213 lines
16 KiB
Plaintext
213 lines
16 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"%matplotlib inline\n",
|
|
"import tensorflow as tf\n",
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import math\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import msgpack as msg\n",
|
|
"import msgpack_numpy as m\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from skimage.transform import resize\n",
|
|
"# from sklearn.color import rgb2gray\n",
|
|
"m.patch()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"collapsed": true
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"def load_face_files():\n",
|
|
" all_data = [msg.load(open('./face_images/face_images{}.bin'.format(i),'rb')) for i in range(1,6)]\n",
|
|
" images = np.vstack([i[b'images'] for i in all_data])\n",
|
|
" gray_images = np.dot(images,np.array([0.2125,0.7154,0.0721]))/255.0\n",
|
|
"# print(gray_images.shape)\n",
|
|
"# scaled_gray_images = resize(,(32,32))/255.0\n",
|
|
"# import pdb;pdb.set_trace()\n",
|
|
" coords = np.vstack([i[b'co-ords'] for i in all_data])\n",
|
|
" coords_norm = coords/255.0\n",
|
|
" return gray_images,coords_norm\n",
|
|
"\n",
|
|
"images,coords = load_face_files()\n",
|
|
"\n",
|
|
"def plot_image(idx,n=1):\n",
|
|
" im = images[idx]\n",
|
|
" part_coords = np.split(coords[idx],3)\n",
|
|
" plt.figure(figsize=(16,16),dpi=80)\n",
|
|
" plt.subplot(n,4,1)\n",
|
|
" plt.imshow(im,'gray')\n",
|
|
" for i in range(2,5):\n",
|
|
" [x,y,w,h] = part_coords[i-2]#[:4]\n",
|
|
" # print([x,y,w,h],all([i<0 for i in [x,y,w,h]]))\n",
|
|
" if not all([j<0 for j in [x,y,w,h]]):\n",
|
|
" plt.subplot(n,4,i)\n",
|
|
" plt.imshow(im[y:y+h,x:x+w],'gray')\n",
|
|
"\n",
|
|
"\n",
|
|
"def get_head_images(c):\n",
|
|
" h_idx = []\n",
|
|
" for (idx,i) in enumerate(c):\n",
|
|
" head_coords = np.split(i,3)[0]\n",
|
|
" if not any([j<0 for j in head_coords]):\n",
|
|
" h_idx.append(idx)\n",
|
|
" return h_idx\n",
|
|
"\n",
|
|
"# plot_image(958)\n",
|
|
"\n",
|
|
"head_idxs = get_head_images(coords)\n",
|
|
"head_images = images[head_idxs].reshape(-1,images.shape[1]*images.shape[2])\n",
|
|
"head_coords = coords[head_idxs,:4].astype(np.float32)\n",
|
|
"tr_head_imgs,te_head_imgs,tr_head_crds,te_head_crds = train_test_split(head_images,head_coords,test_size=0.33)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"collapsed": true,
|
|
"scrolled": true
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"def create_model(input_dim,output_dim):\n",
|
|
" g = tf.Graph()\n",
|
|
" with g.as_default():\n",
|
|
" learning_rate = tf.constant(0.1,name='learning_rate')\n",
|
|
" beta = tf.constant(0.00001,name='regularization_beta')\n",
|
|
" error_upper_bound = tf.constant(1.1,name='upper_bound')\n",
|
|
" error_lower_bound = tf.constant(0.9,name='lower_bound')\n",
|
|
" x = tf.placeholder(tf.float32, [None,input_dim])\n",
|
|
" y = tf.placeholder(tf.float32, [None,output_dim])\n",
|
|
" W1 = tf.Variable(tf.random_normal([input_dim, 512],stddev=2.0/math.sqrt(input_dim)),name='layer_1_weights')\n",
|
|
" b1 = tf.Variable(tf.random_normal([512]),name='bias_1_weights')\n",
|
|
" W2 = tf.Variable(tf.random_normal([512, 128],stddev=2.0/math.sqrt(512)),name='layer_2_weights')\n",
|
|
" b2 = tf.Variable(tf.random_normal([128]),name='bias_2_weights')\n",
|
|
" W_o = tf.Variable(tf.random_normal([128, output_dim],stddev=2.0/math.sqrt(128)),name='layer_output_weights')\n",
|
|
" b_o = tf.Variable(tf.random_normal([output_dim]),name='bias_output_weights')\n",
|
|
" layer_1 = tf.nn.relu(tf.add(tf.matmul(x,W1),b1))\n",
|
|
" layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1,W2),b2))\n",
|
|
" y_ = tf.nn.sigmoid(tf.add(tf.matmul(layer_2,W_o),b_o))\n",
|
|
" distance = tf.losses.mean_squared_error(labels = y,predictions = y_)\n",
|
|
" regularized_loss = distance+beta*(tf.nn.l2_loss(W1)+tf.nn.l2_loss(W2)+tf.nn.l2_loss(W_o)+tf.nn.l2_loss(b1)+tf.nn.l2_loss(b2)+tf.nn.l2_loss(b_o))\n",
|
|
" ratio = tf.div(y,y_)\n",
|
|
" accuracy = distance#tf.reduce_mean(tf.cast((ratio < error_upper_bound) & (ratio > error_lower_bound), tf.float32))\n",
|
|
" tf.summary.scalar('distance', distance)\n",
|
|
" tf.summary.histogram('Weights1', W1)\n",
|
|
" tf.summary.histogram('Bias1', b1)\n",
|
|
" tf.summary.histogram('Weights2', W2)\n",
|
|
" tf.summary.histogram('Bias2', b2)\n",
|
|
" tf.summary.histogram('Weights_output', W_o)\n",
|
|
" tf.summary.histogram('Bias_output', b_o)\n",
|
|
" merged_summary = tf.summary.merge_all()\n",
|
|
" train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(regularized_loss)\n",
|
|
" return (g,x,y,y_,train_step,accuracy,merged_summary)\n",
|
|
"\n",
|
|
"(g,x,y,y_,train_step,accuracy,merged_summary) = create_model(tr_head_imgs.shape[1],tr_head_crds.shape[1])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {
|
|
"collapsed": false
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"distance on validation set 0.123010858893\n",
|
|
"distance on validation set 0.0423361249268\n"
|
|
]
|
|
},
|
|
{
|
|
"ename": "KeyboardInterrupt",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[1;32m<ipython-input-5-ee62be87709e>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 21\u001b[0m \u001b[1;32mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"distance on validation set {}\"\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0macc\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;31m#,'saved to ',save_path)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 22\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 23\u001b[1;33m \u001b[0mtrain_model\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mg\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my_\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mtrain_step\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0maccuracy\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmerged_summary\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
|
|
