| import play.api.libs.ws.ning._ | |
| import play.api.libs.ws._ | |
| import play.api.libs.concurrent.Execution.Implicits | |
| object Sample { | |
| def main(args: Array[String]) { | |
| implicit val client = NingWSClient() | |
| implicit val context = Implicits.defaultContext | |
| // close with sslClient.close() when finished with client |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| # Make sure that caffe is on the python path: | |
| caffe_root = '../' # this file is expected to be in {caffe_root}/examples | |
| import sys | |
| sys.path.insert(0, caffe_root + 'python') | |
| import caffe |
| # Using flickr_api to search and download images | |
| # https://github.com/alexis-mignon/python-flickr-api/wiki/Tutorial | |
| import flickr_api as f | |
| f.set_keys(api_key = 'xxxxxxxxxxxxxxxxxxxxxxx', | |
| api_secret = 'xxxxxxxxxxx') | |
| auth = f.auth.AuthHandler() | |
| w = f.Walker(f.Photo.search, tags="sumo") |
| # Dependencies: https://github.com/alexis-mignon/python-flickr-api | |
| import flickr_api as f | |
| from sets import Set | |
| f.set_keys(api_key = 'xxxxxxxxxxxxxxxxxxxxxxxxxxx', | |
| api_secret = 'xxxxxxxxxxxxxxx') | |
| auth = f.auth.AuthHandler() |
| from skimage import io | |
| from skimage import transform as tf | |
| import random | |
| import numpy as np | |
| import md5 | |
| import glob | |
| def rotate(image): | |
| angle = random.randint(1,360) |
| #!/usr/bin/env python | |
| # -------------------------------------------------------- | |
| # Faster R-CNN | |
| # Copyright (c) 2015 Microsoft | |
| # Licensed under The MIT License [see LICENSE for details] | |
| # Written by Ross Girshick | |
| # -------------------------------------------------------- | |
| """ |
| def detect_and_save(self, input_path): | |
| img = cv2.imread(input_path) | |
| copy_img = img.copy() | |
| bboxes = self.detect(img) | |
| for bbox_cls in bboxes: | |
| for bbox, class_name in bbox_cls: | |
| cv2.rectangle(frameClone, (bbox[0], bbox[1]), (bbox[2], bbox[3]), (0, 255, 0), 2) | |
| cv2.putText(copy_img,class_name,(bbox[0],bbox[1] - 20), cv2.FONT_HERSHEY_PLAIN, 1.0, (0,0,255), 1) | |
| save_path = "data/" +str(hashlib.md5(img).hexdigest()) + ".jpg" | |
| cv2.imwrite(save_path,copy_img) |
| img = read_image(file_name) | |
| x_batch = np.ndarray((1, 3, model.insize, model.insize), dtype=np.float32) | |
| x_batch[0] = img | |
| y_batch = np.ndarray((1,), dtype=np.int32) | |
| y_batch[0] = label | |
| x = chainer.Variable(xp.asarray(x_batch), volatile=True) | |
| t = chainer.Variable(xp.asarray(y_batch), volatile=True) |
This tutorial is a fine-tuned clone of zeyuanxy's one for the py-faster-rcnn code.
We will illustrate how to train Py-Faster-RCNN on another dataset in the following steps, and we will take INRIA Person as the example dataset.
The current tutorial need you to have clone and tested the regular py-faster-rcnn repository from rbgirshick.
$ git clone https://github.com/rbgirshick/py-faster-rcnn
| image = cv2.imread('imgtest/boss.jpg') | |
| cpimg = image.copy() | |
| image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) | |
| image = skimage.img_as_float(image).astype(np.float32) |