fix: Try permissions error fix

Dockerfile

@@ -29,3 +29,5 @@ ENV PATH="/opt/venv/bin:$PATH"
 # Expose the port and run the app
 EXPOSE 8000
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+
+

main.py

@@ -43,64 +43,64 @@ ANIMALS = ['Cat', 'Dog', 'Panda'] # Animal names here, these represent the label
 # 1) download your SavedModel from the Hub into a writable directory (Spaces often
 # run with the repository checkout read-only). Prefer TMPDIR or /tmp.
 repo_id = "IDS75912/masterclass-2025"
-local_model_dir = os.environ.get('HF_MODEL_DIR') or os.environ.get('TMPDIR') or '/tmp/model'
+local_model_dir = os.environ.get('HF_MODEL_DIR', './model_dir')
 
 # Ensure the directory exists and is writable. If creating fails, raise a clear error.
 try:
     os.makedirs(local_model_dir, exist_ok=True)
-except PermissionError:
-    raise RuntimeError(f"Cannot create model directory '{local_model_dir}'. Ensure the process has write access or set HF_MODEL_DIR to a writable path.")
+except Exception as e:
+    raise RuntimeError(f"Cannot create model directory '{local_model_dir}'. Ensure the process has write access or set HF_MODEL_DIR to a writable path., Error: {e}")
 
 # download files into local_model_dir and load model with resilient error handling
 model = None
 model_load_error = None
-try:
+#try:
     # First try using a cache dir so downloads happen in a shared cache and final move
     # into local_model_dir is less likely to require risky renames inside the repo.
-    cache_dir = '/tmp/.cache/huggingface'
-    os.makedirs(cache_dir, exist_ok=True)
+    # cache_dir = '/tmp/.cache/huggingface'
+    # os.makedirs(cache_dir, exist_ok=True)
 
-    hf_hub_download(repo_id, filename="config.json", repo_type="model", local_dir=local_model_dir, cache_dir=cache_dir)
-    hf_hub_download(repo_id, filename="metadata.json", repo_type="model", local_dir=local_model_dir, cache_dir=cache_dir)
-    hf_hub_download(repo_id, filename="model.weights.h5", repo_type="model", local_dir=local_model_dir, cache_dir=cache_dir)
+hf_hub_download(repo_id, filename="config.json", repo_type="model", local_dir=local_model_dir )
+hf_hub_download(repo_id, filename="metadata.json", repo_type="model", local_dir=local_model_dir)
+hf_hub_download(repo_id, filename="model.weights.h5", repo_type="model", local_dir=local_model_dir)
 
     # 2) load it
-    model = tf.keras.models.load_model(local_model_dir)
-    logging.info(f"Model loaded successfully from {local_model_dir}")
-except Exception as e:
-    # Primary download attempt failed -> try streamed fallback which writes directly
-    # into local_model_dir (avoids internal temp/move when those operations are blocked).
-    primary_err = e
-    logging.error("Primary hf_hub_download failed, attempting streamed fallback: %s", e)
-    try:
-        for filename in ("config.json", "metadata.json", "model.weights.h5"):
-            url = hf_hub_url(repo_id=repo_id, filename=filename, repo_type='model')
-            logging.info(f"Streaming {filename} from {url} into {local_model_dir}")
-            resp = requests.get(url, stream=True, timeout=60)
-            resp.raise_for_status()
-            # write to a temp file inside the target dir then move atomically
-            with tempfile.NamedTemporaryFile(dir=local_model_dir, delete=False) as tmpf:
-                for chunk in resp.iter_content(chunk_size=8192):
-                    if chunk:
-                        tmpf.write(chunk)
-                tmp_path = tmpf.name
-            final_path = os.path.join(local_model_dir, filename)
-            try:
-                shutil.move(tmp_path, final_path)
-            except Exception:
-                # if atomic move fails, try copy+remove
-                shutil.copy(tmp_path, final_path)
-                os.remove(tmp_path)
-
-        # After streamed download, try loading
-        model = tf.keras.models.load_model(local_model_dir)
-        logging.info(f"Model loaded successfully from {local_model_dir} after streamed fallback")
-    except Exception as e2:
-        model_load_error = f"primary: {primary_err}; fallback: {e2}"
-        tb = traceback.format_exc()
-        logging.error("Streamed fallback failed: %s", e2)
-        logging.error(tb)
-        model = None
+model = tf.keras.models.load_model(local_model_dir)
+logging.info(f"Model loaded successfully from {local_model_dir}")
+# except Exception as e:
+#     # Primary download attempt failed -> try streamed fallback which writes directly
+#     # into local_model_dir (avoids internal temp/move when those operations are blocked).
+#     primary_err = e
+#     logging.error("Primary hf_hub_download failed, attempting streamed fallback: %s", e)
+#     try:
+#         for filename in ("config.json", "metadata.json", "model.weights.h5"):
+#             url = hf_hub_url(repo_id=repo_id, filename=filename, repo_type='model')
+#             logging.info(f"Streaming {filename} from {url} into {local_model_dir}")
+#             resp = requests.get(url, stream=True, timeout=60)
+#             resp.raise_for_status()
+#             # write to a temp file inside the target dir then move atomically
+#             with tempfile.NamedTemporaryFile(dir=local_model_dir, delete=False) as tmpf:
+#                 for chunk in resp.iter_content(chunk_size=8192):
+#                     if chunk:
+#                         tmpf.write(chunk)
+#                 tmp_path = tmpf.name
+#             final_path = os.path.join(local_model_dir, filename)
+#             try:
+#                 shutil.move(tmp_path, final_path)
+#             except Exception:
+#                 # if atomic move fails, try copy+remove
+#                 shutil.copy(tmp_path, final_path)
+#                 os.remove(tmp_path)
+
+#         # After streamed download, try loading
+#         model = tf.keras.models.load_model(local_model_dir)
+#         logging.info(f"Model loaded successfully from {local_model_dir} after streamed fallback")
+#     except Exception as e2:
+#         model_load_error = f"primary: {primary_err}; fallback: {e2}"
+#         tb = traceback.format_exc()
+#         logging.error("Streamed fallback failed: %s", e2)
+#         logging.error(tb)
+#         model = None
 
 
 @app.post('/upload/image')
@@ -151,9 +151,6 @@ def predict_stub() -> Dict[str, Any]:
 
 
 
-
-
-
 if __name__ == "__main__":
 	# Run with: conda run -n gradio uvicorn main:app --reload
 	import uvicorn