"\u001b[1;32m<ipython-input-5-ee62be87709e>\u001b[0m in \u001b[0;36mtrain_model\u001b[1;34m(g, x, y, y_, train_step, accuracy, merged_summary)\u001b[0m\n\u001b[0;32m 12\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m20000\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 13\u001b[0m \u001b[0mbatch_xs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mbatch_ys\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbatch_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtr_head_imgs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mtr_head_crds\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m128\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 14\u001b[1;33m \u001b[0ms\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrun\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mtrain_step\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mfeed_dict\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m{\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mbatch_xs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0mbatch_ys\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 15\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m%\u001b[0m\u001b[1;36m100\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 16\u001b[0m \u001b[0mt_batch_xs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mt_batch_ys\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbatch_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtr_head_imgs\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mtr_head_crds\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m32\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m/media/Data/Test/py/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36mrun\u001b[1;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 887\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 888\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[1;32m--> 889\u001b[1;33m run_metadata_ptr)\n\u001b[0m\u001b[0;32m 890\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 891\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m/media/Data/Test/py/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_run\u001b[1;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 1118\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mfinal_fetches\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mfinal_targets\u001b[0m \u001b[1;32mor\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mhandle\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mfeed_dict_tensor\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1119\u001b[0m results = self._do_run(handle, final_targets, final_fetches,\n\u001b[1;32m-> 1120\u001b[1;33m feed_dict_tensor, options, run_metadata)\n\u001b[0m\u001b[0;32m 1121\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1122\u001b[0m \u001b[0mresults\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m/media/Data/Test/py/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_do_run\u001b[1;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[0;32m 1315\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mhandle\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1316\u001b[0m return self._do_call(_run_fn, self._session, feeds, fetches, targets,\n\u001b[1;32m-> 1317\u001b[1;33m options, run_metadata)\n\u001b[0m\u001b[0;32m 1318\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1319\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_do_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_prun_fn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_session\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeeds\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetches\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m/media/Data/Test/py/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_do_call\u001b[1;34m(self, fn, *args)\u001b[0m\n\u001b[0;32m 1321\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_do_call\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1322\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1323\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1324\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mOpError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1325\u001b[0m \u001b[0mmessage\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcompat\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mas_text\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0me\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m/media/Data/Test/py/lib/python2.7/site-packages/tensorflow/python/client/session.pyc\u001b[0m in \u001b[0;36m_run_fn\u001b[1;34m(session, feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[0;32m 1300\u001b[0m return tf_session.TF_Run(session, options,\n\u001b[0;32m 1301\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget_list\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1302\u001b[1;33m status, run_metadata)\n\u001b[0m\u001b[0;32m 1303\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1304\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_prun_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msession\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"def batch_data(data_x,data_y,size=128):\n",
|
|
" batch_idxs = np.random.randint(0,data_x.shape[0],size=size)\n",
|
|
" return (data_x[batch_idxs],data_y[batch_idxs])\n",
|
|
"\n",
|
|
"def train_model(g,x,y,y_,train_step,accuracy,merged_summary):\n",
|
|
" with g.as_default():\n",
|
|
" with tf.Session() as s:\n",
|
|
" train_writer = tf.summary.FileWriter('./tensor_log',s.graph)\n",
|
|
" tf.global_variables_initializer().run()\n",
|
|
"# saver = tf.train.Saver()\n",
|
|
" # saver.restore(s, \"/tmp/model.ckpt\")\n",
|
|
" for i in range(20000):\n",
|
|
" batch_xs,batch_ys = batch_data(tr_head_imgs,tr_head_crds,128)\n",
|
|
" s.run([train_step],feed_dict={x:batch_xs,y:batch_ys})\n",
|
|
" if i%100 == 0:\n",
|
|
" t_batch_xs,t_batch_ys = batch_data(tr_head_imgs,tr_head_crds,32)\n",
|
|
" [acc]= s.run([accuracy], feed_dict={x: t_batch_xs,y: t_batch_ys})\n",
|
|
" # train_writer.add_summary(summary,i)\n",
|
|
"# save_path = saver.save(s, \"/tmp/model.ckpt\")\n",
|
|
"# print(y_vals,t_batch_ys)\n",
|
|
" print(\"distance on validation set {}\".format(acc))#,'saved to ',save_path)\n",
|
|
"\n",
|
|
"train_model(g,x,y,y_,train_step,accuracy,merged_summary)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {
|
|
"collapsed": true
|
|
},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"hide_input": false,
|
|
"kernelspec": {
|
|
"display_name": "Python 2",
|
|
"language": "python",
|
|
"name": "python2"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 2
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython2",
|
|
"version": "2.7.14"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|