self.device = device
train_sequences = expr.generate_sequences(
- nb_train_samples, nb_variables=nb_variables, length=2*sequence_length, randomize_length=True,
+ nb_train_samples,
+ nb_variables=nb_variables,
+ length=sequence_length,
+ # length=2 * sequence_length,
+ # randomize_length=True,
)
test_sequences = expr.generate_sequences(
- nb_test_samples, nb_variables=nb_variables, length=sequence_length,
+ nb_test_samples,
+ nb_variables=nb_variables,
+ length=sequence_length,
)
self.char2id = dict(
[
input.split(self.batch_size), dynamic_ncols=True, desc=desc
):
if split == "train":
- last=(batch!=self.filler).max(0).values.nonzero().max()+1
- batch=batch[:,:last]
+ last = (batch != self.filler).max(0).values.nonzero().max() + 1
+ batch = batch[:, :last]
yield batch
def vocabulary_size(self):
nb_total = input.size(0)
nb_correct = (input == result).long().min(1).values.sum()
- return nb_total, nb_correct
+ #######################################################################
+ # Comput predicted vs. true variable values
- test_nb_total, test_nb_correct = compute_nb_correct(self.test_input[:1000])
+ nb_delta = torch.zeros(5, dtype=torch.int64)
+ nb_missed = 0
+
+ values_input = expr.extract_results([self.seq2str(s) for s in input])
+ values_result = expr.extract_results([self.seq2str(s) for s in result])
+
+ for i, r in zip(values_input, values_result):
+ for n, vi in i.items():
+ vr = r.get(n)
+ if vr is None or vr < 0:
+ nb_missed += 1
+ else:
+ d = abs(vr - vi)
+ if d >= nb_delta.size(0):
+ nb_missed += 1
+ else:
+ nb_delta[d] += 1
+
+ ######################################################################
+
+ return nb_total, nb_correct, nb_delta, nb_missed
+
+ (
+ test_nb_total,
+ test_nb_correct,
+ test_nb_delta,
+ test_nb_missed,
+ ) = compute_nb_correct(self.test_input[:1000])
log_string(
f"accuracy_test {n_epoch} nb_total {test_nb_total} nb_correct {test_nb_correct} accuracy {(100.0*test_nb_correct)/test_nb_total:.02f}%"
)
+ nb_total = test_nb_delta.sum() + test_nb_missed
+ for d in range(test_nb_delta.size(0)):
+ log_string(
+ f"error_value {n_epoch} delta {d} {test_nb_delta[d]} {test_nb_delta[d]*100/nb_total:.02f}%"
+ )
+ log_string(
+ f"error_value {n_epoch} missed {test_nb_missed} {test_nb_missed*100/nb_total:.02f}%"
+ )
+
##############################################################
# Log a few generated sequences
input = self.test_input[:10]
)
correct = (1 - ar_mask) * self.space + ar_mask * input
for n in range(result.size(0)):
- comment="GOOD" if (result[n]-input[n]).abs().max()==0 else ""
+ comment = "GOOD" if (result[n] - input[n]).abs().max() == 0 else ""
log_string(f"test_after {self.seq2str(result[n])} {comment}")
log_string(f"correct {self.seq2str(correct[n])}")
##############################################################