Hi all,
I did export data training for deep learning and had a resulted folder(C:\Data\Deep_Learning\test_25Aug\esri_training_2).
My training bounding boxes have different size as figured
When I run the script:
data=prepare_data(training_deep, chip_size=448, batch_size=2, transforms=False)
data.show_batch()
It has an error as below. Could you please help me to fix it? Thank you.
~\AppData\Local\ESRI\conda\envs\arcgispro-py3-clone\lib\site-packages\matplotlib\cbook\__init__.py in _check_shape(_shape, **kwargs) 2291 2292 raise ValueError( -> 2293 f"{k!r} must be {len(target_shape)}D " 2294 f"with shape ({text_shape}). " 2295 f"Your input has shape {v.shape}." ValueError: 'vertices' must be 2D with shape (M, 2). Your input has shape (0,).
<Figure size 288x288 with 1 Axes>
Solved! Go to Solution.
Hi Sandeep,
I have fixed the error. I found out that my training polygon has the fields class, classValue, Confidence. When I deleted the field class and confidence, everything is normal.
Cheers,
Lien
Hi,
Can you paste the full error ?
Thanks,
Sandeep
Hi Sandeep,
I have fixed the error. I found out that my training polygon has the fields class, classValue, Confidence. When I deleted the field class and confidence, everything is normal.
Cheers,
Lien