nlothian/imagerecognizer.py

## imagerecognizer.py
from flask import Flask

from flask import request

import simplejson as json
from decimal import Decimal

import numpy as np
import os
import sys


# Make sure that you set this to the location your caffe2 library lies.
caffe2_root = '<enter the path to caffe2 here'
sys.path.insert(0, os.path.join(caffe2_root, 'gen'))

# After setting the caffe2 root path, we will import all the caffe2 libraries needed.
from caffe2.proto import caffe2_pb2
from pycaffe2 import core, net_drawer, workspace

# net is the network definition.
net = caffe2_pb2.NetDef()
net.ParseFromString(open('inception_net.pb').read())
# tensors contain the parameter tensors.
tensors = caffe2_pb2.TensorProtos()
tensors.ParseFromString(open('inception_tensors.pb').read())

DEVICE_OPTION = caffe2_pb2.DeviceOption()

# Uncomment this to use the CPU
#DEVICE_OPTION.device_type = caffe2_pb2.CPU

# If you have a GPU and want to run things there, uncomment the below two lines.
# If you have multiple GPUs, you also might want to specify a gpu id.
DEVICE_OPTION.device_type = caffe2_pb2.CUDA
DEVICE_OPTION.cuda_gpu_id = 0

# Caffe2 has a concept of "workspace", which is similar to that of Matlab. Each workspace
# is a self-contained set of tensors and networks. In this case, we will just use the default
# workspace so we won't dive too deep into it.
workspace.SwitchWorkspace('default')

# First, we feed all the parameters to the workspace.
for param in tensors.protos:
    workspace.FeedBlob(param.name, param, DEVICE_OPTION)
# The network expects an input blob called "input", which we create here.
# The content of the input blob is going to be fed when we actually do
# classification.
workspace.CreateBlob("input")
# Specify the device option of the network, and then create it.
net.device_option.CopyFrom(DEVICE_OPTION)
workspace.CreateNet(net)


# We will also load the synsets file where we can look up the actual words for each of our prediction.
synsets = [l.strip() for l in open('synsets.txt').readlines()]

def ClassifyFromUrl(url, output_name="softmax2"):
    from skimage import io, transform
    img = io.imread(url)

    # Crop the center
    shorter_edge = min(img.shape[:2])
    crop_height = (img.shape[0] - shorter_edge) / 2
    crop_width = (img.shape[1] - shorter_edge) / 2
    cropped_img = img[crop_height:crop_height + shorter_edge, crop_width:crop_width + shorter_edge]
    # Resize the image to 224 * 224
    resized_img = transform.resize(cropped_img, (224, 224))

    # normalize the image and feed it into the network. The network expects
    # a four-dimensional tensor, since it can process images in batches. In our
    # case, we will basically make the image as a batch of size one.
    normalized_img = resized_img.reshape((1, 224, 224, 3)).astype(np.float32) * 256 - 117
    workspace.FeedBlob("input", normalized_img, DEVICE_OPTION)
    workspace.RunNet("inception")
    return workspace.FetchBlob(output_name)


app = Flask(__name__)

@app.route('/', methods=['GET'])
def index():
    return "<html><body><form action='recognize' method='GET'><input type='text' size='100' name='url'><button type='submit'>Submit</button></form></body></html>"


@app.route('/recognize', methods=['GET'])
def recognize():

    url = request.args.get('url', '')

    predictions = ClassifyFromUrl(url).flatten()
    indices = np.argsort(predictions)

    output = [];
    # We want the first 4 predictions
    maxIdx = -1 * min(len(predictions), 5)


    for idx in indices[:maxIdx:-1]:
        output.append({'prediction':synsets[idx], 'score':Decimal(str(predictions[idx]))})


