switch to Docker space

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.10
+
+ARG PIP_NO_CACHE_DIR=1
+
+RUN apt install tesseract-ocr
+RUN wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
+    && dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb
+
+RUN pip install torch==2.1.1 -i https://download.pytorch.org/whl/cpu
+RUN pip install paddlepaddle==2.5.1 -i https://mirror.baidu.com/pypi/simple
+RUN pip install transformers pytesseract paddleocr gradio Pillow
+
+CMD ["python", "app.py"]

README.md

@@ -1,12 +1,9 @@
 ---
 title: Layoutlm Docvqa Paddleocr
-emoji: 🏃
+emoji: 📄
 colorFrom: indigo
 colorTo: yellow
-sdk: gradio
-sdk_version: 4.8.0
-app_file: app.py
-pinned: false
+sdk: docker
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,19 +1,3 @@
-import sys
-
-if sys.platform == "linux":
-    try:
-        import paddle
-
-    except ImportError:
-        import os
-
-        # install libssl1.1 on HF spaces
-        os.system(
-            "wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb"
-        )
-        os.system("dpkg -x libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb .")
-        os.environ["LD_LIBRARY_PATH"] = os.environ.get("LD_LIBRARY_PATH", "") + ":./usr/lib/x86_64-linux-gnu"
-
 import cv2
 import gradio as gr
 import numpy as np
@@ -45,9 +29,7 @@ def predict(image: Image.Image, question: str, ocr_engine: str):
         boxes = np.asarray([x[0] for x in ocr_result])  # (n_boxes, 4, 2)
 
         for box in boxes:
-            cv2.polylines(
-                image_np, [box.reshape(-1, 1, 2).astype(int)], True, (0, 255, 255), 3
-            )
+            cv2.polylines(image_np, [box.reshape(-1, 1, 2).astype(int)], True, (0, 255, 255), 3)
 
         x1 = boxes[:, :, 0].min(1) * 1000 / image.width
         y1 = boxes[:, :, 1].min(1) * 1000 / image.height

packages.txt

@@ -1,2 +0,0 @@
-sudo
-tesseract-ocr

requirements.txt

@@ -1,9 +0,0 @@
---index-url https://download.pytorch.org/whl/cpu
---extra-index-url https://mirror.baidu.com/pypi/simple
-numpy
-torch
-transformers
-paddlepaddle==2.5.1
-paddleocr
-opencv-python-headless
-pytesseract