In Masterarbeit:"Anomalie-Detektion in Zellbildern zur Anwendung der Leukämieerkennung" verwendete Methode des 3. Platzes der ISBI2019.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

run.ipynb 18KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679
  1. {
  2. "cells": [
  3. {
  4. "cell_type": "code",
  5. "execution_count": null,
  6. "id": "cd8aaf96",
  7. "metadata": {},
  8. "outputs": [],
  9. "source": [
  10. "!pip install pandas tqdm"
  11. ]
  12. },
  13. {
  14. "cell_type": "code",
  15. "execution_count": null,
  16. "id": "26bd5e25",
  17. "metadata": {
  18. "scrolled": true
  19. },
  20. "outputs": [],
  21. "source": [
  22. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results"
  23. ]
  24. },
  25. {
  26. "cell_type": "code",
  27. "execution_count": 55,
  28. "id": "b753e6b8",
  29. "metadata": {
  30. "scrolled": false
  31. },
  32. "outputs": [
  33. {
  34. "name": "stdout",
  35. "output_type": "stream",
  36. "text": [
  37. "Loading model\n",
  38. "Classifying\n",
  39. "59it [00:41, 1.43it/s] \n",
  40. "Positive: 1234\n",
  41. "Negative: 633\n",
  42. "AUC: 0.8797024225483345\n"
  43. ]
  44. }
  45. ],
  46. "source": [
  47. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/20220216T154306Z.AZHL\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32"
  48. ]
  49. },
  50. {
  51. "cell_type": "code",
  52. "execution_count": null,
  53. "id": "3246460b",
  54. "metadata": {},
  55. "outputs": [],
  56. "source": [
  57. "# TRAIN\n",
  58. "# dataset : CNMC\n",
  59. "# res : 32\n",
  60. "# epochs : 100\n",
  61. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 32"
  62. ]
  63. },
  64. {
  65. "cell_type": "code",
  66. "execution_count": null,
  67. "id": "8a953a39",
  68. "metadata": {},
  69. "outputs": [],
  70. "source": [
  71. "# TRAIN\n",
  72. "# dataset : CNMC\n",
  73. "# res : 128\n",
  74. "# epochs : 100\n",
  75. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 128"
  76. ]
  77. },
  78. {
  79. "cell_type": "code",
  80. "execution_count": null,
  81. "id": "12c15b33",
  82. "metadata": {},
  83. "outputs": [],
  84. "source": [
  85. "# TRAIN\n",
  86. "# dataset : CNMC\n",
  87. "# res : 224\n",
  88. "# epochs : 100\n",
  89. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 224"
  90. ]
  91. },
  92. {
  93. "cell_type": "code",
  94. "execution_count": null,
  95. "id": "08ba15b4",
  96. "metadata": {},
  97. "outputs": [],
  98. "source": [
  99. "# TRAIN\n",
  100. "# dataset : CNMC\n",
  101. "# res : 256\n",
  102. "# epochs : 100\n",
  103. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 256"
  104. ]
  105. },
  106. {
  107. "cell_type": "code",
  108. "execution_count": null,
  109. "id": "3cf25ec3",
  110. "metadata": {},
  111. "outputs": [],
  112. "source": [
  113. "# TRAIN\n",
  114. "# dataset : CNMC\n",
  115. "# res : 450\n",
  116. "# epochs : 100\n",
  117. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  118. ]
  119. },
  120. {
  121. "cell_type": "code",
  122. "execution_count": null,
  123. "id": "73b9d9d3",
  124. "metadata": {},
  125. "outputs": [],
  126. "source": [
  127. "# TRAIN\n",
  128. "# dataset : CNMC_Grayscale\n",
  129. "# res : 450\n",
  130. "# epochs : 100\n",
  131. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_grayscale\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  132. ]
  133. },
  134. {
  135. "cell_type": "code",
  136. "execution_count": null,
  137. "id": "ce16353c",
  138. "metadata": {},
  139. "outputs": [],
