a

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,13 @@
+---
+title: Custom Object Detection
+emoji: 🏃
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+license: cc
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

.ipynb_checkpoints/app-checkpoint.py

@@ -15,7 +15,40 @@ from PIL import Image
 import PIL
 
 HF_DATASETS_CACHE="./"
-
+class ImageClassificationCollator:
+        def __init__(self, feature_extractor):
+            self.feature_extractor = feature_extractor
+
+        def __call__(self, batch):
+            encodings = self.feature_extractor([x[0] for x in batch], return_tensors='pt')
+            encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.long)
+            return encodings 
+class Classifier(pl.LightningModule):
+
+        def __init__(self, model, lr: float = 2e-5, **kwargs):
+            super().__init__()
+            self.save_hyperparameters('lr', *list(kwargs))
+            self.model = model
+            self.forward = self.model.forward
+            self.val_acc = Accuracy(
+                task='multiclass' if model.config.num_labels > 2 else 'binary',
+                num_classes=model.config.num_labels
+            )
+
+        def training_step(self, batch, batch_idx):
+            outputs = self(**batch)
+            self.log(f"train_loss", outputs.loss)
+            return outputs.loss
+
+        def validation_step(self, batch, batch_idx):
+            outputs = self(**batch)
+            self.log(f"val_loss", outputs.loss)
+            acc = self.val_acc(outputs.logits.argmax(1), batch['labels'])
+            self.log(f"val_acc", acc, prog_bar=True)
+            return outputs.loss
+
+        def configure_optimizers(self):
+            return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
 
 def video_identity(video,user_name,class_name,trainortest,ready):
     if ready=='yes':
@@ -38,14 +71,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
             label2id[class_name] = str(i)
             id2label[str(i)] = class_name      
             
-        class ImageClassificationCollator:
-            def __init__(self, feature_extractor):
-                self.feature_extractor = feature_extractor
-
-            def __call__(self, batch):
-                encodings = self.feature_extractor([x[0] for x in batch], return_tensors='pt')
-                encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.long)
-                return encodings 
+       
         feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
         model = ViTForImageClassification.from_pretrained(
             'google/vit-base-patch16-224-in21k',
@@ -54,33 +80,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
             id2label=id2label
         )
         collator = ImageClassificationCollator(feature_extractor)
-        class Classifier(pl.LightningModule):
-
-            def __init__(self, model, lr: float = 2e-5, **kwargs):
-                super().__init__()
-                self.save_hyperparameters('lr', *list(kwargs))
-                self.model = model
-                self.forward = self.model.forward
-                self.val_acc = Accuracy(
-                    task='multiclass' if model.config.num_labels > 2 else 'binary',
-                    num_classes=model.config.num_labels
-                )
-
-            def training_step(self, batch, batch_idx):
-                outputs = self(**batch)
-                self.log(f"train_loss", outputs.loss)
-                return outputs.loss
-
-            def validation_step(self, batch, batch_idx):
-                outputs = self(**batch)
-                self.log(f"val_loss", outputs.loss)
-                acc = self.val_acc(outputs.logits.argmax(1), batch['labels'])
-                self.log(f"val_acc", acc, prog_bar=True)
-                return outputs.loss
-
-            def configure_optimizers(self):
-                return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
-
+       
             
            
         train_loader = DataLoader(train_ds, batch_size=2, collate_fn=collator, num_workers=8, shuffle=True)
@@ -94,7 +94,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
                 
         pl.seed_everything(42)
         classifier = Classifier(model, lr=2e-5)
-        trainer = pl.Trainer(accelerator='gpu', devices=1, precision=16, max_epochs=3)
+        trainer = pl.Trainer(accelerator='cpu', devices=1, precision=16, max_epochs=3)
         
         trainer.fit(classifier, train_loader, test_loader)
         

app.py

@@ -15,7 +15,40 @@ from PIL import Image
 import PIL
 
 HF_DATASETS_CACHE="./"
-
+class ImageClassificationCollator:
+        def __init__(self, feature_extractor):
+            self.feature_extractor = feature_extractor
+
+        def __call__(self, batch):
+            encodings = self.feature_extractor([x[0] for x in batch], return_tensors='pt')
+            encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.long)
+            return encodings 
+class Classifier(pl.LightningModule):
+
+        def __init__(self, model, lr: float = 2e-5, **kwargs):
+            super().__init__()
+            self.save_hyperparameters('lr', *list(kwargs))
+            self.model = model
+            self.forward = self.model.forward
+            self.val_acc = Accuracy(
+                task='multiclass' if model.config.num_labels > 2 else 'binary',
+                num_classes=model.config.num_labels
+            )
+
+        def training_step(self, batch, batch_idx):
+            outputs = self(**batch)
+            self.log(f"train_loss", outputs.loss)
+            return outputs.loss
+
+        def validation_step(self, batch, batch_idx):
+            outputs = self(**batch)
+            self.log(f"val_loss", outputs.loss)
+            acc = self.val_acc(outputs.logits.argmax(1), batch['labels'])
+            self.log(f"val_acc", acc, prog_bar=True)
+            return outputs.loss
+
+        def configure_optimizers(self):
+            return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
 
 def video_identity(video,user_name,class_name,trainortest,ready):
     if ready=='yes':
@@ -38,14 +71,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
             label2id[class_name] = str(i)
             id2label[str(i)] = class_name      
             
-        class ImageClassificationCollator:
-            def __init__(self, feature_extractor):
-                self.feature_extractor = feature_extractor
-
-            def __call__(self, batch):
-                encodings = self.feature_extractor([x[0] for x in batch], return_tensors='pt')
-                encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.long)
-                return encodings 
+       
         feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
         model = ViTForImageClassification.from_pretrained(
             'google/vit-base-patch16-224-in21k',
@@ -54,33 +80,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
             id2label=id2label
         )
         collator = ImageClassificationCollator(feature_extractor)
-        class Classifier(pl.LightningModule):
-
-            def __init__(self, model, lr: float = 2e-5, **kwargs):
-                super().__init__()
-                self.save_hyperparameters('lr', *list(kwargs))
-                self.model = model
-                self.forward = self.model.forward
-                self.val_acc = Accuracy(
-                    task='multiclass' if model.config.num_labels > 2 else 'binary',
-                    num_classes=model.config.num_labels
-                )
-
-            def training_step(self, batch, batch_idx):
-                outputs = self(**batch)
-                self.log(f"train_loss", outputs.loss)
-                return outputs.loss
-
-            def validation_step(self, batch, batch_idx):
-                outputs = self(**batch)
-                self.log(f"val_loss", outputs.loss)
-                acc = self.val_acc(outputs.logits.argmax(1), batch['labels'])
-                self.log(f"val_acc", acc, prog_bar=True)
-                return outputs.loss
-
-            def configure_optimizers(self):
-                return torch.optim.Adam(self.parameters(), lr=self.hparams.lr)
-
+       
             
            
         train_loader = DataLoader(train_ds, batch_size=2, collate_fn=collator, num_workers=8, shuffle=True)
@@ -94,7 +94,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
                 
         pl.seed_everything(42)
         classifier = Classifier(model, lr=2e-5)
-        trainer = pl.Trainer(accelerator='gpu', devices=1, precision=16, max_epochs=3)
+        trainer = pl.Trainer(accelerator='cpu', devices=1, precision=16, max_epochs=3)
         
         trainer.fit(classifier, train_loader, test_loader)