fix

Dockerfile

@@ -1,13 +1,20 @@
-FROM python:3.10
+FROM python:3.9
 
 WORKDIR ./code
 
-COPY requirements.txt ./code/requirements.txt
+COPY ./requirements.txt /code/requirements.txt
 
-RUN pip install --no-cache-dir --upgrade -r ./code/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-COPY main.py models/fruit_recognition_model.pth ./models/
-COPY templates/ ./templates
-COPY metadata.json .
+RUN useradd -m -u 1000 user
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

endpoint.py

@@ -0,0 +1,8 @@
+from transformers import pipeline
+
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
+
+@app.get("/infer_t5")
+def t5(input):
+    output = pipe_flan(input)
+    return {"output": output[0]["generated_text"]}

main.py

@@ -1,87 +1,8 @@
-# main.py
-import json
-from fastapi import FastAPI, File, UploadFile, Request
-from fastapi.responses import HTMLResponse, JSONResponse
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.templating import Jinja2Templates
-from PIL import Image
-from io import BytesIO
-import torch
-import torch.nn as nn
-import torchvision.transforms as transforms
-from torchvision import models
-
-class FruitRecognizer:
-    def __init__(self, model_path, num_classes):
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        self.model = models.resnet18(pretrained=False)
-        self.model.fc = nn.Linear(self.model.fc.in_features, num_classes)
-        self.model.load_state_dict(torch.load(model_path, map_location=self.device))
-        self.model.to(self.device)
-        self.model.eval()
-
-        self.transform = transforms.Compose([
-            transforms.Resize(256),
-            transforms.CenterCrop(224),
-            transforms.ToTensor(),
-            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-        ])
-
-    def recognize_fruit_from_path(self, image_path, class_names):
-        img = Image.open(image_path).convert("RGB")
-        img = self.transform(img)
-        img = img.unsqueeze(0).to(self.device)
-
-        with torch.no_grad():
-            outputs = self.model(img)
-            _, predicted = torch.max(outputs.data, 1)
-            predicted_class = class_names[predicted.item()]
-
-        return predicted_class
-    
-    def recognize_fruit(self, image, class_names):
-        img = self.transform(image)
-        img = img.unsqueeze(0).to(self.device)
-
-        with torch.no_grad():
-            outputs = self.model(img)
-            _, predicted = torch.max(outputs.data, 1)
-            predicted_class = class_names[predicted.item()]
-
-        return predicted_class
-    
 
 app = FastAPI()
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-with open('metadata.json', 'r') as f:
-    metadata = json.load(f)
-
-class_names = metadata['classes']
-
-model_path = "models/fruit_recognition_model.pth"
-recognizer = FruitRecognizer(model_path, len(class_names))
-
-templates = Jinja2Templates(directory="templates")
-
-@app.get("/", response_class=HTMLResponse)
-async def root(request: Request):
-    return templates.TemplateResponse("index.html", {"request": request})
-
-@app.post("/predict/")
-async def predict_fruit(request: Request, file: UploadFile = File(...)):
-    try:
-        print("request")
-        img = Image.open(BytesIO(await file.read())).convert("RGB")
-        predicted_class = recognizer.recognize_fruit(img, class_names)
-        return JSONResponse({"predicted_class": predicted_class})
-    except Exception as e:
-        return JSONResponse({"error": str(e)}, status_code=400)
+app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
+@app.get("/")
+def index() -> FileResponse:
+    return FileResponse(path="/app/static/index.html", media_type="text/html")

main2.py

@@ -0,0 +1,87 @@
+# main.py
+import json
+from fastapi import FastAPI, File, UploadFile, Request
+from fastapi.responses import HTMLResponse, JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.templating import Jinja2Templates
+from PIL import Image
+from io import BytesIO
+import torch
+import torch.nn as nn
+import torchvision.transforms as transforms
+from torchvision import models
+
+class FruitRecognizer:
+    def __init__(self, model_path, num_classes):
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model = models.resnet18(pretrained=False)
+        self.model.fc = nn.Linear(self.model.fc.in_features, num_classes)
+        self.model.load_state_dict(torch.load(model_path, map_location=self.device))
+        self.model.to(self.device)
+        self.model.eval()
+
+        self.transform = transforms.Compose([
+            transforms.Resize(256),
+            transforms.CenterCrop(224),
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+        ])
+
+    def recognize_fruit_from_path(self, image_path, class_names):
+        img = Image.open(image_path).convert("RGB")
+        img = self.transform(img)
+        img = img.unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            outputs = self.model(img)
+            _, predicted = torch.max(outputs.data, 1)
+            predicted_class = class_names[predicted.item()]
+
+        return predicted_class
+    
+    def recognize_fruit(self, image, class_names):
+        img = self.transform(image)
+        img = img.unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            outputs = self.model(img)
+            _, predicted = torch.max(outputs.data, 1)
+            predicted_class = class_names[predicted.item()]
+
+        return predicted_class
+    
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+with open('metadata.json', 'r') as f:
+    metadata = json.load(f)
+
+class_names = metadata['classes']
+
+model_path = "models/fruit_recognition_model.pth"
+recognizer = FruitRecognizer(model_path, len(class_names))
+
+templates = Jinja2Templates(directory="templates")
+
+@app.get("/", response_class=HTMLResponse)
+async def root(request: Request):
+    return templates.TemplateResponse("index.html", {"request": request})
+
+@app.post("/predict/")
+async def predict_fruit(request: Request, file: UploadFile = File(...)):
+    try:
+        print("request")
+        img = Image.open(BytesIO(await file.read())).convert("RGB")
+        predicted_class = recognizer.recognize_fruit(img, class_names)
+        return JSONResponse({"predicted_class": predicted_class})
+    except Exception as e:
+        return JSONResponse({"error": str(e)}, status_code=400)
+

static/index.html

@@ -0,0 +1,36 @@
+<main>
+    <section id="text-gen">
+      <h2 class="relative group">
+      <a 
+          id="text-generation-using-flan-t5" 
+          class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" 
+          href="#text-generation-using-flan-t5"
+      >
+          <span><IconCopyLink/></span>
+      </a>
+      <span>
+          Text generation using Flan T5
+      </span>
+  </h2>
+  
+      <p>
+        Model:
+        <a
+          href="https://huggingface.co/google/flan-t5-small"
+          rel="noreferrer"
+          target="_blank"
+          >google/flan-t5-small
+        </a>
+      </p>
+      <form class="text-gen-form">
+        <label for="text-gen-input">Text prompt</label>
+        <input
+          id="text-gen-input"
+          type="text"
+          value="German: There are many ducks"
+        />
+        <button id="text-gen-submit">Submit</button>
+        <p class="text-gen-output"></p>
+      </form>
+    </section>
+  </main>

static/script.js

@@ -0,0 +1,17 @@
+const textGenForm = document.querySelector(".text-gen-form");
+
+const translateText = async (text) => {
+  const inferResponse = await fetch(`infer_t5?input=${text}`);
+  const inferJson = await inferResponse.json();
+
+  return inferJson.output;
+};
+
+textGenForm.addEventListener("submit", async (event) => {
+  event.preventDefault();
+
+  const textGenInput = document.getElementById("text-gen-input");
+  const textGenParagraph = document.querySelector(".text-gen-output");
+
+  textGenParagraph.textContent = await translateText(textGenInput.value);
+});