使用 AWS EC2 上的 Apache MXNet 和 Multimedia Commons 数据集来估计图像位置

    | LocationNet                                                    | PlaNet                           

import os
import urllib
import mxnet as mx
import logging
import numpy as np
from skimage import io, transform
from collections import namedtuple
from math import radians, sin, cos, sqrt, asin
path = 'https://s3.amazonaws.com/mmcommons-tutorial/models/'
model_path = 'models/'
if not os.path.exists(model_path):
os.mkdir(model_path)
urllib.urlretrieve(path+'RN101-5k500-symbol.json', model_path+'RN101-5k500-symbol.json')
urllib.urlretrieve(path+'RN101-5k500-0012.params', model_path+'RN101-5k500-0012.params')

# Load the pre-trained model
prefix = "models/RN101-5k500"
load_epoch = 12
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, load_epoch)
mod = mx.mod.Module(symbol=sym, context=mx.gpu())
mod.bind([('data', (1,3,224,224))], for_training=False)mod.set_params(arg_params, aux_params, allow_missing=True)

# Download and load grids file
urllib.urlretrieve('https://raw.githubusercontent.com/multimedia-berkeley/tutorials/master/grids.txt','grids.txt')
# Load labels.
grids = []
with open('grids.txt', 'r') as f:
for line in f:
line = line.strip().split('\t')
lat = float(line[1])
lng = float(line[2])
grids.append((lat, lng))

def distance(p1, p2):
R = 6371 # Earth radius in km
lat1, lng1, lat2, lng2 = map(radians, (p1[0], p1[1], p2[0], p2[1]))
dlat = lat2 - lat1
dlng = lng2 - lng1
a = sin(dlat * 0.5) ** 2 + cos(lat1) * cos(lat2) * (sin(dlng * 0.5) ** 2)

return 2 * R * asin(sqrt(a))

# mean image for preprocessing
mean_rgb = np.array([123.68, 116.779, 103.939])
mean_rgb = mean_rgb.reshape((3, 1, 1))
def PreprocessImage(path, show_img=False):
# load image.
img = io.imread(path)
# We crop image from center to get size 224x224.
short_side = min(img.shape[:2])
yy = int((img.shape[0] - short_side) / 2)
xx = int((img.shape[1] - short_side) / 2)
crop_img = img[yy : yy + short_side, xx : xx + short_side]
resized_img = transform.resize(crop_img, (224,224))
if show_img:
io.imshow(resized_img)
# convert to numpy.ndarray
sample = np.asarray(resized_img) * 256
# swap axes to make image from (224, 224, 3) to (3, 224, 224)
sample = np.swapaxes(sample, 0, 2)
sample = np.swapaxes(sample, 1, 2)
# sub mean
normed_img = sample - mean_rgb
normed_img = normed_img.reshape((1, 3, 224, 224))return [mx.nd.array(normed_img)]

Batch = namedtuple('Batch', ['data'])
def predict(imgurl, prefix='images/'):
download_url(imgurl, prefix)
imgname = imgurl.split('/')[-1]
batch = PreprocessImage(prefix + imgname, True)
#predict and show top 5 results
mod.forward(Batch(batch), is_train=False)
prob = mod.get_outputs()[0].asnumpy()[0]
pred = np.argsort(prob)[::-1]
result = list()
for i in range(5):
pred_loc = grids[int(pred[i])]
res = (i+1, prob[pred[i]], pred_loc)
print('rank=%d, prob=%f, lat=%s, lng=%s' \
% (i+1, prob[pred[i]], pred_loc[0], pred_loc[1]))
result.append(res[2])
return result
def download_url(imgurl, img_directory):
if not os.path.exists(img_directory):
os.mkdir(img_directory)
imgname = imgurl.split('/')[-1]
filepath = os.path.join(img_directory, imgname)
if not os.path.exists(filepath):
filepath, _ = urllib.urlretrieve(imgurl, filepath)
statinfo = os.stat(filepath)
print('Succesfully downloaded', imgname, statinfo.st_size, 'bytes.')

return filepath

#download and predict geo-location of an image of Tokyo Tower
url = 'https://farm5.staticflickr.com/4275/34103081894_f7c9bfa86c_k_d.jpg'

result = predict(url)

rank=1, prob=0.139923, lat=35.6599344486, lng=139.728919109
rank=2, prob=0.095210, lat=35.6546613641, lng=139.745685815
rank=3, prob=0.042224, lat=35.7098435803, lng=139.810458528
rank=4, prob=0.032602, lat=35.6641725688, lng=139.746648114
rank=5, prob=0.023119, lat=35.6901996892, lng=139.692857396

import gmaps
gmaps.configure(api_key="") # Fill in with your API key
fig = gmaps.figure()
for i in range(len(result)):
marker = gmaps.marker_layer([result[i]], label=str(i+1))
fig.add_layer(marker)
fig