I have included env.txt file in my submission to use the second environment but still getting this error.
Please help.
Hi,
That happens because the submission zip folder does not match the structure defined in the competition submission mechanism.
Your zip includes a folder with the files in it, please zip direct only the required files.
Please refer to the “Sample submission” in the “Participate” tab for more details about the required structure.
Neta,
MAFAT Challenge Team
I have again submitted with the suggested changes, it is still failing and this time without any error.
Please help.
Hi,
After that modifications, your submission runs in the "Secondary" environment, and that error: "ModuleNotFoundError: No module named 'mmengine'" is resolved.
Your submission still needs additional updates to be in the status "finished".
I recommend that you run your inference code locally on one of the frames of the training dataset, to verify the correctness of the code.
It seems now that your error comes from the "predict" function.
Neta,
MAFAT Challenge Team
Thanks for replying.
I have already tested for one frame.
Where can i see the exact error from the predict function? So that i can ensure its output in correct format.
Hi,
You can run this short code snippet demonstrating the inference pipeline (without statistic calibration and metadata), and see where and what the error is in your submission code:
from model import model
import cv2
image_path = '/content/images/126_0_1280.tiff'
predictor = model()
predictor.load('/content')
img = cv2.imread(image_path, -1)
print(img.shape)
res = predictor.predict(img, None)
print(res)
I hope this example will clear things out,
Neta,
MAFAT Challenge Team