Open bayerj opened 15 years ago
And has to be corrected:
[ RUN ] TestGradient.LstmLayer New Parametrized instance. Numeric/Analytical:-0 <-> 0 Numeric/Analytical:-0 <-> 0 Numeric/Analytical:-0 <-> 2.11224 Numeric/Analytical:-0 <-> 0 Expected: (0.001) > (gradient_check(*net_p, true)), actual: 0.001 vs 2.11224
However, the examples give the same solutions as PyBrain. Or?
This is due to gradient_check not being able to handle sequential modules so far.
And has to be corrected:
However, the examples give the same solutions as PyBrain. Or?