train running

lib/models/generators/cnn.py

@@ -41,7 +41,7 @@ class CNNRouteGeneratorModel(LightningBaseModule):
         # 0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
         kld_loss = -0.5 * torch.sum(1 + logvar - mu.pow(2) - logvar.exp())
         # Dimensional Resizing
-        kld_loss /= self.in_shape
+        kld_loss /= reduce(mul, self.in_shape)
 
         loss = (kld_loss + discriminated_bce_loss) / 2
         return dict(loss=loss, log=dict(loss=loss,
@@ -65,7 +65,10 @@ class CNNRouteGeneratorModel(LightningBaseModule):
     def validation_step(self, *args):
         return self._test_val_step(*args)
 
-    def validation_epoch_end(self, outputs):
+    def validation_epoch_end(self, outputs: list):
+        return self._test_val_epoch_end(outputs)
+
+    def _test_val_epoch_end(self, outputs, test=False):
         evaluation = ROCEvaluation(plot_roc=True)
         pred_label = torch.cat([x['pred_label'] for x in outputs])
         labels = torch.cat([x['label'] for x in outputs]).unsqueeze(1)
@@ -73,8 +76,9 @@ class CNNRouteGeneratorModel(LightningBaseModule):
 
         # Sci-py call ROC eval call is eval(true_label, prediction)
         roc_auc, tpr, fpr = evaluation(labels.cpu().numpy(), pred_label.cpu().numpy(), )
-        # self.logger.log_metrics(score_dict)
-        self.logger.log_image(f'{self.name}_ROC-Curve_E{self.current_epoch}', plt.gcf())
+        if test:
+            # self.logger.log_metrics(score_dict)
+            self.logger.log_image(f'{self.name}_ROC-Curve_E{self.current_epoch}', plt.gcf())
         plt.clf()
         maps, trajectories, labels, val_restul_dict = self.generate_random()
 
@@ -88,6 +92,10 @@ class CNNRouteGeneratorModel(LightningBaseModule):
     def test_step(self, *args):
         return self._test_val_step(*args)
 
+    def test_epoch_end(self, outputs):
+        return self._test_val_epoch_end(outputs, test=True)
+
+
     @property
     def discriminator(self):
         if self._disc is None:
@@ -247,8 +255,15 @@ class CNNRouteGeneratorModel(LightningBaseModule):
         return z, mu, logvar
 
     def generate_random(self, n=6):
-        maps = [self.map_storage[choice(self.map_storage.keys)] for _ in range(n)]
-        trajectories = torch.stack([x.get_random_trajectory() for x in maps] * 2)
-        maps = torch.stack([x.as_2d_array for x in maps] * 2)
-        labels = torch.as_tensor([0] * n + [1] * n)
-        return maps, trajectories, labels, self._test_val_step(maps, trajectories, labels)
+        maps = [self.map_storage[choice(self.map_storage.keys_list)] for _ in range(n)]
+
+        trajectories = [x.get_random_trajectory() for x in maps] * 2
+        trajectories = [x.draw_in_array(self.map_storage.max_map_size) for x in trajectories]
+        trajectories = [torch.as_tensor(x, dtype=torch.float32) for x in trajectories]
+        trajectories = self._move_to_model_device(torch.stack(trajectories))
+
+        maps = [torch.as_tensor(x.as_array, dtype=torch.float32) for x in maps] * 2
+        maps = self._move_to_model_device(torch.stack(maps))
+
+        labels = self._move_to_model_device(torch.as_tensor([0] * n + [1] * n))
+        return maps, trajectories, labels, self._test_val_step(([maps, trajectories], labels), -9999)