Update app.py

app.py

@@ -1,26 +1,104 @@
-from huggingface_hub import from_pretrained_fastai
 import gradio as gr
+import torchvision.transforms as transforms
+import torchvision.transforms as transforms
+import random
+import PIL
+
+from fastai.vision.all import *
+from huggingface_hub import from_pretrained_fastai
+from fastai.basics import *
+from fastai.vision import models
 from fastai.vision.all import *
-import os
+from fastai.metrics import *
+from fastai.data.all import *
+from fastai.callback import *
+from pathlib import Path
+
+
+def get_y_fn (x):
+    return Path(str(x).replace("Images","Labels").replace("color","gt").replace(".jpg",".png"))
+
+from albumentations import (
+    Compose,
+    OneOf,
+    ElasticTransform,
+    GridDistortion,
+    OpticalDistortion,
+    HorizontalFlip,
+    Rotate,
+    Transpose,
+    CLAHE,
+    ShiftScaleRotate,
+    VerticalFlip
+)
+
+class SegmentationAlbumentationsTransform(ItemTransform):
+    split_idx = 0
 
-try:
-    import toml
-except ImportError:
-    os.system('pip install toml')
-    import toml
+    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"])
+
+class TargetMaskConvertTransform(ItemTransform):
+    def __init__(self):
+        pass
+    def encodes(self, x):
+        img,mask = x
+
+        #Convert to array
+        mask = np.array(mask)
+
+        mask[mask==255]=1
+        mask[mask==150]=2
+        mask[mask==76]=3
+        mask[mask==74]=3
+        mask[mask==29]=4
+        mask[mask==25]=4
+        mask[(mask != 1) & (mask != 2) & (mask != 3) & (mask != 4)] = 0
+
+
+        # Back to PILMask
+        mask = PILMask.create(mask)
+        return img, mask
+
+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)
 
 # repo_id = "YOUR_USERNAME/YOUR_LEARNER_NAME"
 repo_id = "maviced/practica3"
 
 learner = from_pretrained_fastai(repo_id)
 labels = learner.dls.vocab
+model = learner.model
+model = learner.cpu()
 
 # Definimos una función que se encarga de llevar a cabo las predicciones
 def predict(img):
-    # img = PILImage.create(img)
-    pred,pred_idx,probs = learner.predict(img)
-    return {labels[i]: float(probs[i]) for i in range(len(labels))}
+    # img = PILImage.create(img
+    image = transforms.Resize((480,640))(img)
+    tensor = transform_image(image=image)
+    model.to(device)
+    with torch.no_grad():
+        outputs = model(tensor)
+    
+    outputs = torch.argmax(outputs,1)
+    mask = np.array(outputs.cpu())
+    mask[mask==1]=255
+    mask[mask==2]=150
+    mask[mask==3]=76
+    mask[mask==4]=29
+    mask=np.reshape(mask,(480,640))
+    return Image.fromarray(mask.astype('uint8'))
     
 # Creamos la interfaz y la lanzamos. 
-gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=gr.outputs.Label(num_top_classes=3),examples=['color_155.jpg','color_154.jpg']).launch(share=False)
+gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(480, 640)), outputs=gr.inputs.Image(shape=(480, 640)),examples=['color_155.jpg','color_154.jpg']).launch(share=False)