rename var file to image

Author: robmarkcole

README.md

@@ -20,50 +20,41 @@ If you want to create custom models, there is the easy way, and the longer but m
 ## Usage
 Start the tflite-server on port 5000 :
 ```
-(venv) $ uvicorn tflite-server:app --reload --port 5000
+(venv) $ uvicorn tflite-server:app --reload --port 5000 --host 0.0.0.0
 ```
 
 You can check that the tflite-server is running by visiting `http://ip:5000/` from any machine, where `ip` is the ip address of the host (`localhost` if querying from the same machine). The docs can be viewed at `http://localhost:5000/docs`
 
 Post an image to detecting objects via cURL:
 ```
-curl -X POST "http://localhost:5000/v1/vision/detection" -H  "accept: application/json" -H  "Content-Type: multipart/form-data" -F "file=@tests/people_car.jpg;type=image/jpeg"
+curl -X POST "http://localhost:5000/v1/vision/detection" -H  "accept: application/json" -H  "Content-Type: multipart/form-data" -F "image=@tests/people_car.jpg;type=image/jpeg"
 ```
 Which should return:
 ```
 {
   "predictions": [
     {
-      "confidence": 0.93359375, 
-      "label": "car", 
-      "x_max": 619, 
-      "x_min": 302, 
-      "y_max": 348, 
+      "confidence": 0.93359375,
+      "label": "car",
+      "x_max": 619,
+      "x_min": 302,
+      "y_max": 348,
       "y_min": 120
-    }, 
+    },
     {
-      "confidence": 0.7890625, 
-      "label": "person", 
-      "x_max": 363, 
-      "x_min": 275, 
-      "y_max": 323, 
+      "confidence": 0.7890625,
+      "label": "person",
+      "x_max": 363,
+      "x_min": 275,
+      "y_max": 323,
       "y_min": 126
     },
 .
 .
 .
 'success': True}
 ```
-
-To detect faces:
-```
-curl -X POST "http://localhost:5000/v1/vision/face" -H  "accept: application/json" -H  "Content-Type: multipart/form-data" -F "file=@tests/faces.jpg;type=image/jpeg"
-```
-
-To detect the scene (dogs vs cats model):
-```
-curl -X POST "http://localhost:5000/v1/vision/scene" -H  "accept: application/json" -H  "Content-Type: multipart/form-data" -F "file=@tests/cat.jpg;type=image/jpeg"
-```
+An example request using the python requests package is in `tests/live-test.py`
 
 ## Add tflite-server as a service
 You can run tflite-server as a [service](https://www.raspberrypi.org/documentation/linux/usage/systemd.md), which means tflite-server will automatically start on RPi boot, and can be easily started & stopped. Create the service file in the appropriate location on the RPi using: ```sudo nano /etc/systemd/system/tflite-server.service```

tflite-server.py

@@ -2,7 +2,6 @@
 Expose tflite models via a rest API.
 """
 import io
-import logging
 import sys
 
 import numpy as np
@@ -14,14 +13,6 @@
 
 app = FastAPI()
 
-LOGFORMAT = "%(asctime)s %(levelname)s %(name)s : %(message)s"
-logging.basicConfig(
-    # filename="tflite-server.log", # select filename or stream
-    stream=sys.stdout,
-    level=logging.DEBUG,
-    format=LOGFORMAT,
-)
-
 MIN_CONFIDENCE = 0.1  # The absolute lowest confidence for a detection.
 
 FACE_DETECTION_URL = "/v1/vision/face"
@@ -72,14 +63,10 @@ async def info():
 
 
 @app.post(FACE_DETECTION_URL)
-async def predict_face(file: UploadFile = File(...)):
+async def predict_face(image: UploadFile = File(...)):
     data = {"success": False}
-    if file.content_type.startswith("image/") is False:
-        raise HTTPException(
-            status_code=400, detail=f"File '{file.filename}' is not an image."
-        )
     try:
-        contents = await file.read()
+        contents = await image.read()
         image = Image.open(io.BytesIO(contents))  # A PIL image
         image_width = image.size[0]
         image_height = image.size[1]
@@ -92,9 +79,7 @@ async def predict_face(file: UploadFile = File(...)):
         # Process image and get predictions
         face_interpreter.invoke()
         boxes = face_interpreter.get_tensor(face_output_details[0]["index"])[0]
-        classes = face_interpreter.get_tensor(face_output_details[1]["index"])[
-            0
-        ]
+        classes = face_interpreter.get_tensor(face_output_details[1]["index"])[0]
         scores = face_interpreter.get_tensor(face_output_details[2]["index"])[0]
 
         faces = []
@@ -121,14 +106,10 @@ async def predict_face(file: UploadFile = File(...)):
 
 
 @app.post(OBJ_DETECTION_URL)
-async def predict_object(file: UploadFile = File(...)):
+async def predict_object(image: UploadFile = File(...)):
     data = {"success": False}
-    if file.content_type.startswith("image/") is False:
-        raise HTTPException(
-            status_code=400, detail=f"File '{file.filename}' is not an image."
-        )
     try:
-        contents = await file.read()
+        contents = await image.read()
         image = Image.open(io.BytesIO(contents))  # A PIL image
         image_width = image.size[0]
         image_height = image.size[1]
@@ -167,14 +148,10 @@ async def predict_object(file: UploadFile = File(...)):
 
 
 @app.post(SCENE_URL)
-async def predict_scene(file: UploadFile = File(...)):
+async def predict_scene(image: UploadFile = File(...)):
     data = {"success": False}
-    if file.content_type.startswith("image/") is False:
-        raise HTTPException(
-            status_code=400, detail=f"File '{file.filename}' is not an image."
-        )
     try:
-        contents = await file.read()
+        contents = await image.read()
         image = Image.open(io.BytesIO(contents))  # A PIL image
         # Format data and send to interpreter
         resized_image = image.resize(