This is an open source project for the stage E of the Hamoye Data Science Internship program, cohort 2020, with real life applications in the health, engineering, demography, education and technology.
4
stars
17
forks
source link
Calculated the f1_score between output of padding and blender #40
Made a mistake in the previous blender. Calculated the f1_score between the output of union of CNN and LSTM and the blender, instead of between output of padding and blender. This seems to be the best basic for comparing the f1_score with those of CNN and LSTM.
This blending ensemble improved LSTM's f1_score by 0.03
Made a mistake in the previous blender. Calculated the f1_score between the output of union of CNN and LSTM and the blender, instead of between output of padding and blender. This seems to be the best basic for comparing the f1_score with those of CNN and LSTM.
This blending ensemble improved LSTM's f1_score by 0.03
Find the notebook here