- nb_total = input.size(0)
- nb_correct = (input == result).long().min(1).values.sum()
-
- #######################################################################
- # Comput predicted vs. true variable values
-
- 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])
-
- filename = os.path.join(result_dir, f"expr_result_{n_epoch:04d}.txt")
-
- with open(filename, "w") as f:
- for i, r in zip(values_input, values_result):
- for n, vi in i.items():
- vr = r.get(n)
- f.write(f"{vi} {-1 if vr is None else vr}\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[:10000])
-
- logger(
- 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)):
- logger(
- f"error_value {n_epoch} delta {d} {test_nb_delta[d]} {test_nb_delta[d]*100/nb_total:.02f}%"
- )
- logger(
- f"error_value {n_epoch} missed {test_nb_missed} {test_nb_missed*100/nb_total:.02f}%"
- )
-
- ##############################################################
- # Log a few generated sequences
- if input_file is None:
- input = self.test_input[:10]
- else:
- with open(input_file, "r") as f:
- sequences = [e.strip() for e in f.readlines()]
- sequences = [s + " " + "#" * 50 for s in sequences]
- input = self.tensorize(sequences)
-
- result = input.clone()
- s = (result == self.space).long()
- ar_mask = (s.cumsum(dim=1) - s).clamp(min=0, max=1)
- result = (1 - ar_mask) * result + ar_mask * self.filler
-
- for n in range(result.size(0)):
- logger(f"test_before {self.seq2str(result[n])}")
-
- masked_inplace_autoregression(
- model,
- self.batch_size,
- result,
- ar_mask,
- deterministic_synthesis,
- device=self.device,
- )
-
- 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 ""
- logger(f"test_after {self.seq2str(result[n])} {comment}")
- logger(f"truth {self.seq2str(correct[n])}")
- ##############################################################
-
-
-######################################################################
-
-import world
-
-
-class World(Task):
- def __init__(
- self,
- nb_train_samples,
- nb_test_samples,
- batch_size,
- vqae_nb_epochs,
- logger=None,
- device=torch.device("cpu"),
- device_storage=torch.device("cpu"),
- ):
- super().__init__()
-
- self.batch_size = batch_size
- self.device = device
-
- (
- train_frames,
- train_action_seq,
- test_frames,
- test_action_seq,
- self.frame2seq,
- self.seq2frame,
- ) = world.create_data_and_processors(
- nb_train_samples,
- nb_test_samples,
- mode="first_last",
- nb_steps=30,
- nb_epochs=vqae_nb_epochs,
- logger=logger,
- device=device,
- device_storage=device_storage,
- )
-
- train_frame_seq = self.frame2seq(train_frames).to(device_storage)
- test_frame_seq = self.frame2seq(test_frames).to(device_storage)
-
- nb_frame_codes = max(train_frame_seq.max(), test_frame_seq.max()) + 1
- nb_action_codes = max(train_action_seq.max(), test_action_seq.max()) + 1
-
- self.len_frame_seq = train_frame_seq.size(1)
- self.len_action_seq = train_action_seq.size(1)
- self.nb_codes = nb_frame_codes + nb_action_codes
-
- train_frame_seq = train_frame_seq.reshape(train_frame_seq.size(0) // 2, 2, -1)
-
- train_action_seq += nb_frame_codes
- self.train_input = torch.cat(
- (train_frame_seq[:, 0, :], train_action_seq, train_frame_seq[:, 1, :]), 1
- )
-
- test_frame_seq = test_frame_seq.reshape(test_frame_seq.size(0) // 2, 2, -1)
- test_action_seq += nb_frame_codes
- self.test_input = torch.cat(
- (test_frame_seq[:, 0, :], test_action_seq, test_frame_seq[:, 1, :]), 1
- )
-
- def batches(self, split="train", nb_to_use=-1, desc=None):
- assert split in {"train", "test"}
- input = self.train_input if split == "train" else self.test_input
- if nb_to_use > 0:
- input = input[:nb_to_use]
- if desc is None:
- desc = f"epoch-{split}"
- for batch in tqdm.tqdm(
- input.split(self.batch_size), dynamic_ncols=True, desc=desc
- ):
- yield batch.to(self.device)
-
- def vocabulary_size(self):
- return self.nb_codes
-
- def produce_results(
- self, n_epoch, model, result_dir, logger, deterministic_synthesis
- ):
- k = torch.arange(
- 2 * self.len_frame_seq + self.len_action_seq, device=self.device
- )[None, :]
-
- input = self.test_input[:64].to(self.device)
- result = input.clone()
-
- ar_mask = (
- (k >= self.len_frame_seq + self.len_action_seq).long().expand_as(result)
- )
- result *= 1 - ar_mask
-
- masked_inplace_autoregression(
- model,
- self.batch_size,
- result,
- ar_mask,
- deterministic_synthesis,
- device=self.device,
- )