Update app.py

app.py

@@ -1,29 +1,37 @@
+from huggingface_hub import from_pretrained_fastai
 import gradio as gr
 from fastai.vision.all import *
-import numpy as np
-from PIL import Image
-from huggingface_hub import hf_hub_download
 import torchvision.transforms as transforms
-import torch
-from albumentations import (
-    Compose,
-    HorizontalFlip,
-    Rotate,
-    GridDistortion
-)
+import torchvision.transforms as transforms
+from fastai.basics import *
+from fastai.vision import models
+from fastai.vision.all import *
+from fastai.metrics import *
+from fastai.data.all import *
+from fastai.callback import *
 from pathlib import Path
+import random
+import PIL
 
-# --- FUNCIONES Y CLASES NECESARIAS PARA EL PICKLE ---
-
-def get_y_fn(x):
-    return Path(str(x).replace("Images","Labels").replace("color","gt").replace(".jpg",".png"))
+#Primero definimos todas las funciones, clases y variables que sopn necesarias para que esto funcione
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+def transform_image(image):
+    my_transforms = transforms.Compose([transforms.ToTensor(),
+                                        transforms.Normalize(
+                                            [0.485, 0.456, 0.406],
+                                            [0.229, 0.224, 0.225])])
+    image_aux = image
+    return my_transforms(image_aux).unsqueeze(0).to(device)
 
 class TargetMaskConvertTransform(ItemTransform):
     def __init__(self):
         pass
     def encodes(self, x):
         img,mask = x
+
+        #Convert to array
         mask = np.array(mask)
+
         mask[(mask!=255) & (mask!=150) & (mask!=76) & (mask!=74) & (mask!=29) & (mask!=25)]=0
         mask[mask==255]=1
         mask[mask==150]=2
@@ -31,50 +39,68 @@ class TargetMaskConvertTransform(ItemTransform):
         mask[mask==74]=4
         mask[mask==29]=3
         mask[mask==25]=3
-        return img, PILMask.create(mask)
+
+        # Back to PILMask
+        mask = PILMask.create(mask)
+        return img, mask
+
+from albumentations import (
+    Compose,
+    OneOf,
+    ElasticTransform,
+    GridDistortion,
+    OpticalDistortion,
+    HorizontalFlip,
+    Rotate,
+    Transpose,
+    CLAHE,
+    ShiftScaleRotate
+)
+
+def get_y_fn (x):
+    return Path(str(x).replace("Images","Labels").replace("color","gt").replace(".jpg",".png"))
 
 class SegmentationAlbumentationsTransform(ItemTransform):
     split_idx = 0
+
     def __init__(self, aug):
         self.aug = aug
+
     def encodes(self, x):
         img,mask = x
         aug = self.aug(image=np.array(img), mask=np.array(mask))
         return PILImage.create(aug["image"]), PILMask.create(aug["mask"])
 
-# --- CARGAR MODELO ---
-
-model_path = hf_hub_download(repo_id="PablitoGil14/AP-Practica3", filename="export.pkl")
-learn = load_learner(model_path)
+#Cargamos el modelo
+repo_id = "luisvarona/Practica3"
+learn = from_pretrained_fastai(repo_id)
+model = learn.model
+model = model.cpu()
 
-# --- FUNCIÓN DE PREDICCIÓN ---
 
-def segmentar(img: Image.Image):
-    img = img.resize((640, 480))
-    x = transforms.Compose([
-        transforms.ToTensor(),
-        transforms.Normalize(*imagenet_stats)
-    ])(img).unsqueeze(0)
-    
+# Definimos una función que se encarga de llevar a cabo las predicciones
+def predict(img_ruta):
+    # img = PIL.Image.open(img_ruta) #esto si el parámetro de entrada es una ruta a una imagen
+    # img = img_ruta # esto si el parámetro de entrada es una imagen
+    img = PIL.Image.fromarray(img_ruta)
+    image = transforms.Resize((480,640))(img)
+    tensor = transform_image(image=image)
+    model.to(device)
     with torch.no_grad():
-        preds = learn.model.eval()(x)
-        mask = torch.argmax(preds, dim=1).squeeze().cpu().numpy()
-
-    out_mask = np.zeros_like(mask, dtype=np.uint8)
-    out_mask[mask == 1] = 255
-    out_mask[mask == 2] = 150
-    out_mask[mask == 3] = 29
-    out_mask[mask == 4] = 74
-    return Image.fromarray(out_mask)
-
-# --- INTERFAZ GRADIO ---
+      outputs = model(tensor)
+    
+    outputs = torch.argmax(outputs,1)
+    mask = np.array(outputs.cpu())
+    mask[mask==1]=255
+    mask[mask==2]=150
+    mask[mask==3]=29
+    mask[mask==4]=74
+    mask = np.reshape(mask,(480,640))
+    return Image.fromarray(mask.astype('uint8'))
 
-demo = gr.Interface(
-    fn=segmentar,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Image(type="pil"),
-    title="Segmentador de Viñedos",
-    description="Sube una imagen y el modelo segmentará racimos de uva, hojas, madera y postes."
-)
+    
+    #img = PILImage.create(img) #igual hay que usar esto en vez de PIL.Image.open
+    
+# Creamos la interfaz y la lanzamos. 
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(480, 640)), outputs=gr.inputs.Image(shape=(480, 640)), examples=['color_61.jpg','color_62.jpg']).launch(share=False)
 
-demo.launch()