Eval resized image

[tsly123]

Hi @cydonia999,

First, thank you for your work.
I try to detect the face with resized image (512x512x3). I added the cv2.resize function to your code but the result was not as expected. The bbx does not cover exactly the face as shown in followed images, original resolution and resized respectively.

#  line  105 - 117 in  tiny_face_eval.py

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    for filename in filenames:
      fname = filename.split(os.sep)[-1]
      raw_img = cv2.imread(filename)
      raw_img = cv2.cvtColor(raw_img, cv2.COLOR_BGR2RGB)
      raw_img = cv2.resize(raw_img, (img_width, img_height))     <<<<<<<<   RESIZE IMAGE (512x512x3)
      raw_img_f = raw_img.astype(np.float32)

      def _calc_scales():
        raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
        min_scale = min(np.floor(np.log2(np.max(clusters_w[normal_idx] / raw_w))),
                        np.floor(np.log2(np.max(clusters_h[normal_idx] / raw_h))))

Do you have any suggest to how can I get the the result as original resolution image?
Thank you.