                 of shape (128, 128, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv3.norm.bias            loaded from res3_3_branch2c_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv3.norm.running_mean    loaded from res3_3_branch2c_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv3.norm.running_var     loaded from res3_3_branch2c_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv3.norm.weight          loaded from res3_3_branch2c_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res3.3.conv3.weight               loaded from res3_3_branch2c_w                 of shape (512, 128, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv1.norm.bias            loaded from res4_0_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv1.norm.running_mean    loaded from res4_0_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv1.norm.running_var     loaded from res4_0_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv1.norm.weight          loaded from res4_0_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv1.weight               loaded from res4_0_branch2a_w                 of shape (256, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv2.norm.bias            loaded from res4_0_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv2.norm.running_mean    loaded from res4_0_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv2.norm.running_var     loaded from res4_0_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv2.norm.weight          loaded from res4_0_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv2.weight               loaded from res4_0_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv3.norm.bias            loaded from res4_0_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv3.norm.running_mean    loaded from res4_0_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv3.norm.running_var     loaded from res4_0_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv3.norm.weight          loaded from res4_0_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.conv3.weight               loaded from res4_0_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.shortcut.norm.bias         loaded from res4_0_branch1_bn_beta            of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.shortcut.norm.running_var  loaded from res4_0_branch1_bn_running_var     of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.shortcut.norm.weight       loaded from res4_0_branch1_bn_gamma           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.0.shortcut.weight            loaded from res4_0_branch1_w                  of shape (1024, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv1.norm.bias            loaded from res4_1_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv1.norm.running_mean    loaded from res4_1_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv1.norm.running_var     loaded from res4_1_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv1.norm.weight          loaded from res4_1_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv1.weight               loaded from res4_1_branch2a_w                 of shape (256, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv2.norm.bias            loaded from res4_1_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv2.norm.running_mean    loaded from res4_1_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv2.norm.running_var     loaded from res4_1_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv2.norm.weight          loaded from res4_1_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv2.weight               loaded from res4_1_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv3.norm.bias            loaded from res4_1_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv3.norm.running_mean    loaded from res4_1_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv3.norm.running_var     loaded from res4_1_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv3.norm.weight          loaded from res4_1_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.1.conv3.weight               loaded from res4_1_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv1.norm.bias            loaded from res4_2_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv1.norm.running_mean    loaded from res4_2_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv1.norm.running_var     loaded from res4_2_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv1.norm.weight          loaded from res4_2_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv1.weight               loaded from res4_2_branch2a_w                 of shape (256, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv2.norm.bias            loaded from res4_2_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv2.norm.running_mean    loaded from res4_2_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv2.norm.running_var     loaded from res4_2_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv2.norm.weight          loaded from res4_2_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv2.weight               loaded from res4_2_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv3.norm.bias            loaded from res4_2_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv3.norm.running_mean    loaded from res4_2_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv3.norm.running_var     loaded from res4_2_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv3.norm.weight          loaded from res4_2_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.2.conv3.weight               loaded from res4_2_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv1.norm.bias            loaded from res4_3_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv1.norm.running_mean    