Initial checking

app.py

@@ -0,0 +1,79 @@
+import torch
+import torch.nn as nn
+
+from transformers import AutoTokenizer
+from transformers.configuration_utils import PretrainedConfig
+from transformers.models.distilbert.modeling_distilbert import DistilBertPreTrainedModel, DistilBertModel
+
+
+import gradio as gr
+
+class IMBDModel(DistilBertPreTrainedModel):
+
+    def __init__(self, config : PretrainedConfig):
+        super(IMBDModel, self).__init__(config)
+
+        self.distilbert = DistilBertModel(config)
+
+        # # freeze whole model
+        # for params in self.distilbert.parameters():
+        #     params.requires_grad = False
+
+        # layers = self.distilbert.transformer.layer
+        # print("Total Layers:", len(layers))
+
+        # # Enable trainable few layers.
+        # for layer_num in [5]:
+        #     for params in layers[layer_num].parameters():
+        #         params.requires_grad = True
+
+        self.fc = nn.Linear(config.dim, 1)
+
+        self.post_init()
+
+    def forward(self, x):
+
+        x = self.distilbert(**x).last_hidden_state
+        pooled_output = x[:, 0]
+
+        x = self.fc(pooled_output)
+
+        return x
+    
+
+infer_path = "./model/fold0_epoch01_loss0.1403_val_loss0.1994_roc_auc0.9779/"
+    
+tokenizer = AutoTokenizer.from_pretrained(infer_path)
+    
+pretrained_model = IMBDModel.from_pretrained(infer_path, local_files_only=True)
+pretrained_model.eval()
+    
+def prediction(text):
+
+    tokens = tokenizer(text, padding='max_length', truncation=True, max_length=512)
+    tokens = {k:torch.tensor([v]) for k, v in tokens.items()}
+    
+    with torch.no_grad():
+        
+        scores = pretrained_model(tokens)
+        scores = torch.sigmoid(scores).numpy()
+        
+        scores = scores[0][0]
+        
+        if scores >= 0.6:
+            label = "Positive"
+        elif 0.4 <= scores < 0.6:
+            label = "Neutral"
+        else:
+            label = "Negative"
+
+    return f"{label} feedback", f"{scores:.2f}"
+
+
+demo = gr.Interface(
+    fn=prediction, 
+    inputs=gr.Textbox(lines=5, placeholder="Text to analyze..."), 
+    outputs=["text", "text"]
+)
+
+demo.launch(server_name="0.0.0.0") 

model/fold0_epoch01_loss0.1403_val_loss0.1994_roc_auc0.9779/config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "IMBDModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "vocab_size": 30522
+}

model/fold0_epoch01_loss0.1403_val_loss0.1994_roc_auc0.9779/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edef516831654dda01b1564712e0d950eb18db4c5a13b65f33f3dad305f1b4fc
+size 265486837

model/fold0_epoch01_loss0.1403_val_loss0.1994_roc_auc0.9779/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

model/fold0_epoch01_loss0.1403_val_loss0.1994_roc_auc0.9779/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

requirements.txt

@@ -0,0 +1,2 @@
+torch==1.12.1
+transformers==4.23.1