feat: init api

Dockerfile

@@ -0,0 +1,16 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+COPY ./app /code/app
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -4,6 +4,7 @@ emoji: 🏢
 colorFrom: blue
 colorTo: purple
 sdk: docker
+app_port: 
 pinned: false
 ---
 

app.py

@@ -0,0 +1,34 @@
+import numpy as np
+from fastapi import FastAPI, File, UploadFile
+import tensorflow as tf
+from io import StringIO
+from PIL import Image
+
+app = FastAPI()
+
+labels = []
+model = tf.keras.models.load_model('./models.h5')
+with open("labels.txt") as f:
+    for line in f:
+        labels.append(line.replace('\n', ''))
+
+def classify_image(inp):
+    # Create a copy of the input array to avoid reference issues
+    inp_copy = np.copy(inp)
+    # Resize the input image to the expected shape (224, 224)
+    inp_copy = Image.fromarray(inp_copy)
+    inp_copy = inp_copy.resize((224, 224))
+    inp_copy = np.array(inp_copy)
+    inp_copy = inp_copy.reshape((-1, 224, 224, 3))
+    inp_copy = tf.keras.applications.efficientnet.preprocess_input(inp_copy)
+    prediction = model.predict(inp_copy).flatten()
+    confidences = {labels[i]: float(prediction[i]) for i in range(90)}
+    return confidences
+
+@app.post("/predict/")
+async def predict(file: UploadFile = File(...)):
+    contents = await file.read()
+    img = Image.open(StringIO(contents))
+    img = np.array(img)
+    confidences = classify_image(img)
+    return confidences

requirements.txt

@@ -0,0 +1,11 @@
+tensorflow
+tensorflow-estimator==2.15.0
+tensorflow-gcs-config==2.15.0
+tensorflow-hub==0.16.1
+tensorflow-io-gcs-filesystem==0.36.0
+tensorflow-metadata==1.15.0
+tensorflow-probability==0.23.0
+fastapi
+numpy==1.25.2
+Pillow==9.4.0
+keras==2.15.0