Update app.py

app.py

@@ -1,75 +1,105 @@
 from huggingface_hub import from_pretrained_fastai
-from fastai.vision.all import *
 import gradio as gr
-import numpy as np
-from PIL import Image
+from fastai.vision.all import *
 import torchvision.transforms as transforms
-from albumentations import (
-    Compose, GridDistortion, HorizontalFlip, Rotate
-)
+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 torch
+import random
+import PIL
 
+#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):
-    preprocess = transforms.Compose([
-        transforms.ToTensor(),
-        transforms.Normalize([0.485, 0.456, 0.406],
-                             [0.229, 0.224, 0.225])
-    ])
-    return preprocess(image).unsqueeze(0).to(device)
-
-def get_y_fn(x):
-    return Path(str(x).replace("Images", "Labels").replace("color", "gt").replace(".jpg", ".png"))
+    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
+        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
-        mask[(mask==76) | (mask==74)] = 4
-        mask[(mask==29) | (mask==25)] = 3
-        return img, PILMask.create(mask)
+
+        mask[(mask!=255) & (mask!=150) & (mask!=76) & (mask!=74) & (mask!=29) & (mask!=25)]=0
+        mask[mask==255]=1
+        mask[mask==150]=2
+        mask[mask==76]=4
+        mask[mask==74]=4
+        mask[mask==29]=3
+        mask[mask==25]=3
+
+        # 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 __init__(self, aug):
+        self.aug = aug
+
     def encodes(self, x):
-        img, mask = x
+        img,mask = x
         aug = self.aug(image=np.array(img), mask=np.array(mask))
         return PILImage.create(aug["image"]), PILMask.create(aug["mask"])
 
-repo_id = "PablitoGil14/AP-Practica3"
+#Cargamos el modelo
+repo_id = "luisvarona/Practica3"
 learn = from_pretrained_fastai(repo_id)
-model = learn.model.cpu()
+model = learn.model
+model = model.cpu()
 
-def predict(img_input):
-    image = Image.fromarray(img_input).resize((640, 480))
-    tensor = transform_image(image)
+
+# 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():
-        output = model(tensor)
-    pred = torch.argmax(output, dim=1).squeeze().cpu().numpy()
-
-    # Recolorear la máscara
-    colored = np.zeros_like(pred, dtype=np.uint8)
-    colored[pred == 1] = 255
-    colored[pred == 2] = 150
-    colored[pred == 3] = 29
-    colored[pred == 4] = 74
-    return Image.fromarray(colored)
-
-demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="numpy", label="Sube una imagen", shape=(480, 640)),
-    outputs=gr.Image(type="pil", label="Máscara generada"),
-    examples=["color_161.jpg", "color_162.jpg"],
-    title="Segmentador de Viñedos",
-    description="Sube una imagen y este modelo segmentará racimos de uva, hojas, madera y postes."
-)
-
-demo.launch()
+      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'))
 
+    
+    #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_161.jpg','color_162.jpg']).launch(share=False)