Downloads: 1
Diff of
/notebooks/ni_viewer_best.ipynb
[000000]
..
[ccb1dd]
Switch to unified view
| a | b/notebooks/ni_viewer_best.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 11, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [ |
||
| 8 | { |
||
| 9 | "name": "stdout", |
||
| 10 | "output_type": "stream", |
||
| 11 | "text": [ |
||
| 12 | "Using matplotlib backend: TkAgg\n" |
||
| 13 | ] |
||
| 14 | } |
||
| 15 | ], |
||
| 16 | "source": [ |
||
| 17 | "import nibabel as nib\n", |
||
| 18 | "import os\n", |
||
| 19 | "from nilearn.image import crop_img\n", |
||
| 20 | "from nilearn.image import new_img_like, resample_to_img\n", |
||
| 21 | "import numpy as np\n", |
||
| 22 | "\n", |
||
| 23 | "import sys\n", |
||
| 24 | "sys.path.append('..')\n", |
||
| 25 | "\n", |
||
| 26 | "from scipy.ndimage.filters import gaussian_filter, gaussian_laplace, laplace, maximum_filter, minimum_filter, prewitt, sobel\n", |
||
| 27 | "\n", |
||
| 28 | "from fetal_net.postprocess import postprocess_prediction\n", |
||
| 29 | "\n", |
||
| 30 | "%matplotlib\n", |
||
| 31 | "\n", |
||
| 32 | "def vod(mask1, mask2, verbose=False):\n", |
||
| 33 | " mask1, mask2 = mask1.flatten(), mask2.flatten()\n", |
||
| 34 | " intersection = np.sum((mask1 + mask2) > 1)\n", |
||
| 35 | " union = np.sum((mask1+mask2) > 0)\n", |
||
| 36 | " if verbose:\n", |
||
| 37 | " print('intersection\\t', intersection)\n", |
||
| 38 | " print('union\\t\\t', union)\n", |
||
| 39 | " return 1 - (intersection + 1) / (union + 1)" |
||
| 40 | ] |
||
| 41 | }, |
||
| 42 | { |
||
| 43 | "cell_type": "code", |
||
| 44 | "execution_count": null, |
||
| 45 | "metadata": {}, |
||
| 46 | "outputs": [], |
||
| 47 | "source": [ |
||
| 48 | "!ls ../../Datasets/fetus/78" |
||
| 49 | ] |
||
| 50 | }, |
||
| 51 | { |
||
| 52 | "cell_type": "code", |
||
| 53 | "execution_count": 163, |
||
| 54 | "metadata": {}, |
||
| 55 | "outputs": [ |
||
| 56 | { |
||
| 57 | "name": "stdout", |
||
| 58 | "output_type": "stream", |
||
| 59 | "text": [ |
||
| 60 | "222 260 41_2\r\n" |
||
| 61 | ] |
||
| 62 | } |
||
| 63 | ], |
||
| 64 | "source": [ |
||
| 65 | "!ls ../../predictions/unet96_all/predictions/val/" |
||
| 66 | ] |
||
| 67 | }, |
||
| 68 | { |
||
| 69 | "cell_type": "code", |
||
| 70 | "execution_count": 184, |
||
| 71 | "metadata": { |
||
| 72 | "scrolled": true |
||
| 73 | }, |
||
| 74 | "outputs": [], |
||
| 75 | "source": [ |
||
| 76 | "src_dir = '../../predictions/unet96_all/predictions/val/'\n", |
||
| 77 | "subject_id = '222'\n", |
||
| 78 | "vol = nib.load(os.path.join(src_dir, subject_id, 'data_volume.nii.gz'))\n", |
||
| 79 | "truth = nib.load(os.path.join(src_dir, subject_id, 'truth.nii.gz'))\n", |
||
| 80 | "pred = nib.load(os.path.join(src_dir, subject_id, 'prediction.nii.gz'))" |
||
| 81 | ] |
||
| 82 | }, |
||
| 83 | { |
||
| 84 | "cell_type": "code", |
||
| 85 | "execution_count": 185, |
||
| 86 | "metadata": {}, |
||
| 87 | "outputs": [ |
||
| 88 | { |
||
| 89 | "name": "stdout", |
||
| 90 | "output_type": "stream", |
||
| 91 | "text": [ |
||
| 92 | "thres\t\t: 0.1412296536763702\n", |
||
| 93 | "pp_0_01\t\t: 0.1259709038930662\n", |
||
| 94 | "pp_05_05\t: 0.13838074797935984\n", |
||
| 95 | "pp_1_05\t\t: 0.15213493934900457\n" |
||
| 96 | ] |
||
