Opencv new dataset vs Explicit dataset vs old dataset comparison

Comparing which circuits do the brains complete

Model	Dataset	Montmeló	Simple circuit no red line	Simple circuit no line no wall	Simple circuit white road	Simple circuit white road no line
Explicit	-	✅	❌	❌	✅	❌
OpenCV	-	✅	❌	❌	✅	❌
PilotNet	Old	✅	❌	✅	✅	❌
PilotNet	Explicit	✅	❌(last turns)	❌(some turns ok)	✅	❌
PilotNet	OpenCV(fastest)	✅(lowering rate much)	❌	❌	✅	❌
Deepest LSTM	Old	✅	❌	✅	❌	❌
Deepest LSTM	Explicit	✅	❌	❌	✅	❌
Deepest LSTM	OpenCV(fastest)	✅(lowering rate)	❌	✅(over the grass)	✅	❌
Frankenstein	Old	✅(lowering rate)	✅	✅(over the grass	✅	❌
Frankenstein	Explicit	✅	❌	❌	✅	❌
Frankenstein	OpenCV(fastest)	-	-	-	-	-
PilotNet 3D	Old	✅(lowering rate)	❌	❌	✅	❌
PilotNet 3D	Explicit	❌	❌	❌	❌	❌
PilotNet 3D	OpenCV(fastest)	-	-	-	-	-

Comparing stats values

Model	Dataset	MAE train	MAE val	MSE train	MSE val
PilotNet	Old	5.16e⁻3	0.028	2.6e⁻4	5.63e⁻3
PilotNet	Explicit	2.39e⁻3	3.03e⁻3	5.39e⁻3	4.39e⁻3
PilotNet	OpenCV(fastest)	4.40e⁻3	5.46e⁻3	1.67e⁻3	6.45e⁻3
Deepest LSTM	Old	-	0.047	-	8.27e⁻3
Deepest LSTM	Explicit	0.023	0.02	3.73e⁻3	3.39e⁻3
Deepest LSTM	OpenCV(fastest)	0.018	0.016	4.16e⁻3	3.82e⁻3
Frankenstein	Old	0.032	0.044	3.49e⁻3	6.32e⁻3
Frankenstein	Explicit	0.016	0.015	2.05e⁻3	2.14e⁻3
Frankenstein	OpenCV(fastest)	0.019	0.018	3.9e⁻3	3.5e⁻3

Comparing V and W of each brain

Dataset	V min	V max	W min	W max
Old	-0.6	13	-3	3
Explicit	-0.6	13	-3	3
OpenCV(fastest)	6.5	24	-7.1	7.1

Comparing dataset cases distribution for V and W

Old dataset

Old dataset time distributed

Explicit dataset

Explicit dataset time distributed

OpenCV dataset

OpenCV dataset time distributed