loaded from res4_3_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv1.norm.running_var     loaded from res4_3_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv1.norm.weight          loaded from res4_3_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv1.weight               loaded from res4_3_branch2a_w                 of shape (256, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv2.norm.bias            loaded from res4_3_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv2.norm.running_mean    loaded from res4_3_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv2.norm.running_var     loaded from res4_3_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv2.norm.weight          loaded from res4_3_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv2.weight               loaded from res4_3_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv3.norm.bias            loaded from res4_3_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv3.norm.running_mean    loaded from res4_3_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv3.norm.running_var     loaded from res4_3_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv3.norm.weight          loaded from res4_3_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.3.conv3.weight               loaded from res4_3_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv1.norm.bias            loaded from res4_4_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv1.norm.running_mean    loaded from res4_4_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv1.norm.running_var     loaded from res4_4_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv1.norm.weight          loaded from res4_4_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv1.weight               loaded from res4_4_branch2a_w                 of shape (256, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv2.norm.bias            loaded from res4_4_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv2.norm.running_mean    loaded from res4_4_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv2.norm.running_var     loaded from res4_4_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv2.norm.weight          loaded from res4_4_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv2.weight               loaded from res4_4_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv3.norm.bias            loaded from res4_4_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv3.norm.running_mean    loaded from res4_4_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv3.norm.running_var     loaded from res4_4_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv3.norm.weight          loaded from res4_4_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.4.conv3.weight               loaded from res4_4_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv1.norm.bias            loaded from res4_5_branch2a_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv1.norm.running_mean    loaded from res4_5_branch2a_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv1.norm.running_var     loaded from res4_5_branch2a_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv1.norm.weight          loaded from res4_5_branch2a_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv1.weight               loaded from res4_5_branch2a_w                 of shape (256, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv2.norm.bias            loaded from res4_5_branch2b_bn_beta           of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv2.norm.running_mean    loaded from res4_5_branch2b_bn_running_mean   of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv2.norm.running_var     loaded from res4_5_branch2b_bn_running_var    of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv2.norm.weight          loaded from res4_5_branch2b_bn_gamma          of shape (256,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv2.weight               loaded from res4_5_branch2b_w                 of shape (256, 256, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv3.norm.bias            loaded from res4_5_branch2c_bn_beta           of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv3.norm.running_mean    loaded from res4_5_branch2c_bn_running_mean   of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv3.norm.running_var     loaded from res4_5_branch2c_bn_running_var    of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv3.norm.weight          loaded from res4_5_branch2c_bn_gamma          of shape (1024,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res4.5.conv3.weight               loaded from res4_5_branch2c_w                 of shape (1024, 256, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv1.norm.bias            loaded from res5_0_branch2a_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv1.norm.running_mean    loaded from res5_0_branch2a_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv1.norm.running_var     loaded from res5_0_branch2a_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv1.norm.weight          loaded from res5_0_branch2a_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv1.weight               loaded from res5_0_branch2a_w                 of shape (512, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv2.norm.bias            loaded from res5_0_branch2b_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv2.norm.running_mean    loaded from res5_0_branch2b_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv2.norm.running_var     loaded from res5_0_branch2b_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv2.norm.weight          loaded from res5_0_branch2b_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv2.weight               loaded from res5_0_branch2b_w                 of shape (512, 512, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv3.norm.bias            loaded from res5_0_branch2c_bn_beta           of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv3.norm.running_mean    loaded from res5_0_branch2c_bn_running_mean   of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv3.norm.running_var     loaded from res5_0_branch2c_bn_running_var    of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv3.norm.weight          loaded from res5_0_branch2c_bn_gamma          of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.conv3.weight               loaded from res5_0_branch2c_w                 of shape (2048, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.shortcut.norm.bias         loaded from res5_0_branch1_bn_beta            of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean    of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.shortcut.norm.running_var  loaded from res5_0_branch1_bn_running_var     of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.shortcut.norm.weight       loaded from res5_0_branch1_bn_gamma           of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.0.shortcut.weight            loaded from res5_0_branch1_w                  of shape (2048, 1024, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv1.norm.bias            loaded from res5_1_branch2a_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv1.norm.running_mean    loaded from res5_1_branch2a_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv1.norm.running_var     loaded from res5_1_branch2a_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv1.norm.weight          loaded from res5_1_branch2a_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv1.weight               loaded from res5_1_branch2a_w                 of shape (512, 2048, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv2.norm.bias            loaded from res5_1_branch2b_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv2.norm.running_mean    loaded from res5_1_branch2b_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv2.norm.running_var     loaded from res5_1_branch2b_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv2.norm.weight          loaded from res5_1_branch2b_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv2.weight               loaded from res5_1_branch2b_w                 of shape (512, 512, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv3.norm.bias            loaded from res5_1_branch2c_bn_beta           of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv3.norm.running_mean    loaded from res5_1_branch2c_bn_running_mean   of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv3.norm.running_var     loaded from res5_1_branch2c_bn_running_var    of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv3.norm.weight          loaded from res5_1_branch2c_bn_gamma          of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.1.conv3.weight               loaded from res5_1_branch2c_w                 of shape (2048, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv1.norm.bias            loaded from res5_2_branch2a_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv1.norm.running_mean    loaded from res5_2_branch2a_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv1.norm.running_var     loaded from res5_2_branch2a_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv1.norm.weight          loaded from res5_2_branch2a_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv1.weight               loaded from res5_2_branch2a_w                 of shape (512, 2048, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv2.norm.bias            loaded from res5_2_branch2b_bn_beta           of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv2.norm.running_mean    loaded from res5_2_branch2b_bn_running_mean   of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv2.norm.running_var     loaded from res5_2_branch2b_bn_running_var    of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv2.norm.weight          loaded from res5_2_branch2b_bn_gamma          of shape (512,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv2.weight               loaded from res5_2_branch2b_w                 of shape (512, 512, 3, 3)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv3.norm.bias            loaded from res5_2_branch2c_bn_beta           of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv3.norm.running_mean    loaded from res5_2_branch2c_bn_running_mean   of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv3.norm.running_var     loaded from res5_2_branch2c_bn_running_var    of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv3.norm.weight          loaded from res5_2_branch2c_bn_gamma          of shape (2048,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res5.2.conv3.weight               loaded from res5_2_branch2c_w                 of shape (2048, 512, 1, 1)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.stem.conv1.norm.bias              loaded from res_conv1_bn_beta                 of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.stem.conv1.norm.running_mean      loaded from res_conv1_bn_running_mean         of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.stem.conv1.norm.running_var       loaded from res_conv1_bn_running_var          of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.stem.conv1.norm.weight            loaded from res_conv1_bn_gamma                of shape (64,)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: backbone.bottom_up.stem.conv1.weight                 loaded from conv1_w                           of shape (64, 3, 7, 7)