  140. "source": [
  141. "# TRAIN\n",
  142. "# dataset : CNMC_no_red\n",
  143. "# res : 450\n",
  144. "# epochs : 100\n",
  145. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_red\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  146. ]
  147. },
  148. {
  149. "cell_type": "code",
  150. "execution_count": null,
  151. "id": "959ab837",
  152. "metadata": {},
  153. "outputs": [],
  154. "source": [
  155. "# TRAIN\n",
  156. "# dataset : CNMC_no_green\n",
  157. "# res : 450\n",
  158. "# epochs : 100\n",
  159. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_green\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  160. ]
  161. },
  162. {
  163. "cell_type": "code",
  164. "execution_count": null,
  165. "id": "879beb46",
  166. "metadata": {},
  167. "outputs": [],
  168. "source": [
  169. "# TRAIN\n",
  170. "# dataset : CNMC_no_blue\n",
  171. "# res : 450\n",
  172. "# epochs : 100\n",
  173. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_blue\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  174. ]
  175. },
  176. {
  177. "cell_type": "code",
  178. "execution_count": null,
  179. "id": "6d545dce",
  180. "metadata": {},
  181. "outputs": [],
  182. "source": [
  183. "# TRAIN\n",
  184. "# dataset : CNMC_red_only\n",
  185. "# res : 450\n",
  186. "# epochs : 100\n",
  187. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_red_only\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  188. ]
  189. },
  190. {
  191. "cell_type": "code",
  192. "execution_count": null,
  193. "id": "25480226",
  194. "metadata": {},
  195. "outputs": [],
  196. "source": [
  197. "# TRAIN\n",
  198. "# dataset : CNMC_green_only\n",
  199. "# res : 450\n",
  200. "# epochs : 100\n",
  201. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_green_only\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  202. ]
  203. },
  204. {
  205. "cell_type": "code",
  206. "execution_count": null,
  207. "id": "a064d169",
  208. "metadata": {},
  209. "outputs": [],
  210. "source": [
  211. "# TRAIN\n",
  212. "# dataset : CNMC_blue_only\n",
  213. "# res : 450\n",
  214. "# epochs : 100\n",
  215. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_blue_only\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  216. ]
  217. },
  218. {
  219. "cell_type": "code",
  220. "execution_count": null,
  221. "id": "8d53828a",
  222. "metadata": {},
  223. "outputs": [],
  224. "source": [
  225. "# TRAIN\n",
  226. "# dataset : CNMC\n",
  227. "# res : 450\n",
  228. "# epochs : 100\n",
  229. "!python3 main_manual.py --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC\" --batch-size 32 --epochs 100 --seed 30042022 --device cuda --out results --res 450"
  230. ]
  231. },
  232. {
  233. "cell_type": "code",
  234. "execution_count": 183,
  235. "id": "ea9c2f23",
  236. "metadata": {},
  237. "outputs": [
  238. {
  239. "name": "stdout",
  240. "output_type": "stream",
  241. "text": [
  242. "PROPOSAL\n",
  243. "68.51\t83.57 ± 5.16\t89.61\n",
  244. "84.33\t89.06 ± 2.09\t92.95\n",
  245. "38.73\t73.26 ± 11.77\t84.72\n",
  246. "66.76\t83.35 ± 5.61\t89.57\n",
  247. "66.81\t83.36 ± 5.60\t89.55\n",
  248. "68.51\t83.57 ± 5.16\t89.61\n",
  249. "\n",
  250. "Figure(900x500)\n",
  251. "Figure(900x200)\n",
  252. "Figure(900x200)\n"
  253. ]
  254. }
  255. ],
  256. "source": [
  257. "# PLOT\n",
  258. "# dataset : CNMC\n",
  259. "# res : 450\n",
  260. "# epochs : 100\n",
  261. "!python3 plot.py"
  262. ]
  263. },
  264. {