| 97 | } |
||
| 98 | ], |
||
| 99 | "source": [ |
||
| 100 | "print('thres\\t\\t: {}'.format(vod(truth.get_data(), pred.get_data() > 0.5)))\n", |
||
| 101 | "print('pp_0_01\\t\\t: {}'.format(vod(truth.get_data(), postprocess_prediction(pred.get_data(), gaussian_std=0, threshold=0.1))))\n", |
||
| 102 | "print('pp_05_05\\t: {}'.format(vod(truth.get_data(), postprocess_prediction(pred.get_data(), gaussian_std=0.5, threshold=0.5))))\n", |
||
| 103 | "print('pp_1_05\\t\\t: {}'.format(vod(truth.get_data(), postprocess_prediction(pred.get_data(), gaussian_std=1, threshold=0.5))))" |
||
| 104 | ] |
||
| 105 | }, |
||
| 106 | { |
||
| 107 | "cell_type": "code", |
||
| 108 | "execution_count": 166, |
||
| 109 | "metadata": {}, |
||
| 110 | "outputs": [ |
||
| 111 | { |
||
| 112 | "data": { |
||
| 113 | "text/plain": [ |
||
| 114 | "4.408514612614356" |
||
| 115 | ] |
||
| 116 | }, |
||
| 117 | "execution_count": 166, |
||
| 118 | "metadata": {}, |
||
| 119 | "output_type": "execute_result" |
||
| 120 | } |
||
| 121 | ], |
||
| 122 | "source": [ |
||
| 123 | "np.max(vol.get_data())" |
||
| 124 | ] |
||
| 125 | }, |
||
| 126 | { |
||
| 127 | "cell_type": "code", |
||
| 128 | "execution_count": 186, |
||
| 129 | "metadata": {}, |
||
| 130 | "outputs": [ |
||
| 131 | { |
||
| 132 | "data": { |
||
| 133 | "text/plain": [ |
||
| 134 | "<OrthoSlicer3D: (256, 256, 52)>" |
||
| 135 | ] |
||
| 136 | }, |
||
| 137 | "execution_count": 186, |
||
| 138 | "metadata": {}, |
||
| 139 | "output_type": "execute_result" |
||
| 140 | }, |
||
| 141 | { |
||
| 142 | "name": "stderr", |
||
| 143 | "output_type": "stream", |
||
| 144 | "text": [ |
||
| 145 | "Traceback (most recent call last):\n", |
||
| 146 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 388, in process\n", |
||
| 147 | " proxy(*args, **kwargs)\n", |
||
| 148 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 228, in __call__\n", |
||
| 149 | " return mtd(*args, **kwargs)\n", |
||
| 150 | "TypeError: _cleanup() takes 1 positional argument but 2 were given\n" |
||
| 151 | ] |
||
| 152 | } |
||
| 153 | ], |
||
| 154 | "source": [ |
||
| 155 | "new_img_like(vol, data=vol.get_data()+pred.get_data()*3).orthoview()" |
||
| 156 | ] |
||
| 157 | }, |
||
| 158 | { |
||
| 159 | "cell_type": "code", |
||
| 160 | "execution_count": 99, |
||
| 161 | "metadata": { |
||
| 162 | "collapsed": true |
||
| 163 | }, |
||
| 164 | "outputs": [ |
||
| 165 | { |
||
| 166 | "data": { |
||
| 167 | "text/plain": [ |
||
| 168 | "<OrthoSlicer3D: (256, 256, 108)>" |
||
| 169 | ] |
||
| 170 | }, |
||
| 171 | "execution_count": 99, |
||
| 172 | "metadata": {}, |
||
| 173 | "output_type": "execute_result" |
||
| 174 | }, |
||
| 175 | { |
||
| 176 | "name": "stderr", |
||
| 177 | "output_type": "stream", |
||
| 178 | "text": [ |
||
| 179 | "Traceback (most recent call last):\n", |
||
| 180 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 388, in process\n", |
||
| 181 | " proxy(*args, **kwargs)\n", |
||
| 182 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 228, in __call__\n", |
||
| 183 | " return mtd(*args, **kwargs)\n", |
||
| 184 | "TypeError: _cleanup() takes 1 positional argument but 2 were given\n" |
||
| 185 | ] |
||
| 186 | } |
||
| 187 | ], |
||
| 188 | "source": [ |
||
| 189 | "new_img_like(vol, data=pred.get_data()*2).orthoview()" |
||
| 190 | ] |
||
| 191 | }, |
||
| 192 | { |
||
| 193 | "cell_type": "code", |
||
| 194 | "execution_count": 9, |
||
| 195 | "metadata": { |
||
| 196 | "collapsed": true |
||
| 197 | }, |
||
| 198 | "outputs": [ |
||
| 199 | { |
||
| 200 | "ename": "NameError", |
||
| 201 | "evalue": "name 'postprocess_prediction' is not defined", |
||
| 202 | "traceback": [ |
||
| 203 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 204 | "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", |
||
| 205 | "\u001b[0;32m<ipython-input-9-eccee40acd61>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnew_img_like\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvol\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtruth\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpostprocess_prediction\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpred\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mthreshold\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgaussian_std\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.75\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0morthoview\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", |
||
| 206 | "\u001b[0;31mNameError\u001b[0m: name 'postprocess_prediction' is not defined" |
||
| 207 | ], |
||
| 208 | "output_type": "error" |
||
| 209 | } |
||
| 210 | ], |
||
| 211 | "source": [ |
||
| 212 | "new_img_like(vol, data=truth.get_data()-(postprocess_prediction(pred.get_data(), threshold=0.5, gaussian_std=0.75))).orthoview()" |
||
| 213 | ] |
||
| 214 | }, |
||
| 215 | { |
||
| 216 | "cell_type": "code", |
||
| 217 | "execution_count": 40, |
||
| 218 | "metadata": {}, |
||
| 219 | "outputs": [ |
||
| 220 | { |
||
| 221 | "name": "stdout", |
||
| 222 | "output_type": "stream", |
||
| 223 | "text": [ |
||
| 224 | "[5162475 5280 3609 3332 4608 4416 3130 2749 3290\n", |
||
| 225 | " 181063] [0.11921013 0.19536062 0.27151111 0.3476616 0.42381208 0.49996257\n", |
||
| 226 | " 0.57611306 0.65226355 0.72841404 0.80456452 0.88071501]\n" |
||
| 227 | ] |
||
| 228 | } |
||
| 229 | ], |
||
| 230 | "source": [ |
||
| 231 | "from matplotlib import pyplot as plt\n", |
||
| 232 | "a, bins = np.histogram(pred.get_data())\n", |
||
| 233 | "plt.hist(pred.get_data().reshape([-1]), bins=100) \n", |
||
| 234 | "plt.title(\"histogram\") \n", |
||
| 235 | "plt.show()\n", |
||
| 236 | "print(a,bins)" |
||
| 237 | ] |
||
| 238 | }, |
||
| 239 | { |
||
| 240 | "cell_type": "code", |
||
| 241 | "execution_count": 206, |
||
| 242 | "metadata": {}, |
||
| 243 | "outputs": [ |
||
| 244 | { |
||
| 245 | "name": "stdout", |
||
| 246 | "output_type": "stream", |
||
| 247 | "text": [ |
||
| 248 | "intersection\t 0\n", |
||
| 249 | "union\t\t 645376\n", |
||
| 250 | "1: 0.9999984505180692\n" |
||
| 251 | ] |
||
| 252 | } |
||
| 253 | ], |
||
| 254 | "source": [ |
||
| 255 | "print('1: {}'.format(vod(vol.get_data()>0.5, vol.get_data()>0.5, verbose=True)))" |
||
| 256 | ] |
||
| 257 | }, |
||
| 258 | { |
||
| 259 | "cell_type": "code", |
||
| 260 | "execution_count": 209, |
||
| 261 | "metadata": {}, |
||
| 262 | "outputs": [ |
||
| 263 | { |
||
| 264 | "name": "stdout", |
||
| 265 | "output_type": "stream", |
||
| 266 | "text": [ |