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: Some model parameters or buffers are not found in the checkpoint:
  backbone.fpn_lateral2.{bias, weight}
  backbone.fpn_lateral3.{bias, weight}
  backbone.fpn_lateral4.{bias, weight}
  backbone.fpn_lateral5.{bias, weight}
  backbone.fpn_output2.{bias, weight}
  backbone.fpn_output3.{bias, weight}
  backbone.fpn_output4.{bias, weight}
  backbone.fpn_output5.{bias, weight}
  pixel_mean
  pixel_std
  proposal_generator.anchor_generator.cell_anchors.{0, 1, 2, 3, 4}
  proposal_generator.rpn_head.anchor_deltas.{bias, weight}
  proposal_generator.rpn_head.conv.{bias, weight}
  proposal_generator.rpn_head.objectness_logits.{bias, weight}
  roi_heads.box_head.fc1.{bias, weight}
  roi_heads.box_head.fc2.{bias, weight}
  roi_heads.box_predictor.bbox_pred.{bias, weight}
  roi_heads.box_predictor.cls_score.{bias, weight}
  roi_heads.keypoint_head.conv_fcn1.{bias, weight}
  roi_heads.keypoint_head.conv_fcn2.{bias, weight}
  roi_heads.keypoint_head.conv_fcn3.{bias, weight}
  roi_heads.keypoint_head.conv_fcn4.{bias, weight}
  roi_heads.keypoint_head.conv_fcn5.{bias, weight}
  roi_heads.keypoint_head.conv_fcn6.{bias, weight}
  roi_heads.keypoint_head.conv_fcn7.{bias, weight}
  roi_heads.keypoint_head.conv_fcn8.{bias, weight}
  roi_heads.keypoint_head.score_lowres.{bias, weight}
[06/23 12:29:49 d2.checkpoint.c2_model_loading]: The checkpoint state_dict contains keys that are not used by the model:
  fc1000_b
  fc1000_w
  conv1_b
WARNING [06/23 12:29:49 d2.evaluation.coco_evaluation]: json_file was not found in MetaDataCatalog for 'test_data'. Trying to convert it to COCO format ...
[06/23 12:29:49 d2.data.datasets.coco]: Converting annotations of dataset 'test_data' to COCO format ...)
[06/23 12:29:49 d2.data.datasets.coco]: Converting dataset dicts into COCO format
[06/23 12:29:49 d2.data.datasets.coco]: Conversion finished, #images: 1, #annotations: 1
[06/23 12:29:49 d2.data.datasets.coco]: Caching COCO format annotations at './output/test_data_coco_format.json' ...
[06/23 12:29:49 d2.data.build]: Distribution of instances among all 1 categories:
|  category  | #instances   |
|:----------:|:-------------|
| classname  | 1            |
|            |              |
[06/23 12:29:49 d2.data.common]: Serializing 1 elements to byte tensors and concatenating them all ...
[06/23 12:29:49 d2.data.common]: Serialized dataset takes 0.00 MiB
[06/23 12:29:49 d2.evaluation.evaluator]: Start inference on 1 images
[06/23 12:30:00 d2.evaluation.evaluator]: Inference done 1/1. 10.9180 s / img. ETA=0:00:00
[06/23 12:30:00 d2.evaluation.evaluator]: Total inference time: 0:00:10.963213 (10.963213 s / img per device, on 1 devices)
[06/23 12:30:00 d2.evaluation.evaluator]: Total inference pure compute time: 0:00:10 (10.918039 s / img per device, on 1 devices)
[06/23 12:30:00 d2.evaluation.coco_evaluation]: Preparing results for COCO format ...
[06/23 12:30:00 d2.evaluation.coco_evaluation]: Saving results to ./output/coco_instances_results.json
[06/23 12:30:00 d2.evaluation.coco_evaluation]: Evaluating predictions ...
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=0.01s).
Accumulating evaluation results...
DONE (t=0.00s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
[06/23 12:30:00 d2.evaluation.coco_evaluation]: Evaluation results for bbox: 
|  AP   |  AP50  |  AP75  |  APs  |  APm  |  APl  |
|:-----:|:------:|:------:|:-----:|:-----:|:-----:|
| 0.000 | 0.000  | 0.000  |  nan  |  nan  | 0.000 |
[06/23 12:30:00 d2.evaluation.coco_evaluation]: Note that some metrics cannot be computed.
Loading and preparing results...
DONE (t=0.00s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *keypoints*
Traceback (most recent call last):
  File "eval.py", line 136, in <module>
    inference_on_dataset(trainer.model, val_loader, evaluator)
  File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/evaluator.py", line 176, in inference_on_dataset
    results = evaluator.evaluate()
  File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 143, in evaluate
    self._eval_predictions(set(self._tasks), predictions)
  File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 186, in _eval_predictions
    if len(coco_results) > 0
  File "/home/itamar/projects/measure-kid-server/detectron2/detectron2/evaluation/coco_evaluation.py", line 508, in _evaluate_predictions_on_coco
    coco_eval.evaluate()
  File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 150, in evaluate
    for imgId in p.imgIds
  File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 151, in <dictcomp>
    for catId in catIds}
  File "/home/itamar/anaconda3/envs/measure-kid/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 230, in computeOks
    e = (dx**2 + dy**2) / vars / (gt['area']+np.spacing(1)) / 2
ValueError: operands could not be broadcast together with shapes (70,) (17,)
ppwwyyxx commented 4 years ago

Works on colab: https://colab.research.google.com/gist/ppwwyyxx/1c7bdbc486ef48dcb65a29d6c773577b/detectron2-tutorial.ipynb

Please provide a simple way that reproduces the issue. Otherwise there is nothing we can do.

ItamarSafriel commented 4 years ago

Ok, how can I debug this? something might be wrong with my env? If the code works on colab then I don't know how I can reproduce this (on my own machine it still doesn't work). I didn't do it, but changing the OKS sigmas manually on the cocoeval.py file is the same as setting them up from the cfg? maybe I have a problem with my pycocotools?

Thanks!

ppwwyyxx commented 4 years ago

The feature of OKS was added in pycocotools last year: https://github.com/cocodataset/cocoapi. You're probably using an older version of it.

ItamarSafriel commented 4 years ago

Wow that was it! I had version 2.0 and when I install version 2.01 it worked.

Thanks!