Merge branch 'disentangling_only' into disentangling_only_py3.8

# Conflicts:
#	models/model.py

3 files changed, 37 insertions, 10 deletions

diff --git a/utils/configuration.py b/utils/configuration.py
index 340815b..46149b3 100644
--- a/utils/configuration.py
+++ b/utils/configuration.py
@@ -8,6 +8,7 @@ class SystemConfiguration(TypedDict):
     CUDA_VISIBLE_DEVICES: str
     save_dir: str
     image_log_on: bool
+    val_size: int
 
 
 class DatasetConfiguration(TypedDict):
@@ -35,7 +36,6 @@ class ModelHPConfiguration(TypedDict):
 
 
 class OptimizerHPConfiguration(TypedDict):
-    start_iter: int
     lr: int
     betas: Tuple[float, float]
     eps: float
@@ -44,8 +44,8 @@ class OptimizerHPConfiguration(TypedDict):
 
 
 class SchedulerHPConfiguration(TypedDict):
-    step_size: int
-    gamma: float
+    start_step: int
+    final_gamma: float
 
 
 class HyperparameterConfiguration(TypedDict):
diff --git a/utils/dataset.py b/utils/dataset.py
index 72cf050..41e2f1e 100644
--- a/utils/dataset.py
+++ b/utils/dataset.py
@@ -111,9 +111,9 @@ class CASIAB(data.Dataset):
         #     in Bag #2 condition from 90 degree angle
         classes, conditions, views = [], [], []
         if selector:
-            selected_classes = selector.pop('classes', None)
-            selected_conditions = selector.pop('conditions', None)
-            selected_views = selector.pop('views', None)
+            selected_classes = selector.get('classes', None)
+            selected_conditions = selector.get('conditions', None)
+            selected_views = selector.get('views', None)
 
             class_regex = r'\d{3}'
             condition_regex = r'(nm|bg|cl)-0[0-6]'
diff --git a/utils/sampler.py b/utils/sampler.py
index 0977f94..581d7a2 100644
--- a/utils/sampler.py
+++ b/utils/sampler.py
@@ -15,7 +15,18 @@ class TripletSampler(data.Sampler):
     ):
         super().__init__(data_source)
         self.metadata_labels = data_source.metadata['labels']
+        metadata_conditions = data_source.metadata['conditions']
+        self.subsets = {}
+        for condition in metadata_conditions:
+            pre, _ = condition.split('-')
+            if self.subsets.get(pre, None) is None:
+                self.subsets[pre] = []
+            self.subsets[pre].append(condition)
+        self.num_subsets = len(self.subsets)
+        self.num_seq = {pre: len(seq) for (pre, seq) in self.subsets.items()}
+        self.min_num_seq = min(self.num_seq.values())
         self.labels = data_source.labels
+        self.conditions = data_source.conditions
         self.length = len(self.labels)
         self.indexes = np.arange(0, self.length)
         (self.pr, self.k) = batch_size
@@ -26,15 +37,31 @@ class TripletSampler(data.Sampler):
             # Sample pr subjects by sampling labels appeared in dataset
             sampled_subjects = random.sample(self.metadata_labels, k=self.pr)
             for label in sampled_subjects:
-                clips_from_subject = self.indexes[self.labels == label].tolist()
+                mask = self.labels == label
+                # Fix unbalanced datasets
+                if self.num_subsets > 1:
+                    condition_mask = np.zeros(self.conditions.shape, dtype=bool)
+                    for num, conditions_ in zip(
+                            self.num_seq.values(), self.subsets.values()
+                    ):
+                        if num > self.min_num_seq:
+                            conditions = random.sample(
+                                conditions_, self.min_num_seq
+                            )
+                        else:
+                            conditions = conditions_
+                        for condition in conditions:
+                            condition_mask |= self.conditions == condition
+                    mask &= condition_mask
+                clips = self.indexes[mask].tolist()
                 # Sample k clips from the subject without replacement if
                 # have enough clips, k more clips will sampled for
                 # disentanglement
                 k = self.k * 2
-                if len(clips_from_subject) >= k:
-                    _sampled_indexes = random.sample(clips_from_subject, k=k)
+                if len(clips) >= k:
+                    _sampled_indexes = random.sample(clips, k=k)
                 else:
-                    _sampled_indexes = random.choices(clips_from_subject, k=k)
+                    _sampled_indexes = random.choices(clips, k=k)
                 sampled_indexes += _sampled_indexes
 
             yield sampled_indexes