Halaman

    Social Items

Recognizing the environment in one glance is one of the human brain’s most accomplished deeds. While the tremendous recent progress in object recognition tasks originates from the availability of large datasets such as COCO and the rise of Convolution Neural Networks ( CNNs) to learn high-level features, scene recognition performance has not achieved the same level of success.

In this blog post, we will see how classification models perform on classifying images of a scene. For this task, we have taken the Places365-Standard dataset to train the model. This dataset has 1,803,460 training images and 365 classes with the image number per class varying from 3,068 to 5,000 and the size of images is 256*256.

Installing and Downloading the data

!git clone https://github.com/Tessellate-Imaging/monk_v1.git
! cd monk_v1/installation/Linux && pip install -r requirements_cu9.txt

After installing the dependencies, I downloaded the Places365-Standard dataset which is available to download from here.

Create an Experiment

I have created an experiment, and for this task, I used mxnet gluon back-end.

import os
import sys
sys.path.append("monk_v1/monk/");
from gluon_prototype import prototype
gtf = prototype(verbose=1);

gtf.Prototype("Places_365", "Experiment");

 

Model Selection and Training

gtf.Default(dataset_path="train/",
path_to_csv="labels.csv",
model_name="vgg16",
freeze_base_network=False,
num_epochs=20);
gtf.Train();

Prediction

gtf = prototype(verbose=1);
gtf.Prototype("Places_365", "Experiment", eval_infer=True);
img_name = "test_256/Places365_test_00208427.jpg"
predictions = gtf.Infer(img_name=img_name);
from IPython.display import Image
Image(filename=img_name)

img_name = "test_256/Places365_test_00151496.jpg" 
predictions = gtf.Infer(img_name=img_name);
from IPython.display import Image
Image(filename=img_name)
Prediction on test images
Wrong Image in baseball_field
img=mpimg.imread(“images/train/baseball_field2469.jpg”)
imgplot = plt.imshow(img)
Label: field_road
Label: forest_road

Natural Scene Recognition Using Deep Learning

Recognizing the environment in one glance is one of the human brain’s most accomplished deeds. While the tremendous recent progress in object recognition tasks originates from the availability of large datasets such as COCO and the rise of Convolution Neural Networks ( CNNs) to learn high-level features, scene recognition performance has not achieved the same level of success.

In this blog post, we will see how classification models perform on classifying images of a scene. For this task, we have taken the Places365-Standard dataset to train the model. This dataset has 1,803,460 training images and 365 classes with the image number per class varying from 3,068 to 5,000 and the size of images is 256*256.

Installing and Downloading the data

!git clone https://github.com/Tessellate-Imaging/monk_v1.git
! cd monk_v1/installation/Linux && pip install -r requirements_cu9.txt

After installing the dependencies, I downloaded the Places365-Standard dataset which is available to download from here.

Create an Experiment

I have created an experiment, and for this task, I used mxnet gluon back-end.

import os
import sys
sys.path.append("monk_v1/monk/");
from gluon_prototype import prototype
gtf = prototype(verbose=1);

gtf.Prototype("Places_365", "Experiment");

 

Model Selection and Training

gtf.Default(dataset_path="train/",
path_to_csv="labels.csv",
model_name="vgg16",
freeze_base_network=False,
num_epochs=20);
gtf.Train();

Prediction

gtf = prototype(verbose=1);
gtf.Prototype("Places_365", "Experiment", eval_infer=True);
img_name = "test_256/Places365_test_00208427.jpg"
predictions = gtf.Infer(img_name=img_name);
from IPython.display import Image
Image(filename=img_name)

img_name = "test_256/Places365_test_00151496.jpg" 
predictions = gtf.Infer(img_name=img_name);
from IPython.display import Image
Image(filename=img_name)
Prediction on test images
Wrong Image in baseball_field
img=mpimg.imread(“images/train/baseball_field2469.jpg”)
imgplot = plt.imshow(img)
Label: field_road
Label: forest_road

No comments