||
| 267 | "intersection\t 295947\n", |
||
| 268 | "union\t\t 338601\n", |
||
| 269 | "1: 0.1259709038930662\n" |
||
| 270 | ] |
||
| 271 | } |
||
| 272 | ], |
||
| 273 | "source": [ |
||
| 274 | "print('1: {}'.format(vod(truth.get_data(), postprocess_prediction(pred.get_data(), gaussian_std=0.1, threshold=0.1), verbose=True)))\n", |
||
| 275 | "#print('2: {}'.format(vod(truth.get_data(), postprocess_prediction(pred2.get_data(), gaussian_std=1, threshold=0.5))))\n", |
||
| 276 | "#print('3: {}'.format(vod(truth.get_data(), postprocess_prediction(pred3.get_data(), gaussian_std=1, threshold=0.5))))" |
||
| 277 | ] |
||
| 278 | }, |
||
| 279 | { |
||
| 280 | "cell_type": "code", |
||
| 281 | "execution_count": null, |
||
| 282 | "metadata": {}, |
||
| 283 | "outputs": [], |
||
| 284 | "source": [] |
||
| 285 | }, |
||
| 286 | { |
||
| 287 | "cell_type": "code", |
||
| 288 | "execution_count": 77, |
||
| 289 | "metadata": {}, |
||
| 290 | "outputs": [ |
||
| 291 | { |
||
| 292 | "data": { |
||
| 293 | "text/plain": [ |
||
| 294 | "<OrthoSlicer3D: (256, 256, 52)>" |
||
| 295 | ] |
||
| 296 | }, |
||
| 297 | "execution_count": 77, |
||
| 298 | "metadata": {}, |
||
| 299 | "output_type": "execute_result" |
||
| 300 | }, |
||
| 301 | { |
||
| 302 | "name": "stderr", |
||
| 303 | "output_type": "stream", |
||
| 304 | "text": [ |
||
| 305 | "Traceback (most recent call last):\n", |
||
| 306 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 388, in process\n", |
||
| 307 | " proxy(*args, **kwargs)\n", |
||
| 308 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 228, in __call__\n", |
||
| 309 | " return mtd(*args, **kwargs)\n", |
||
| 310 | "TypeError: _cleanup() takes 1 positional argument but 2 were given\n" |
||
| 311 | ] |
||
| 312 | } |
||
| 313 | ], |
||
| 314 | "source": [ |
||
| 315 | "new_img_like(truth, data=1*truth.get_data()+1*(postprocess_prediction(pred.get_data(), gaussian_std=0.5, threshold=0.5).astype(int))).orthoview()" |
||
| 316 | ] |
||
| 317 | }, |
||
| 318 | { |
||
| 319 | "cell_type": "code", |
||
| 320 | "execution_count": 218, |
||
| 321 | "metadata": {}, |
||
| 322 | "outputs": [ |
||
| 323 | { |
||
| 324 | "name": "stdout", |
||
| 325 | "output_type": "stream", |
||
| 326 | "text": [ |
||
| 327 | "0.0 - 0.14122965\n", |
||
| 328 | "0.33 - 0.14118736\n", |
||
| 329 | "0.67 - 0.14025291\n", |
||
| 330 | "1.0 - 0.15213494\n", |
||
| 331 | "1.3 - 0.1559348\n", |
||
| 332 | "1.7 - 0.15859626\n", |
||
| 333 | "2.0 - 0.16103441\n", |
||
| 334 | "2.3 - 0.16361388\n", |
||
| 335 | "2.7 - 0.16607572\n", |
||
| 336 | "3.0 - 0.16784486\n" |
||
| 337 | ] |
||
| 338 | } |
||
| 339 | ], |
||
| 340 | "source": [ |
||
| 341 | "for i in range(10):\n", |
||
| 342 | " print('{:.2} - {:.8}'.format(i/3, vod(truth.get_data(), gaussian_filter(pred.get_data(), i/3) > 0.5)))" |
||
| 343 | ] |
||
| 344 | }, |
||
| 345 | { |
||
| 346 | "cell_type": "code", |
||
| 347 | "execution_count": 220, |
||
| 348 | "metadata": {}, |
||
| 349 | "outputs": [ |
||
| 350 | { |
||
| 351 | "name": "stdout", |
||
| 352 | "output_type": "stream", |
||
| 353 | "text": [ |
||
| 354 | "0.0 - 0.9065614372518576\n", |
||
| 355 | "0.05 - 0.14814359689532586\n", |
||
| 356 | "0.1 - 0.13409773457672813\n", |
||
