email_034-attachment-send-file-code-css

facebookresearch / mmd

ML models often mispredict, and it is hard to tell when and why. We present a data mining based approach to discover whether there is a certain form of data that particular causes the model to mispredict.

Summary


		Main Code: 743 LOC (11 files) = PY (100%) Secondary code: Test: 0 LOC (0); Generated: 0 LOC (0); Build & Deploy: 0 LOC (0); Other: 101 LOC (3);
		File Size: 0% long (>1000 LOC), 100% short (<= 200 LOC)
		Unit Size: 0% long (>100 LOC), 80% short (<= 10 LOC)
		Conditional Complexity: 0% complex (McCabe index > 50), 81% simple (McCabe index <= 5)
		Logical Component Decomposition: primary (2 components)
		Goals: Keep the system simple and easy to change (4)