search

waspinator / pycococreator

Helper functions to create COCO datasets
Apache License 2.0
765 stars 179 forks source link

/annotations/instances_valminusminival2018.json file missing #3

Open BennoStaub opened 6 years ago

BennoStaub commented 6 years ago

Trying to train Mask R CNN, I get the error that above file is missing. Did you try to use your created dataset for a model like Mask R CNN? Maybe there are more files missing. Eager to hear from you and thx.

waspinator commented 6 years ago

Everything needed to train should be there. I'll be publishing an article on how to use Matterport's Mask RCNN implementation on the shapes dataset next week, which should hopefully answer most of your questions.

hiankun commented 6 years ago

I am not sure whether my problem is the same one in this topic.

When I tried to run visualize_coco.ipynb, it said there's no file named instances_shape_train2018.json. Then I found it via your article in which I downloaded shapes_train_dataset to replace the one given by the Jupyter notebook example.

Maybe it's a good idea to update the examples/shapes/train content with corresponding json file, or indicate the download link in README.md?

gaqiness commented 6 years ago

It is not in GitHub, I think you can download from https://patrickwasp.com/wp-content/uploads/2018/04/shapes_train_dataset.zip

austinmw commented 6 years ago

You need to comment out the line in coco.py where it tries to load that (it's trying to append an additional set of data for training). Also change the import minival line to just import val. The reason for this is that the model authors used a bigger training set and smaller validation set than the split of the original data.