ucbdrive/shapeprop

Learning Saliency Propagation for Semi-supervised Instance Segmentation

shapeprop's Issues

what is meaning for coco_2017_voc_category_train?

Does this experiment involve the VOC dataset？ Does the data prepration section in README only mention the COCO dataset, do users need to make any changes or mixes to this dataset?

Can you provide trained models for us to test demo pictures?

RuntimeError: Expected object of scalar type Bool but got scalar type Byte for argument #2 'other' in call to _th_and

I run the classwise semi-supervision demo guided by the readme, I have only one GPU so run the command as:
python shapeprop/tools/train_net.py --config-file configs/coco_voc_mask_rcnn_r50_fpn_1x.yml
and error occurs when executing:

File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/pzs/pzs/ShapeProp/shapeprop/tools/train_net.py", line 192, in
main()
File "/home/pzs/pzs/ShapeProp/shapeprop/tools/train_net.py", line 185, in main
model = train(cfg, args.local_rank, args.distributed)
File "/home/pzs/pzs/ShapeProp/shapeprop/tools/train_net.py", line 85, in train
arguments,
File "/home/pzs/pzs/ShapeProp/shapeprop/engine/trainer.py", line 69, in do_train
loss_dict = model(images, targets)
File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pzs/pzs/ShapeProp/shapeprop/modeling/detector/generalized_rcnn.py", line 56, in forward
x, result, detector_losses = self.roi_heads(features, proposals, targets)
File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pzs/pzs/ShapeProp/shapeprop/modeling/roi_heads/roi_heads.py", line 42, in forward
x, detections, loss_mask = self.mask(mask_features, detections, targets)
File "/home/pzs/.pyenv/versions/3.7.8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/pzs/pzs/ShapeProp/shapeprop/modeling/roi_heads/mask_head/mask_head.py", line 77, in forward
loss_mask = self.loss_evaluator(proposals, mask_logits, targets)
File "/home/pzs/pzs/ShapeProp/shapeprop/modeling/roi_heads/mask_head/loss.py", line 119, in call
labels, mask_targets, valid_inds = self.prepare_targets(proposals, targets)
File "/home/pzs/pzs/ShapeProp/shapeprop/modeling/roi_heads/mask_head/loss.py", line 91, in prepare_targets
valid_masks = (labels_per_image > 0) & matched_targets.get_field("valid_masks").to(dtype=torch.uint8)
RuntimeError: Expected object of scalar type Bool but got scalar type Byte for argument #2 'other' in call to _th_and

I think my coco datasets should be configured properly.
Ubuntu 20.04
CUDA 10.0(Nvidia 2080Ti)
PyTorch 1.4.0+cu100
Python 3.7.8

Generalization with less data experiment

Hi,

first of all, really nice work! I very much enjoyed reading it.

I'm working on a similar topic and wonder if you also uploaded the code for your experiment "Generalization with less data", shown in figure 6 of your work. I looked through your code but could not find it ad-hoc.

Best,
David,

compilation error and solution

I encounter the compilation error with the computer configuration:
cuda 10.0, pytorch1.1, python 3.7.
I do not know the meaning of Apex(#1564802), but i have solved my problem with this method: NVIDIA/apex#802 (comment)