Upload 3 files

README.md

@@ -1,12 +1,13 @@
----
-title: Trtest1
-emoji: 👁
-colorFrom: purple
-colorTo: yellow
-sdk: gradio
-sdk_version: 5.9.1
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: test train
+emoji: 🙄
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,105 @@
+import spaces
+import gradio as gr
+import torch
+import torchvision
+from PIL import Image
+import numpy as np
+import os
+from huggingface_hub import HfApi, HfFolder, Repository
+from transformers import ViTForImageClassification, Trainer, TrainingArguments
+from datasets import load_dataset
+from sklearn.metrics import accuracy_score
+
+
+@spaces.GPU
+def dummy_gpu():
+    pass
+
+
+HF_MODEL = "google/vit-base-patch16-224"
+HF_DATASET = "verytuffcat/recaptcha-dataset"
+
+
+HF_TOKEN = os.getenv("HF_TOKEN", "")
+if os.getenv("HF_REPO"): HF_REPO = os.getenv("HF_REPO")
+if os.getenv("HF_DATASET"): HF_DATASET = os.getenv("HF_DATASET")
+if os.getenv("HF_MODEL"): HF_MODEL = os.getenv("HF_MODEL")
+OUT_DIR = "./new_model"
+
+
+def compute_metrics(eval_pred):
+    predictions, labels = eval_pred
+    predictions = np.argmax(predictions, axis=1)
+    return dict(accuracy=accuracy_score(predictions, labels))
+
+
+def collate_fn(batch):
+    pixel_values = torch.stack([torchvision.transforms.functional.to_tensor(x["image"].convert("RGB").resize((224, 224), Image.BICUBIC)) for x in batch])
+    labels = torch.tensor([x["label"] for x in batch])
+    return {"pixel_values": pixel_values, "labels": labels}
+
+
+def train(model_id: str, dataset_id: str, repo_id: str, hf_token: str, log_md: str, progress=gr.Progress(track_tqdm=True)):
+    try:
+        if not model_id or not dataset_id or not repo_id: raise gr.Error("Fill fields.")
+        if not hf_token: hf_token = HF_TOKEN
+        if not hf_token: raise gr.Error("Input HF token.")
+        HfFolder.save_token(hf_token)
+
+        model = ViTForImageClassification.from_pretrained(model_id)
+        dataset = load_dataset(dataset_id, split="train")
+
+        training_args = TrainingArguments(
+            output_dir=OUT_DIR,
+            use_cpu=True,
+            no_cuda=True,
+            fp16=True,
+            optim="adamw_torch",
+            lr_scheduler_type="linear",
+            learning_rate=0.00005,
+            per_device_train_batch_size=8,
+            num_train_epochs=3,
+            gradient_accumulation_steps=1,
+            use_ipex=True,
+            eval_strategy="no",
+            logging_strategy="no",
+            remove_unused_columns=False,
+            push_to_hub=False,
+            save_total_limit=2,
+            report_to="none"
+        )
+        trainer = Trainer(
+            model=model,
+            args=training_args,
+            data_collator=collate_fn,
+            compute_metrics=compute_metrics,
+            train_dataset=dataset,
+            eval_dataset=None,
+        )
+        trainer.train()
+        trainer.save_model(OUT_DIR)
+
+        api = HfApi(token=hf_token)
+        api.create_repo(repo_id=repo_id, private=True, token=hf_token)
+        repo = Repository(local_dir=OUT_DIR, clone_from=repo_id, use_auth_token=hf_token)
+        repo.push_to_hub()
+
+        return log_md
+    except Exception as e:
+        raise gr.Error(f"Error occured: {e}")
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        model_id = gr.Textbox(label="Source model", value=HF_MODEL, lines=1)
+        dataset_id = gr.Textbox(label="Source dataset", value=HF_DATASET, lines=1)
+    with gr.Row():
+        repo_id = gr.Textbox(label="Output repo", value=HF_REPO, lines=1)
+        hf_token = gr.Textbox(label="HF write token", value="", lines=1)
+    train_btn = gr.Button("Train")
+    log_md = gr.Markdown(label="Log", value="<br><br>")
+
+    train_btn.click(train, [model_id, dataset_id, repo_id, hf_token, log_md], [log_md])
+
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,10 @@
+huggingface_hub
+transformers
+torch
+torchvision
+numpy<2
+scikit-learn
+accelerate
+optimum[ipex]
+intel-extension-for-pytorch
+#oneccl_bind_pt --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/cpu/cn/