| 357 | "0.15 - 0.1278775639714016\n", |
||
| 358 | "0.2 - 0.12535605723218368\n", |
||
| 359 | "0.25 - 0.12583704184158218\n", |
||
| 360 | "0.3 - 0.12729425517299553\n", |
||
| 361 | "0.35 - 0.12959742000942132\n", |
||
| 362 | "0.4 - 0.1326181465043882\n", |
||
| 363 | "0.45 - 0.13660837921286184\n", |
||
| 364 | "0.5 - 0.14120474323651855\n", |
||
| 365 | "0.55 - 0.14619835062322617\n", |
||
| 366 | "0.6 - 0.1525275180080523\n", |
||
| 367 | "0.65 - 0.15985079129981627\n", |
||
| 368 | "0.7 - 0.16676434855339228\n", |
||
| 369 | "0.75 - 0.1763829533391864\n", |
||
| 370 | "0.8 - 0.18880411182394718\n", |
||
| 371 | "0.85 - 0.20404091332511465\n", |
||
| 372 | "0.9 - 0.2253708992666924\n", |
||
| 373 | "0.95 - 0.2582048951764738\n", |
||
| 374 | "1.0 - 0.9999968056833283\n" |
||
| 375 | ] |
||
| 376 | } |
||
| 377 | ], |
||
| 378 | "source": [ |
||
| 379 | "for i in range(0,21):\n", |
||
| 380 | " threshold = i * 5 / 100\n", |
||
| 381 | " print('{} - {}'.format(threshold, vod(truth.get_data(), gaussian_filter(pred.get_data(), 0.33) > threshold)))" |
||
| 382 | ] |
||
| 383 | }, |
||
| 384 | { |
||
| 385 | "cell_type": "code", |
||
| 386 | "execution_count": 112, |
||
| 387 | "metadata": {}, |
||
| 388 | "outputs": [ |
||
| 389 | { |
||
| 390 | "name": "stdout", |
||
| 391 | "output_type": "stream", |
||
| 392 | "text": [ |
||
| 393 | "0 - 0.8936488796427577\n" |
||
| 394 | ] |
||
| 395 | } |
||
| 396 | ], |
||
| 397 | "source": [ |
||
| 398 | "for i in range(0,1):\n", |
||
| 399 | " print('{} - {}'.format(i, vod(truth.get_data(), sobel(pred.get_data()) > 0.4)))" |
||
| 400 | ] |
||
| 401 | }, |
||
| 402 | { |
||
| 403 | "cell_type": "code", |
||
| 404 | "execution_count": 37, |
||
| 405 | "metadata": {}, |
||
| 406 | "outputs": [ |
||
| 407 | { |
||
| 408 | "data": { |
||
| 409 | "text/plain": [ |
||
| 410 | "0.5230235351692842" |
||
| 411 | ] |
||
| 412 | }, |
||
| 413 | "execution_count": 37, |
||
| 414 | "metadata": {}, |
||
| 415 | "output_type": "execute_result" |
||
| 416 | } |
||
| 417 | ], |
||
| 418 | "source": [ |
||
| 419 | "from scipy.ndimage.morphology import binary_fill_holes\n", |
||
| 420 | "vod(truth.get_data(), binary_fill_holes(gaussian_filter(pred.get_data(), 1) > 0.5))" |
||
| 421 | ] |
||
| 422 | }, |
||
| 423 | { |
||
| 424 | "cell_type": "code", |
||
| 425 | "execution_count": 10, |
||
| 426 | "metadata": {}, |
||
| 427 | "outputs": [ |
||
| 428 | { |
||
| 429 | "name": "stdout", |
||
| 430 | "output_type": "stream", |
||
| 431 | "text": [ |
||
| 432 | "intersection\t 175895\n", |
||
| 433 | "union\t\t 196316\n" |
||
| 434 | ] |
||
| 435 | }, |
||
| 436 | { |
||
| 437 | "data": { |
||
| 438 | "text/plain": [ |
||
| 439 | "0.10402053821115853" |
||
| 440 | ] |
||
| 441 | }, |
||
| 442 | "execution_count": 10, |
||
| 443 | "metadata": {}, |
||
| 444 | "output_type": "execute_result" |
||
| 445 | } |
||
| 446 | ], |
||
| 447 | "source": [ |
||
| 448 | "vod(truth.get_data(), postprocess_prediction(pred.get_data(), gaussian_std=1, threshold=0.5, connected_component=True), verbose=True)" |
||
| 449 | ] |
||
| 450 | }, |
||
| 451 | { |
||
| 452 | "cell_type": "code", |
||
| 453 | "execution_count": 14, |
||
| 454 | "metadata": {}, |
||
| 455 | "outputs": [ |
||
| 456 | { |
||
| 457 | "data": { |
||
