Fix typos

training.py

@@ -33,12 +33,12 @@ print(PATH)
 #%%
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 multigpu = True
-# In[ ]:
+#
 DATASET = 'HN_val'
 BBOX_SUBDATASET = 'bbox_64'
 
 DATASET_DIR = PATH / 'data' / DATASET / 'processed' / 'bbox' / BBOX_SUBDATASET
-EXPERIMENT_DIR = PATH / 'experiment'
+EXPERIMENT_DIR = PATH / 'experiments'
 
 PRETRAINED_MED3D_WEIGHTS = PATH / 'pretrained_weights' / 'resnet_50.pth'
 PRETRAINED_T_STAGE = EXPERIMENT_DIR / 'Tstage_4_noTx_CT_20191114-163418' / 'weights.pth'
@@ -62,7 +62,7 @@ settings = {
 }
 
 assert settings["split"] in ["vallieres", "8020"]
-assert not settings["splits"] == "vallieres" or DATASET == 'HN_val'
+assert not settings["split"] == "vallieres" or DATASET == 'HN_val'
 assert settings["pretrained"] in ["Med3D", "branch-wise", "T-stage", ""]
 
 os.makedirs(EXPERIMENT_DIR / EXPERIMENT_NAME, exist_ok=False)
@@ -107,7 +107,7 @@ np.random.seed(SEED)
 
 dataset_train = NumpyCSVDataset(
     data_dir=DATASET_DIR,
-    clinical_file=clinical_data,
+    clinical_file=clinical_file,
     label_col=target_column,
     size=SIZE,
     mode='train',
@@ -116,7 +116,7 @@ dataset_train = NumpyCSVDataset(
 
 dataset_test = NumpyCSVDataset(
     data_dir=DATASET_DIR,
-    clinical_file=clinical_data,
+    clinical_file=clinical_file,
     label_col=target_column,
     size=SIZE,
     mode='test',
@@ -145,15 +145,6 @@ else:
 dataset_train.indices = np.array(idx_train)
 dataset_test.indices = np.array(idx_test)
 # %%
-# Check class balance
-labels_train = dataset_train.labels
-labels_test = dataset_test.labels
-
-c, n = np.unique(labels_train, return_counts=True)
-print(np.c_[c, n / len(labels_train)])
-c, n = np.unique(labels_test, return_counts=True)
-print(np.c_[c, n / len(labels_test)])
-# %%
 # Create loaders
 loader_train = DataLoader(
     dataset_train, batch_size=BATCH_SIZE, num_workers=12, pin_memory=True, shuffle=True
@@ -164,15 +155,12 @@ loader_test = DataLoader(
 )
 
 # %%
-# Compute weights
+# Compute weights only on training set
 labels_train = dataset_train.labels
 
-# class_sample_count = np.array([len(np.where( labels == t )[0]) for t in np.unique( labels )])
 _, class_sample_count = np.unique(labels_train, return_counts=True)
-n_min = np.min(class_sample_count)
-weights = (
-    n_min / class_sample_count
-)  # versione proporzionale, usare n_min invece che 1 per pesi ~1
+n_max = np.max(class_sample_count)
+weights = n_max / class_sample_count
 weights = torch.Tensor(weights).to(device)
 # %%
 # ### Initialize Model
@@ -487,3 +475,4 @@ metrics_out.to_csv(EXPERIMENT_DIR / EXPERIMENT_NAME / 'metrics_out.csv')
 
 # Save model weights
 torch.save(model.state_dict(), EXPERIMENT_DIR / EXPERIMENT_NAME / 'weights.pth')
+# %%