[General] Rebuild folders with a simpler layout.

.gitignore

@@ -1,4 +1,4 @@
 .DS_Store
-
+.idea/
 venv/
 __pycache__/

ercbcm/ERCBCM.py

@@ -0,0 +1,14 @@
+from torch import nn
+from transformers import BertForSequenceClassification
+
+class ERCBCM(nn.Module):
+  
+    def __init__(self):
+        super(ERCBCM, self).__init__()
+        print('>>> ERCBCM Init!')
+
+        self.bert_base = BertForSequenceClassification.from_pretrained('bert-base-uncased')
+
+    def forward(self, text, label):
+        loss, text_fea = self.bert_base(text, labels=label)[:2]
+        return loss, text_fea

ercbcm/__init__.py

@@ -0,0 +1,33 @@
+import os, sys
+
+myPath = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, myPath + '/../')
+
+# ==========
+
+import torch
+
+from ercbcm.model_loader import load_checkpoint
+from ercbcm.ERCBCM import ERCBCM
+from modules.tokenizer import tokenizer, normalize_v2, PAD_TOKEN_ID
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print('>>> GPU Available?', torch.cuda.is_available())
+
+# ==========
+
+model_for_predict = ERCBCM().to(device)
+load_checkpoint('ercbcm/model.pt', model_for_predict, device)
+
+def predict(sentence, name):
+    label = torch.tensor([0])
+    label = label.type(torch.LongTensor)
+    label = label.to(device)
+    text = tokenizer.encode(normalize_v2(sentence, name))
+    text += [PAD_TOKEN_ID] * (128 - len(text))
+    text = torch.tensor([text])
+    text = text.type(torch.LongTensor)
+    text = text.to(device)
+    _, output = model_for_predict(text, label)
+    pred = torch.argmax(output, 1).tolist()[0]
+    return 'CALLING' if pred == 1 else 'MENTIONING'

{modules/prediction → ercbcm}/model_loader.py

@@ -1,6 +1,6 @@
 import torch
 
-# Save and Load Functions
+# Save and Load Functions.
 
 def save_checkpoint(save_path, model, valid_loss):
     if save_path == None:

{modules/prediction → model}/ERCBCM.py

@@ -5,6 +5,7 @@ class ERCBCM(nn.Module):
   
     def __init__(self):
         super(ERCBCM, self).__init__()
+        print('>>> ERCBCM Init!')
 
         self.encoder = BertForSequenceClassification.from_pretrained('bert-base-uncased')
 

{modules/prediction → model}/__init__.py

@@ -14,13 +14,12 @@ from modules.tokenizer import tokenizer, normalize_v2, PAD_TOKEN_ID
 erc_root_folder = './model'
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print('>>> GPU Available?', torch.cuda.is_available())
 
 # ==========
 
-model_for_evaluate = ERCBCM().to(device)
-
-def prepare():
-    load_checkpoint(erc_root_folder + '/model.pt', model_for_evaluate, device)
+model_for_predict = ERCBCM().to(device)
+load_checkpoint(erc_root_folder + '/model.pt', model_for_predict, device)
 
 def predict(sentence, name):
     label = torch.tensor([0])
@@ -31,6 +30,9 @@ def predict(sentence, name):
     text = torch.tensor([text])
     text = text.type(torch.LongTensor)
     text = text.to(device)
-    _, output = model_for_evaluate(text, label)
+    _, output = model_for_predict(text, label)
     pred = torch.argmax(output, 1).tolist()[0]
-    return 'CALLING' if pred == 1 else 'MENTIONING'
+    return 'CALLING' if pred == 1 else 'MENTIONING'
+
+print(predict('are you okay, jimmy', 'jimmy'))
+print(predict('jimmy is good', 'jimmy'))

model/model_loader.py

@@ -0,0 +1,38 @@
+import torch
+
+import torch.nn as nn
+
+# Save and Load Functions.
+
+def save_checkpoint(save_path, model, valid_loss):
+    if save_path == None:
+        return
+    state_dict = {'model_state_dict': model.state_dict(),
+                  'valid_loss': valid_loss}
+    torch.save(state_dict, save_path)
+    print('[SAVE] Model has been saved successfully to \'{}\''.format(save_path))
+
+def load_checkpoint(load_path, model, device):
+    if load_path == None:
+        return
+    state_dict = torch.load(load_path, map_location=device)
+    print('DICT:', state_dict)
+    print('[LOAD] Model has been loaded successfully from \'{}\''.format(load_path))
+    model.load_state_dict(state_dict['model_state_dict'])
+    return state_dict['valid_loss']
+
+def save_metrics(save_path, train_loss_list, valid_loss_list, global_steps_list):
+    if save_path == None:
+        return
+    state_dict = {'train_loss_list': train_loss_list,
+                  'valid_loss_list': valid_loss_list,
+                  'global_steps_list': global_steps_list}
+    torch.save(state_dict, save_path)
+    print('[SAVE] Model with matrics has been saved successfully to \'{}\''.format(save_path))
+
+def load_metrics(load_path, device):
+    if load_path == None:
+        return
+    state_dict = torch.load(load_path, map_location=device)
+    print('[LOAD] Model with matrics has been loaded successfully from \'{}\''.format(load_path))
+    return state_dict['train_loss_list'], state_dict['valid_loss_list'], state_dict['global_steps_list']