adjustment fot CCS

_parameters.ini

@@ -19,9 +19,6 @@ sr = 16000
 hop_length = 128
 n_fft = 256
 
-sample_segment_len=50
-sample_hop_len=20
-
 random_apply_chance = 0.7
 loudness_ratio = 0.0
 shift_ratio = 0.3
@@ -51,7 +48,7 @@ use_norm = True
 dropout = 0.2
 lat_dim = 32
 features = 64
-filters = [16, 32, 64, 128]
+filters = [16, 32, 64]
 
 [VisualTransformer]
 weight_init = xavier_normal_

models/cnn_baseline.py

@@ -14,10 +14,12 @@ class CNNBaseline(CombinedModelMixins,
                   LightningBaseModule
                   ):
 
-    def __init__(self, in_shape, n_classes, weight_init, activation, use_bias, use_norm, dropout, lat_dim, features,
+    def __init__(self, in_shape, n_classes, weight_init, activation,
+                 use_bias, use_norm, dropout, lat_dim, features,
                  filters,
                  lr, weight_decay, sto_weight_avg, lr_warm_restart_epochs, opt_reset_interval,
-                 loss, scheduler):
+                 loss, scheduler, lr_scheduler_parameter
+                 ):
 
         # TODO: Move this to parent class, or make it much easieer to access....
         a = dict(locals())

models/transformer_model.py

@@ -21,7 +21,7 @@ class VisualTransformer(CombinedModelMixins,
                         ):
 
     def __init__(self, in_shape, n_classes, weight_init, activation,
-                 embedding_size, heads, attn_depth, patch_size, use_residual,
+                 embedding_size, heads, attn_depth, patch_size, use_residual, variable_length,
                  use_bias, use_norm, dropout, lat_dim, loss, scheduler, mlp_dim, head_dim,
                  lr, weight_decay, sto_weight_avg, lr_scheduler_parameter, opt_reset_interval):
 
@@ -88,15 +88,18 @@ class VisualTransformer(CombinedModelMixins,
         tensor = self.autopad(x)
         p = self.params.patch_size
 
-        tensor = rearrange(tensor, 'b c (h p1) (w p2) -> b (w h) (p1 p2 c)', p1=p, p2=p)
+        tensor = rearrange(tensor, 'b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1=p, p2=p)
         b, n, _ = tensor.shape
 
-        # mask
+        if self.params.variable_length and mask is None:
-        lengths = torch.count_nonzero(tensor, dim=-1)
+            # mask
-        mask = (lengths == torch.zeros_like(lengths))
+            lengths = torch.count_nonzero(tensor, dim=-1)
-        # CLS-token awareness
+            mask = (lengths == torch.zeros_like(lengths))
-        # mask = torch.cat((torch.zeros(b, 1), mask), dim=-1)
+            # CLS-token awareness
-        # mask = repeat(mask, 'b n -> b n', h=self.params.heads)
+            # mask = torch.cat((torch.zeros(b, 1), mask), dim=-1)
+            # mask = repeat(mask, 'b n -> b n', h=self.params.heads)
+        else:
+            mask = mask
 
         tensor = self.patch_to_embedding(tensor)
 

multi_run.py

@@ -14,21 +14,24 @@ if __name__ == '__main__':
                         model_name=['VisualTransformer'],
                         batch_size=[50],
                         max_epochs=[200],
-                        random_apply_chance=[0.3],  # trial.suggest_float('random_apply_chance', 0.1, 0.5, step=0.1),
+                        variable_length=[False],
+                        sample_segment_len=[40],
+                        sample_hop_len=[15],
+                        random_apply_chance=[0.5],  # trial.suggest_float('random_apply_chance', 0.1, 0.5, step=0.1),
                         loudness_ratio=[0],  # trial.suggest_float('loudness_ratio', 0.0, 0.5, step=0.1),
                         shift_ratio=[0.3],  # trial.suggest_float('shift_ratio', 0.0, 0.5, step=0.1),
                         noise_ratio=[0.3],  # trial.suggest_float('noise_ratio', 0.0, 0.5, step=0.1),
                         mask_ratio=[0.3],  # trial.suggest_float('mask_ratio', 0.0, 0.5, step=0.1),
-                        lr=[2e-3],  # trial.suggest_uniform('lr', 1e-3, 3e-3),
+                        lr=[1e-3],  # trial.suggest_uniform('lr', 1e-3, 3e-3),
                         dropout=[0.2],  # trial.suggest_float('dropout', 0.0, 0.3, step=0.05),
                         lat_dim=[32],  # 2 ** trial.suggest_int('lat_dim', 1, 5, step=1),
                         mlp_dim=[16],  # 2 ** trial.suggest_int('mlp_dim', 1, 5, step=1),
                         head_dim=[6],  # 2 ** trial.suggest_int('head_dim', 1, 5, step=1),
                         patch_size=[12],  # trial.suggest_int('patch_size', 6, 12, step=3),
-                        attn_depth=[10],  # trial.suggest_int('attn_depth', 2, 14, step=4),
+                        attn_depth=[12],  # trial.suggest_int('attn_depth', 2, 14, step=4),
                         heads=[6],  # trial.suggest_int('heads', 2, 16, step=2),
-                        scheduler=['CosineAnnealingWarmRestarts'],  # trial.suggest_categorical('scheduler', [None, 'LambdaLR']),
+                        scheduler=['LambdaLR'],  # trial.suggest_categorical('scheduler', [None, 'LambdaLR']),
-                        lr_scheduler_parameter=[5],  # [0.98],
+                        lr_scheduler_parameter=[0.95],  # [0.98],
                         embedding_size=[30],  # trial.suggest_int('embedding_size', 12, 64, step=12),
                         loss=['ce_loss'],
                         sampler=['WeightedRandomSampler'],
@@ -40,7 +43,7 @@ if __name__ == '__main__':
     permutations_dicts = [dict(zip(keys, v)) for v in itertools.product(*values)]
     for permutations_dict in tqdm(permutations_dicts, total=len(permutations_dicts)):
         # Parse comandline args, read config and get model
-        cmd_args, found_data_class, found_model_class = parse_comandline_args_add_defaults(
+        cmd_args, found_data_class, found_model_class, found_seed = parse_comandline_args_add_defaults(
             '_parameters.ini', overrides=permutations_dict)
 
         hparams = dict(**cmd_args)
@@ -50,6 +53,6 @@ if __name__ == '__main__':
         # RUN
         # ---------------------------------------
         print(f'Running Loop, parameters are: {permutations_dict}')
-        run_lightning_loop(hparams, found_data_class, found_model_class)
+        run_lightning_loop(hparams, found_data_class, found_model_class, seed=found_seed)
         print(f'Done, parameters were: {permutations_dict}')
         pass

util/module_mixins.py

@@ -148,7 +148,7 @@ class TestMixin:
         class_names = {val: key for val, key in enumerate(['background', 'chimpanze', 'geunon', 'mandrille', 'redcap'])}
 
         df = pd.DataFrame(data=dict(filename=[Path(x).name for x in sorted_y.keys()],
-                                    prediction=y_max.cpu().numpy()))
+                                    prediction=[class_names[x.item()] for x in y_max.cpu()]))
         result_file = Path(self.logger.log_dir / 'predictions.csv')
         if result_file.exists():
             try: