valeriozhang

@aamangeldi hellooo good sir yes. - AIRFLOW__CORE__REMOTE_LOGGING=True - AIRFLOW__CORE__REMOTE_BASE_LOG_FOLDER=s3://my-bucket/logs - AIRFLOW__CORE__ENCRYPT_S3_LOGS=False - AWS_ACCESS_KEY_ID=XXXXXX - AWS_SECRET_ACCESS_KEY=XXXXXXX all i did was hard code in the AWS keys. not smart at all. you...

go to venv/lib/python3.7/site-packages/django/db/backends/sqlite3/base.py change def check_sqlite_version(): if Database.sqlite_version_info < (3, 8, 3): raise ImproperlyConfigured('SQLite 3.8.3 or later is required (found %s).' % to def check_sqlite_version(): if Database.sqlite_version_info < (3, 8,...

Thanks for the quick response! If i comment out the entire dataset_show sections. ``` # dataset_show = PANDADataset(df_train, image_size, n_tiles, 0, transform=transforms_train) # from pylab import rcParams # rcParams['figure.figsize'] =...

[train_famdata-kfolds.zip](https://github.com/kentaroy47/Kaggle-PANDA-1st-place-solution/files/9374176/train_famdata-kfolds.zip)

running it again with the dataset visualization gives the following error (identical to the 5-fold-models error). im not sure why the error message changed.with the dataset code. what file format...

By commenting out that line, i can get the correct shape. BUT, it will give a dimension issue for the visualization. `error: OpenCV(4.2.0) /io/opencv/modules/core/src/copy.cpp:998: error: (-215:Assertion failed) _src.dims() Invalid number...

Yes, the output from `python data_process/a00_save_tiles.py` says that, but` images.shape` is not giving the correct shape. could it be something to do with the transpositions in in the PANDADataset class?