Update input_preprocess.py

input_preprocess.py

@@ -16,19 +16,6 @@ import pickle
 import DeepMIMOv3
 import torch
 
-def set_random_seed(seed=42):
-    torch.manual_seed(seed)
-    np.random.seed(seed)
-    #random.seed(seed)
-    if torch.cuda.is_available():
-        torch.cuda.manual_seed_all(seed)
-    # Ensures deterministic behavior
-    torch.backends.cudnn.deterministic = True
-    torch.backends.cudnn.benchmark = False
-
-# Apply random seed
-set_random_seed()
-
 #%% Scenarios List
 def scenarios_list():
     """Returns an array of available scenarios."""
@@ -208,7 +195,6 @@ def get_parameters(scenario):
     
     return parameters, row_column_users, n_ant_bs, n_ant_ue, n_subcarriers
 
-
 #%% Sample Generation
 def make_sample(user_idx, patch, word2id, n_patches, n_masks, patch_size, gen_raw=False):
     """
@@ -226,7 +212,6 @@ def make_sample(user_idx, patch, word2id, n_patches, n_masks, patch_size, gen_ra
     Returns:
         sample (list): Generated sample for the user.
     """
-    set_random_seed()
     
     tokens = patch[user_idx]
     input_ids = np.vstack((word2id['[CLS]'], tokens))
@@ -246,8 +231,7 @@ def make_sample(user_idx, patch, word2id, n_patches, n_masks, patch_size, gen_ra
                 input_ids[pos] = np.random.rand(patch_size)
             elif rnd_num < 0.9:
                 input_ids[pos] = word2id['[MASK]']
-    #if user_idx == 0:            
-    #    print(f'masked_pos: {masked_pos}')
+                
     return [input_ids, masked_tokens, masked_pos]
 
 
@@ -323,8 +307,7 @@ def load_var(path):
     
     return var
 
-#%%
-
+#%% Label Generation
 def label_gen(task, data, scenario, n_beams=64):
     
     idxs = np.where(data['user']['LoS'] != -1)[0]
@@ -364,13 +347,10 @@ def label_gen(task, data, scenario, n_beams=64):
     return label.astype(int)
 
 def steering_vec(array, phi=0, theta=0, kd=np.pi):
-    # phi = azimuth
-    # theta = elevation
     idxs = DeepMIMOv3.ant_indices(array)
     resp = DeepMIMOv3.array_response(idxs, phi, theta+np.pi/2, kd)
     return resp / np.linalg.norm(resp)
 
-
 def label_prepend(deepmimo_data, preprocessed_chs, task, scenario_idxs, n_beams=64):
     labels = []
     for scenario_idx in scenario_idxs: