File size: 2,862 Bytes
772b566 40bbefd 772b566 7afe095 4763157 7afe095 35fd4e9 772b566 0dcb86b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
from huggingface_hub import from_pretrained_fastai
import gradio as gr
from fastai.vision.all import *
import PIL
import torchvision.transforms as transforms
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"))
def ParentSplitter(x):
return Path(x).parent.name==test_name
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"])
transforms=Compose([HorizontalFlip(p=0.5),
Rotate(p=0.40,limit=10),GridDistortion()
],p=1)
transformPipeline=SegmentationAlbumentationsTransform(transforms)
class TargetMaskConvertTransform(ItemTransform):
def __init__(self):
pass
def encodes(self, x):
img,mask = x
#Convert to array
mask = np.array(mask)
# Aquí definimos cada clase en la máscara
# uva:
mask[mask==255]=1
# hojas:
mask[mask==150]=2
# conductores:
mask[mask==76]=3
mask[mask==74]=3
# madera:
mask[mask==29]=4
mask[mask==25]=4
# Back to PILMask
mask = PILMask.create(mask)
return img, mask
repo_id = "paascorb/practica3_Segmentation"
learner = from_pretrained_fastai(repo_id)
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)
def predict(img):
img = PIL.Image.fromarray(img, "RGB")
image = transforms.Resize((480,640))(img)
tensor = transform_image(image=image)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
learner.to(device)
with torch.no_grad():
outputs = learner(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'))
gr.Interface(fn=predict, inputs=gr.inputs.Image(shape=(128, 128)), outputs=[gr.outputs.Image(type="pil", label="Predicción")], examples=['color_155.jpg','color_154.jpg']).launch(share=False) |