Comments (1)
import matplotlib.pyplot as plt
import numpy as np
from ut_ import *
import os
import cv2
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
image_size = (720, 1024) #(512,512) (720, 1280)
x = cv2.imread("9acec1f912673a1364dd776355b707ce-44684.jpg")
x = cv2.resize(x,image_size[::-1])
x = x.reshape(-1,x.shape[0],x.shape[1],x.shape[2])
n_classes = len(get_VOC2012_classes()) - 1
SegClass = SegModel(None, image_size)
model1 = SegClass.create_seg_model(net='subpixel',n=n_classes, load_weights=False, multi_gpu=False, backbone='xception')
model1.load_weights('weights/xception_subpixel.h5')
preds1 = np.argmax(model1.predict(x), -1)[0].reshape(image_size)
plt.figure(figsize=(14,10))
plt.subplot(141)
plt.imshow(preds1)
plt.axis('off');
plt.savefig("test.png", dpi=200, bbox_inches='tight')
from keras-segmentation-deeplab-v3.1.
Related Issues (20)
- AttributeError: 'ProgbarLogger' object has no attribute 'log_values' HOT 1
- Data generator: where use data augmentation and adaptive pixels weights HOT 2
- model only predict one label after training HOT 2
- What is the licensing status of this repo ?
- xception_subpixel.h5 file HOT 1
- Train assumptions HOT 1
- RecursionError when trying to save 'model' and its 'trained-weights' into a single .h5 file HOT 1
- Code Debugging HOT 3
- ValueError: Shapes are incompatible when saving and loading model using Subpixel
- Xception backbone
- UnboundLocalError: local variable 'logs' referenced before assignment HOT 2
- Adapting to Cityscapes version
- IndexError: arrays used as indices must be of integer (or boolean) type
- xception_pretrained_weights HOT 1
- Problem with train_generator: list index out of range HOT 7
- Train on a custom dataset HOT 5
- error while using Jaccard loss HOT 1
- Error running segmentation.ipynb HOT 1
- Xception_weights HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from keras-segmentation-deeplab-v3.1.