search

lkevinzc / dance

Codes for "DANCE: A Deep Attentive Contour Model for Efficient Instance Segmentation", WACV2021
67 stars 13 forks source link

Face an error when running author's code #5

Closed Archer222arc closed 3 years ago

Archer222arc commented 3 years ago

Traceback (most recent call last): File "train_net.py", line 14, in import core.data # noqa File "/public/home/archer/dance/core/init.py", line 1, in from core import modeling File "/public/home/archer/dance/core/modeling/init.py", line 1, in from .fcos import FCOS File "/public/home/archer/dance/core/modeling/fcos/init.py", line 1, in from .fcos import FCOS File "/public/home/archer/dance/core/modeling/fcos/fcos.py", line 10, in from core.layers import DFConv2d, IOULoss File "/public/home/archer/dance/core/layers/init.py", line 4, in from .extreme_utils import _ext as extreme_utils ImportError: cannot import name '_ext' from 'core.layers.extreme_utils' (/public/home/archer/dance/core/layers/extreme_utils/init.py) And I find there's nothing in init.py

lkevinzc commented 3 years ago

Hi @Archer222arc , thanks for your interest. To run, you need to first build and install the package, as mentioned in the README:

Archer222arc commented 3 years ago

Thank you for help! The above problems is solved and I have another problem. Since the evaluation relies on "edge.json", I've tried using prepare_edge_map.py to generate the corresponding json file consisting of edges of COCOval2017 but failed. More specifically, the annotations_val2017.json's "annotation":[] information does not include "file_name". I'm a new to handle this kind of problem. Could you please give some help? Thank you.

lkevinzc commented 3 years ago

Hi @Archer222arc , actually, when you run prepare_edge_map.py, both training and evaluation data will be process (see this line of code. As long as you have the coco train and eval folders correctly, it should generate edge map data for both train and eval set.