Update app.py

app.py

@@ -1,146 +1,106 @@
+from huggingface_hub import from_pretrained_fastai
 import gradio as gr
-import numpy as np
+
+from fastai.vision.all import *
+
+import torchvision.transforms as transforms
+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
-from diffusers import DiffusionPipeline
-import torch
+import PIL
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+#Definimos las funciones de transformacion que hemos creado en la practica para poder tratar los datos de entrada y que funcione bien
+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)
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+class TargetMaskConvertTransform(ItemTransform):
+    def __init__(self):
+        pass
+    def encodes(self, x):
+        img,mask = x
 
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
+        #Convertimos a array
+        mask = np.array(mask)
 
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+        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
 
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-        
-    generator = torch.Generator().manual_seed(seed)
-    
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
+        # 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"])
+
+#Cargamos el modelo
+
+repo_id = "jegilj/Practica3"
+learn = from_pretrained_fastai(repo_id)
+model = learn.model
+model = model.cpu()
+
+
+# Funcion de predicción
+def predict(img_ruta):
+    img = PIL.Image.fromarray(img_ruta)
+    image = transforms.Resize((480,640))(img)
+    tensor = transform_image(image=image)
+    model.to(device)
+    with torch.no_grad():
+      outputs = model(tensor)
     
-    return image
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
+    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'))
+
     
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
-        with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
-        )
-
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
-    )
-
-demo.queue().launch()
+# 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_184.jpg','color_189.jpg']).launch(share=False)