  265. "cell_type": "markdown",
  266. "id": "8c92073d",
  267. "metadata": {},
  268. "source": [
  269. "# EVALUATION"
  270. ]
  271. },
  272. {
  273. "cell_type": "code",
  274. "execution_count": 135,
  275. "id": "b25a4267",
  276. "metadata": {
  277. "scrolled": false
  278. },
  279. "outputs": [
  280. {
  281. "name": "stdout",
  282. "output_type": "stream",
  283. "text": [
  284. "Loading model\n",
  285. "Classifying\n",
  286. "59it [00:05, 11.69it/s] \n",
  287. "Positive: 1425\n",
  288. "Negative: 442\n",
  289. "AUC: 0.6153299354864846\n"
  290. ]
  291. }
  292. ],
  293. "source": [
  294. "# EVALUATION \n",
  295. "# dataset : CNMC\n",
  296. "# res : 32\n",
  297. "# epochs : 100\n",
  298. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_32\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 32"
  299. ]
  300. },
  301. {
  302. "cell_type": "code",
  303. "execution_count": 136,
  304. "id": "b14e3e67",
  305. "metadata": {
  306. "scrolled": false
  307. },
  308. "outputs": [
  309. {
  310. "name": "stdout",
  311. "output_type": "stream",
  312. "text": [
  313. "Loading model\n",
  314. "Classifying\n",
  315. "59it [00:09, 6.24it/s] \n",
  316. "Positive: 1315\n",
  317. "Negative: 552\n",
  318. "AUC: 0.7711131113339208\n"
  319. ]
  320. }
  321. ],
  322. "source": [
  323. "# EVALUATION\n",
  324. "# dataset : CNMC\n",
  325. "# res : 128\n",
  326. "# epochs : 100\n",
  327. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_128\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 128"
  328. ]
  329. },
  330. {
  331. "cell_type": "code",
  332. "execution_count": 137,
  333. "id": "dfb25744",
  334. "metadata": {
  335. "scrolled": false
  336. },
  337. "outputs": [
  338. {
  339. "name": "stdout",
  340. "output_type": "stream",
  341. "text": [
  342. "Loading model\n",
  343. "Classifying\n",
  344. "59it [00:14, 4.19it/s] \n",
  345. "Positive: 1262\n",
  346. "Negative: 605\n",
  347. "AUC: 0.8143717274835677\n"
  348. ]
  349. }
  350. ],
  351. "source": [
  352. "# EVALUATION\n",
  353. "# dataset : CNMC\n",
  354. "# res : 224\n",
  355. "# epochs : 100\n",
  356. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_224\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 224"
  357. ]
  358. },
  359. {
  360. "cell_type": "code",
  361. "execution_count": 138,
  362. "id": "68600db4",
  363. "metadata": {
  364. "scrolled": false
  365. },
  366. "outputs": [
  367. {
  368. "name": "stdout",
  369. "output_type": "stream",
  370. "text": [
  371. "Loading model\n",
  372. "Classifying\n",
  373. "59it [00:41, 1.44it/s] \n",
  374. "Positive: 1195\n",
  375. "Negative: 672\n",
  376. "AUC: 0.8400701597139936\n"
  377. ]
  378. }
  379. ],
  380. "source": [
  381. "# EVALUATION\n",
  382. "# dataset : CNMC\n",
  383. "# res : 256\n",
  384. "# epochs : 100\n",
  385. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_256\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 256"
  386. ]
  387. },
  388. {
  389. "cell_type": "code",
  390. "execution_count": 139,
  391. "id": "71a5547e",
  392. "metadata": {
  393. "scrolled": false
  394. },
  395. "outputs": [
  396. {
  397. "name": "stdout",
  398. "output_type": "stream",
  399. "text": [
  400. "Loading model\n",
  401. "Classifying\n",
  402. "59it [00:41, 1.42it/s] \n",
  403. "Positive: 1241\n",
  404. "Negative: 626\n",
  405. "AUC: 0.8813918512441892\n"
  406. ]
  407. }
  408. ],
  409. "source": [
  410. "# EVALUATION\n",
  411. "# dataset : CNMC\n",