| 458 | "text/plain": [ |
||
| 459 | "(array([3125052, 11203, 7935, 8868, 112831, 40350, 2922,\n", |
||
| 460 | " 2352, 2914, 588549]),\n", |
||
| 461 | " array([0.11920303, 0.19536243, 0.27152183, 0.34768123, 0.42384063,\n", |
||
| 462 | " 0.50000003, 0.57615943, 0.65231883, 0.72847823, 0.80463763,\n", |
||
| 463 | " 0.88079703]))" |
||
| 464 | ] |
||
| 465 | }, |
||
| 466 | "execution_count": 14, |
||
| 467 | "metadata": {}, |
||
| 468 | "output_type": "execute_result" |
||
| 469 | } |
||
| 470 | ], |
||
| 471 | "source": [ |
||
| 472 | "np.histogram(pred.get_data())" |
||
| 473 | ] |
||
| 474 | }, |
||
| 475 | { |
||
| 476 | "cell_type": "code", |
||
| 477 | "execution_count": 178, |
||
| 478 | "metadata": {}, |
||
| 479 | "outputs": [ |
||
| 480 | { |
||
| 481 | "name": "stderr", |
||
| 482 | "output_type": "stream", |
||
| 483 | "text": [ |
||
| 484 | "/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/nibabel/viewers.py:416: FutureWarning: Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.\n", |
||
| 485 | " vdata = self._data[idx].ravel()\n" |
||
| 486 | ] |
||
| 487 | }, |
||
| 488 | { |
||
| 489 | "data": { |
||
| 490 | "text/plain": [ |
||
| 491 | "<OrthoSlicer3D: (256, 256, 108, 2)>" |
||
| 492 | ] |
||
| 493 | }, |
||
| 494 | "execution_count": 178, |
||
| 495 | "metadata": {}, |
||
| 496 | "output_type": "execute_result" |
||
| 497 | }, |
||
| 498 | { |
||
| 499 | "name": "stderr", |
||
| 500 | "output_type": "stream", |
||
| 501 | "text": [ |
||
| 502 | "Traceback (most recent call last):\n", |
||
| 503 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 388, in process\n", |
||
| 504 | " proxy(*args, **kwargs)\n", |
||
| 505 | " File \"/home/galdude33/anaconda3/envs/keras/lib/python3.6/site-packages/matplotlib/cbook/__init__.py\", line 228, in __call__\n", |
||
| 506 | " return mtd(*args, **kwargs)\n", |
||
| 507 | "TypeError: _cleanup() takes 1 positional argument but 2 were given\n" |
||
| 508 | ] |
||
| 509 | } |
||
| 510 | ], |
||
| 511 | "source": [ |
||
| 512 | "rep1 = (vol.get_data())\n", |
||
| 513 | "rep2 = postprocess_prediction(pred.get_data(), fill_holes=True, gaussian_std=0.5, threshold=0.5)\n", |
||
| 514 | "rep3 = (truth.get_data())\n", |
||
| 515 | "rep = np.concatenate([np.expand_dims(rep1+3*rep2, -1), np.expand_dims(rep1+3*rep3, -1)], axis=-1)\n", |
||
| 516 | "new_img_like(vol, data=rep).orthoview()" |
||
| 517 | ] |
||
| 518 | }, |
||
| 519 | { |
||
| 520 | "cell_type": "code", |
||
| 521 | "execution_count": null, |
||
| 522 | "metadata": {}, |
||
| 523 | "outputs": [], |
||
| 524 | "source": [] |
||
| 525 | } |
||
| 526 | ], |
||
| 527 | "metadata": { |
||
| 528 | "kernelspec": { |
||
| 529 | "display_name": "Python 3", |
||
| 530 | "language": "python", |
||
| 531 | "name": "python3" |
||
| 532 | }, |
||
| 533 | "language_info": { |
||
| 534 | "codemirror_mode": { |
||
| 535 | "name": "ipython", |
||
| 536 | "version": 3 |
||
| 537 | }, |
||
| 538 | "file_extension": ".py", |
||
| 539 | "mimetype": "text/x-python", |
||
| 540 | "name": "python", |
||
| 541 | "nbconvert_exporter": "python", |
||
| 542 | "pygments_lexer": "ipython3", |
||
| 543 | "version": "3.6.6" |
||
| 544 | } |
||
| 545 | }, |
||
| 546 | "nbformat": 4, |
||
| 547 | "nbformat_minor": 1 |
||
| 548 | } |