init

VitTrainer.py

@@ -1,21 +1,45 @@
+# tensor - numpy - PILImage 변환 (https://qlsenddl-lab.tistory.com/37)
+
 import os
 os.environ['KMP_DUPLICATE_LIB_OK']='True'
-from datasets import load_dataset
+from datasets import Dataset
+import torch
+import torchvision.transforms as transforms
 
-# load cifar10 (only small portion for demonstration purposes) 
-train_ds, test_ds = load_dataset('cifar10', split=['train[:5000]', 'test[:2000]'])
-# split up training into training + validation
-splits = train_ds.train_test_split(test_size=0.1)
-train_ds = splits['train']
-val_ds = splits['test']
+from stock.util.Stock2Vector import Stock2Vector
 
-id2label = {id:label for id, label in enumerate(train_ds.features['label'].names)}
-label2id = {label:id for id,label in id2label.items()}
+PROJECT_HOME = os.path.join(os.path.dirname(__file__))
+RESOURCE_PATH = os.path.join(PROJECT_HOME, "resources")
+stock2Vector = Stock2Vector(RESOURCE_PATH)
+X, Y = stock2Vector.getDataset2D("252670")
 
+trans = transforms.ToPILImage()
+X = [trans(torch.tensor([x])) for x in X]
+
+split_point1 = int(len(X)*0.7)
+split_point2 = int(len(X)*0.9)
+train_X = X[:split_point1]
+train_Y = Y[:split_point1]
+valid_X = X[split_point1:split_point2]
+valid_Y = X[split_point1:split_point2]
+test_X = X[split_point2:]
+test_Y = X[split_point2:]
+
+id2label = {0: '0', 1: '1', 2: '2'}
+label2id = {'0': 0, '1': 1, '2': 2}
+
+# load cifar10 (only small portion for demonstration purposes)
+train_data = {'img': train_X, 'label': train_Y}
+val_dsta = {'img': valid_X, 'label': valid_Y}
+test_data = {'img': test_X, 'label': test_Y}
+
+train_ds = Dataset.from_dict(train_data)
+val_ds = Dataset.from_dict(val_dsta)
+test_ds = Dataset.from_dict(test_data)
 
 from transformers import ViTFeatureExtractor
 
-feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224-in21k")
+feature_extractor = ViTFeatureExtractor()
 
 from torchvision.transforms import (CenterCrop,
                                     Compose,
@@ -67,7 +91,10 @@ def collate_fn(examples):
     return {"pixel_values": pixel_values, "labels": labels}
 
 train_dataloader = DataLoader(train_ds, collate_fn=collate_fn, batch_size=4)
-
+train_data_loader = torch.utils.data.DataLoader(train_X,
+                                          batch_size=32,
+                                          shuffle=True,
+                                          num_workers=16)
 
 batch = next(iter(train_dataloader))
 for k,v in batch.items():