How to extract mask?

[claudio9russo7]

Discussed in #4143

^{Originally posted by claudio9russo7 April 9, 2022}
Making the inference with DefaultPredictor returns the bb, I would need the masks or polygons instead. Is it possible to get them with DefaultPredictor?

I saw in the docs that the possibility of making the inference with another method is reported:

model.eval()
with torch.no_grad():
outputs = model(inputs)

I tried this way:

import torch
import glob
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml"))
cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.SOLVER.IMS_PER_BATCH = 1
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1 # only has one class (pnumonia)
cfg.INPUT.FORMAT = "BGR"
#Just run these lines if you have the trained model im memory
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7 # set the testing threshold for this model
#build model
model = build_model(cfg)
DetectionCheckpointer(model).load("output/model_final.pth")
model.eval()#make sure its in eval mode

image = cv2.imread("/kaggle/working/detectron2/images/73-ab1.jpg")
height, width = image.shape[:2]
image = torch.as_tensor(image.astype("float32").transpose(2, 0, 1))
image = ImageList.from_tensors([image])

with torch.no_grad():
inputs = image
outputs = model(inputs)

But I get this error:
IndexError: too many indices for tensor of dimension 3

[github-actions[bot]]

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template.
The following information is missing: "Instructions To Reproduce the Issue and Full Logs"; "Your Environment";