  412. "# res : 450\n",
  413. "# epochs : 100\n",
  414. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 450"
  415. ]
  416. },
  417. {
  418. "cell_type": "code",
  419. "execution_count": 154,
  420. "id": "58450362",
  421. "metadata": {
  422. "scrolled": false
  423. },
  424. "outputs": [
  425. {
  426. "name": "stdout",
  427. "output_type": "stream",
  428. "text": [
  429. "Loading model\n",
  430. "Classifying\n",
  431. "59it [00:41, 1.42it/s] \n",
  432. "Positive: 1261\n",
  433. "Negative: 606\n",
  434. "AUC: 0.8045073375262055\n"
  435. ]
  436. }
  437. ],
  438. "source": [
  439. "# EVALUATION\n",
  440. "# dataset : CNMC_Grayscale\n",
  441. "# res : 450\n",
  442. "# epochs : 100\n",
  443. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_grayscale\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_grayscale/phase2\" --batch-size 32 --res 450"
  444. ]
  445. },
  446. {
  447. "cell_type": "code",
  448. "execution_count": 155,
  449. "id": "48c40f18",
  450. "metadata": {
  451. "scrolled": false
  452. },
  453. "outputs": [
  454. {
  455. "name": "stdout",
  456. "output_type": "stream",
  457. "text": [
  458. "Loading model\n",
  459. "Classifying\n",
  460. "59it [00:44, 1.33it/s] \n",
  461. "Positive: 1178\n",
  462. "Negative: 689\n",
  463. "AUC: 0.8661869929814967\n"
  464. ]
  465. }
  466. ],
  467. "source": [
  468. "# EVALUATION\n",
  469. "# dataset : CNMC_no_red\n",
  470. "# res : 450\n",
  471. "# epochs : 100\n",
  472. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_no_red\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_red/phase2\" --batch-size 32 --res 450"
  473. ]
  474. },
  475. {
  476. "cell_type": "code",
  477. "execution_count": 156,
  478. "id": "b6ad9232",
  479. "metadata": {
  480. "scrolled": false
  481. },
  482. "outputs": [
  483. {
  484. "name": "stdout",
  485. "output_type": "stream",
  486. "text": [
  487. "Loading model\n",
  488. "Classifying\n",
  489. "59it [00:52, 1.12it/s] \n",
  490. "Positive: 1266\n",
  491. "Negative: 601\n",
  492. "AUC: 0.8018310900454735\n"
  493. ]
  494. }
  495. ],
  496. "source": [
  497. "# EVALUATION\n",
  498. "# dataset : CNMC_no_green\n",
  499. "# res : 450\n",
  500. "# epochs : 100\n",
  501. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_no_green\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_green/phase2\" --batch-size 32 --res 450"
  502. ]
  503. },
  504. {
  505. "cell_type": "code",
  506. "execution_count": 157,
  507. "id": "1ba76d51",
  508. "metadata": {
  509. "scrolled": false
  510. },
  511. "outputs": [
  512. {
  513. "name": "stdout",
  514. "output_type": "stream",
  515. "text": [
  516. "Loading model\n",
  517. "Classifying\n",
  518. "59it [00:48, 1.23it/s] \n",
  519. "Positive: 1248\n",
  520. "Negative: 619\n",
  521. "AUC: 0.8570821813062721\n"
  522. ]
  523. }
  524. ],
  525. "source": [
  526. "# EVALUATION\n",
  527. "# dataset : CNMC_no_blue\n",
  528. "# res : 450\n",
  529. "# epochs : 100\n",
  530. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_no_blue\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_no_blue/phase2\" --batch-size 32 --res 450"
  531. ]
  532. },
  533. {
  534. "cell_type": "code",
  535. "execution_count": 158,
  536. "id": "05cfaf9c",
  537. "metadata": {
  538. "scrolled": false
  539. },
  540. "outputs": [
  541. {
  542. "name": "stdout",
  543. "output_type": "stream",
  544. "text": [
  545. "Loading model\n",
  546. "Classifying\n",
  547. "59it [00:52, 1.12it/s] \n",