    #return jsonify(predictions=output)
    return json.dumps({'predictions':output}, use_decimal=True)

if __name__ == '__main__':
    app.debug = True
    app.run()
	from flask import Flask

	from flask import request

	import simplejson as json
	from decimal import Decimal

	import numpy as np
	import os
	import sys


	# Make sure that you set this to the location your caffe2 library lies.
	caffe2_root = '<enter the path to caffe2 here'
	sys.path.insert(0, os.path.join(caffe2_root, 'gen'))

	# After setting the caffe2 root path, we will import all the caffe2 libraries needed.
	from caffe2.proto import caffe2_pb2
	from pycaffe2 import core, net_drawer, workspace

	# net is the network definition.
	net = caffe2_pb2.NetDef()
	net.ParseFromString(open('inception_net.pb').read())
	# tensors contain the parameter tensors.
	tensors = caffe2_pb2.TensorProtos()
	tensors.ParseFromString(open('inception_tensors.pb').read())

	DEVICE_OPTION = caffe2_pb2.DeviceOption()

	# Uncomment this to use the CPU
	#DEVICE_OPTION.device_type = caffe2_pb2.CPU

	# If you have a GPU and want to run things there, uncomment the below two lines.
	# If you have multiple GPUs, you also might want to specify a gpu id.
	DEVICE_OPTION.device_type = caffe2_pb2.CUDA
	DEVICE_OPTION.cuda_gpu_id = 0

	# Caffe2 has a concept of "workspace", which is similar to that of Matlab. Each workspace
	# is a self-contained set of tensors and networks. In this case, we will just use the default
	# workspace so we won't dive too deep into it.
	workspace.SwitchWorkspace('default')

	# First, we feed all the parameters to the workspace.
	for param in tensors.protos:
	workspace.FeedBlob(param.name, param, DEVICE_OPTION)
	# The network expects an input blob called "input", which we create here.
	# The content of the input blob is going to be fed when we actually do
	# classification.
	workspace.CreateBlob("input")
	# Specify the device option of the network, and then create it.
	net.device_option.CopyFrom(DEVICE_OPTION)
	workspace.CreateNet(net)


	# We will also load the synsets file where we can look up the actual words for each of our prediction.
	synsets = [l.strip() for l in open('synsets.txt').readlines()]

	def ClassifyFromUrl(url, output_name="softmax2"):
	from skimage import io, transform
	img = io.imread(url)

	# Crop the center
	shorter_edge = min(img.shape[:2])
	crop_height = (img.shape[0] - shorter_edge) / 2
	crop_width = (img.shape[1] - shorter_edge) / 2
	cropped_img = img[crop_height:crop_height + shorter_edge, crop_width:crop_width + shorter_edge]
	# Resize the image to 224 * 224
	resized_img = transform.resize(cropped_img, (224, 224))

	# normalize the image and feed it into the network. The network expects
	# a four-dimensional tensor, since it can process images in batches. In our
	# case, we will basically make the image as a batch of size one.
	normalized_img = resized_img.reshape((1, 224, 224, 3)).astype(np.float32) * 256 - 117
	workspace.FeedBlob("input", normalized_img, DEVICE_OPTION)
	workspace.RunNet("inception")
	return workspace.FetchBlob(output_name)


	app = Flask(__name__)

	@app.route('/', methods=['GET'])
	def index():
	return "<html><body><form action='recognize' method='GET'><input type='text' size='100' name='url'><button type='submit'>Submit</button></form></body></html>"


	@app.route('/recognize', methods=['GET'])
	def recognize():

	url = request.args.get('url', '')

	predictions = ClassifyFromUrl(url).flatten()
	indices = np.argsort(predictions)

	output = [];
	# We want the first 4 predictions
	maxIdx = -1 * min(len(predictions), 5)


	for idx in indices[:maxIdx:-1]:
	output.append({'prediction':synsets[idx], 'score':Decimal(str(predictions[idx]))})


	#return jsonify(predictions=output)
	return json.dumps({'predictions':output}, use_decimal=True)

	if __name__ == '__main__':
	app.debug = True
	app.run()