README.md

@@ -4,7 +4,6 @@
 
 For more details about this package, make sure to see the documentation available at https://teklia.gitlab.io/atr/dan/.
 
-
 ## Installation
 
 To use DAN in your own scripts, install it using pip:
@@ -55,7 +54,9 @@ See the [dedicated section](https://teklia.gitlab.io/atr/dan/usage/datasets/form
 See the [dedicated section](https://teklia.gitlab.io/atr/dan/usage/train/) on the official DAN documentation.
 
 ### Synthetic data generation
+
 See the [dedicated section](https://teklia.gitlab.io/atr/dan/usage/generate/) on the official DAN documentation.
 
 ### Model prediction
+
 See the [dedicated section](https://teklia.gitlab.io/atr/dan/usage/predict/) on the official DAN documentation.

dan/manager/metrics.py

@@ -152,8 +152,6 @@ class MetricManager:
                 "loss",
                 "loss_ctc",
                 "loss_ce",
-                "syn_max_lines",
-                "syn_prob_lines",
             ]:
                 value = float(
                     np.average(
@@ -225,8 +223,6 @@ class MetricManager:
                 "loss_ctc",
                 "loss_ce",
                 "loss",
-                "syn_max_lines",
-                "syn_prob_lines",
             ]:
                 metrics[metric_name] = [
                     values[metric_name],

dan/manager/training.py

@@ -1188,12 +1188,6 @@ class Manager(OCRManager):
             "str_x": str_x,
             "loss": sum_loss.item(),
             "loss_ce": loss_ce.item(),
-            "syn_max_lines": self.dataset.train_dataset.get_syn_max_lines()
-            if self.params["dataset_params"]["config"]["synthetic_data"]
-            else 0,
-            "syn_prob_lines": self.dataset.train_dataset.get_syn_proba_lines()
-            if self.params["dataset_params"]["config"]["synthetic_data"]
-            else 0,
         }
 
         return values
@@ -1247,10 +1241,6 @@ class Manager(OCRManager):
             else:
                 features = self.models["encoder"](x)
             features_size = features.size()
-            coverage_vector = torch.zeros(
-                (features.size(0), 1, features.size(2), features.size(3)),
-                device=self.device,
-            )
             pos_features = self.models["decoder"].features_updater.get_pos_features(
                 features
             )
@@ -1279,7 +1269,6 @@ class Manager(OCRManager):
                 confidence_scores.append(
                     torch.max(torch.softmax(pred[:, :], dim=1), dim=1).values
                 )
-                coverage_vector = torch.clamp(coverage_vector + weights, 0, 1)
                 predicted_tokens = torch.cat(
                     [
                         predicted_tokens,

dan/ocr/document/train.py

@@ -212,8 +212,6 @@ def get_config():
                 "cer",
                 "wer",
                 "wer_no_punct",
-                "syn_max_lines",
-                "syn_prob_lines",
             ],  # Metrics name for training
             "eval_metrics": [
                 "cer",

dan/predict/prediction.py

@@ -148,10 +148,6 @@ class DAN:
 
             features = self.encoder(input_tensor.float())
             features_size = features.size()
-            coverage_vector = torch.zeros(
-                (features.size(0), 1, features.size(2), features.size(3)),
-                device=self.device,
-            )
             pos_features = self.decoder.features_updater.get_pos_features(features)
             features = torch.flatten(pos_features, start_dim=2, end_dim=3).permute(
                 2, 0, 1
@@ -179,7 +175,6 @@ class DAN:
                 confidence_scores.append(
                     torch.max(torch.softmax(pred[:, :], dim=1), dim=1).values
                 )
-                coverage_vector = torch.clamp(coverage_vector + weights, 0, 1)
                 predicted_tokens = torch.cat(
                     [
                         predicted_tokens,

dan/schedulers.py

@@ -41,7 +41,3 @@ def exponential_dropout_scheduler(dropout_rate, step, max_step):
 def exponential_scheduler(init_value, end_value, step, max_step):
     step = min(step, max_step - 1)
     return init_value - (init_value - end_value) * (1 - np.exp(-10 * step / max_step))
-
-
-def linear_scheduler(init_value, end_value, step, max_step):
-    return init_value + step * (end_value - init_value) / max_step