  548. "Positive: 1239\n",
  549. "Negative: 628\n",
  550. "AUC: 0.8013924335875389\n"
  551. ]
  552. }
  553. ],
  554. "source": [
  555. "# EVALUATION\n",
  556. "# dataset : CNMC_red_only\n",
  557. "# res : 450\n",
  558. "# epochs : 100\n",
  559. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_red_only\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_red_only/phase2\" --batch-size 32 --res 450"
  560. ]
  561. },
  562. {
  563. "cell_type": "code",
  564. "execution_count": 159,
  565. "id": "1ad09456",
  566. "metadata": {
  567. "scrolled": false
  568. },
  569. "outputs": [
  570. {
  571. "name": "stdout",
  572. "output_type": "stream",
  573. "text": [
  574. "Loading model\n",
  575. "Classifying\n",
  576. "59it [00:52, 1.13it/s] \n",
  577. "Positive: 1221\n",
  578. "Negative: 646\n",
  579. "AUC: 0.8590070792695896\n"
  580. ]
  581. }
  582. ],
  583. "source": [
  584. "# EVALUATION\n",
  585. "# dataset : CNMC_green_only\n",
  586. "# res : 450\n",
  587. "# epochs : 100\n",
  588. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_green_only\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_green_only/phase2\" --batch-size 32 --res 450"
  589. ]
  590. },
  591. {
  592. "cell_type": "code",
  593. "execution_count": 160,
  594. "id": "41e8d3a0",
  595. "metadata": {
  596. "scrolled": false
  597. },
  598. "outputs": [
  599. {
  600. "name": "stdout",
  601. "output_type": "stream",
  602. "text": [
  603. "Loading model\n",
  604. "Classifying\n",
  605. "59it [00:52, 1.12it/s] \n",
  606. "Positive: 1255\n",
  607. "Negative: 612\n",
  608. "AUC: 0.8268636253152251\n"
  609. ]
  610. }
  611. ],
  612. "source": [
  613. "# EVALUATION\n",
  614. "# dataset : CNMC_blue_only\n",
  615. "# res : 450\n",
  616. "# epochs : 100\n",
  617. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_blue_only\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC_blue_only/phase2\" --batch-size 32 --res 450"
  618. ]
  619. },
  620. {
  621. "cell_type": "code",
  622. "execution_count": 186,
  623. "id": "88bc18db",
  624. "metadata": {
  625. "scrolled": false
  626. },
  627. "outputs": [
  628. {
  629. "name": "stdout",
  630. "output_type": "stream",
  631. "text": [
  632. "Loading model\n",
  633. "Classifying\n",
  634. "59it [01:24, 1.43s/it] \n",
  635. "Positive: 1235\n",
  636. "Negative: 632\n",
  637. "AUC: 0.8588406050294211\n"
  638. ]
  639. }
  640. ],
  641. "source": [
  642. "# EVALUATION\n",
  643. "# dataset : CNMC-blackborder\n",
  644. "# res : 450\n",
  645. "# epochs : 100\n",
  646. "!python3 submission.py --modelroot \"/home/feoktistovar67431/isbi2019cancer-master/results/model_cnmc_res_450_w_blackborder\" --dataroot \"/home/feoktistovar67431/data/isbi2019/CNMC/phase2\" --batch-size 32 --res 450"
  647. ]
  648. },
  649. {
  650. "cell_type": "code",
  651. "execution_count": null,
  652. "id": "ec31125a",
  653. "metadata": {},
  654. "outputs": [],
  655. "source": []
  656. }
  657. ],
  658. "metadata": {
  659. "kernelspec": {
  660. "display_name": "Python 3",
  661. "language": "python",
  662. "name": "python3"
  663. },
  664. "language_info": {
  665. "codemirror_mode": {
  666. "name": "ipython",
  667. "version": 3
  668. },
  669. "file_extension": ".py",
  670. "mimetype": "text/x-python",
  671. "name": "python",
  672. "nbconvert_exporter": "python",
  673. "pygments_lexer": "ipython3",
  674. "version": "3.6.9"
  675. }
  676. },
  677. "nbformat": 4,
  678. "nbformat_minor": 5
  679. }