def script_testingDoNN(): img_paths=[]; numberOfSamples=100; featureVectorLength=10; numberOfClasses=5; gt_labels=np.random.random_integers(0,numberOfClasses-1,(numberOfSamples,)); features_curr=np.random.random_integers(-100,100,(numberOfSamples,featureVectorLength)); features_curr=np.array(features_curr,dtype=float); numberOfN=5; indices=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,features_curr,numberOfN=numberOfN) print indices.shape==(numberOfSamples,numberOfN); numberOfN=None indices=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,features_curr,numberOfN=numberOfN) print indices.shape==(numberOfSamples,numberOfSamples); indices,conf_matrix=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,features_curr,numberOfN=numberOfN,conf_matrix_return=True) print conf_matrix.shape==(numberOfClasses,numberOfClasses) indices,distances=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,features_curr,numberOfN=numberOfN,conf_matrix_return=False,distances_return=True) print distances.shape==indices.shape==(numberOfSamples,numberOfSamples); indices,conf_matrix,distances=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,features_curr,numberOfN=numberOfN,conf_matrix_return=True,distances_return=True) print conf_matrix.shape==(numberOfClasses,numberOfClasses) print distances.shape==indices.shape==(numberOfSamples,numberOfSamples); plt.figure(); plt.plot(distances[0]); plt.plot(distances[numberOfSamples-1]); plt.savefig('/disk2/temp/checkNN.png'); plt.close();
def script_testingDoNN(): img_paths = [] numberOfSamples = 100 featureVectorLength = 10 numberOfClasses = 5 gt_labels = np.random.random_integers(0, numberOfClasses - 1, (numberOfSamples, )) features_curr = np.random.random_integers( -100, 100, (numberOfSamples, featureVectorLength)) features_curr = np.array(features_curr, dtype=float) numberOfN = 5 indices = script_nearestNeigbourExperiment.doNN(img_paths, gt_labels, features_curr, numberOfN=numberOfN) print indices.shape == (numberOfSamples, numberOfN) numberOfN = None indices = script_nearestNeigbourExperiment.doNN(img_paths, gt_labels, features_curr, numberOfN=numberOfN) print indices.shape == (numberOfSamples, numberOfSamples) indices, conf_matrix = script_nearestNeigbourExperiment.doNN( img_paths, gt_labels, features_curr, numberOfN=numberOfN, conf_matrix_return=True) print conf_matrix.shape == (numberOfClasses, numberOfClasses) indices, distances = script_nearestNeigbourExperiment.doNN( img_paths, gt_labels, features_curr, numberOfN=numberOfN, conf_matrix_return=False, distances_return=True) print distances.shape == indices.shape == (numberOfSamples, numberOfSamples) indices, conf_matrix, distances = script_nearestNeigbourExperiment.doNN( img_paths, gt_labels, features_curr, numberOfN=numberOfN, conf_matrix_return=True, distances_return=True) print conf_matrix.shape == (numberOfClasses, numberOfClasses) print distances.shape == indices.shape == (numberOfSamples, numberOfSamples) plt.figure() plt.plot(distances[0]) plt.plot(distances[numberOfSamples - 1]) plt.savefig('/disk2/temp/checkNN.png') plt.close()
def script_saveNNDistances(file_name, layers): test_set, _ = pickle.load(open(file_name + '.p', 'rb')) vals = np.load(file_name + '.npz') test_set = sorted(test_set, key=lambda x: x[0]) test_set = zip(*test_set) img_paths = list(test_set[0]) gt_labels = list(test_set[1]) numberOfN = None for layer in layers: file_name_l = file_name + '_' + layer + '_all_distances' indices, conf_matrix = script_nearestNeigbourExperiment.doNN( img_paths, gt_labels, vals[layer], numberOfN=numberOfN, distance='cosine', algo='brute', conf_matrix=False, distances=True) pickle.dump([img_paths, gt_labels, indices, conf_matrix], open(file_name_l + '.p', 'wb'))
def script_saveNNDistances(file_name,layers): test_set,_=pickle.load(open(file_name+'.p','rb')); vals=np.load(file_name+'.npz'); test_set=sorted(test_set,key=lambda x: x[0]) test_set=zip(*test_set); img_paths=list(test_set[0]); gt_labels=list(test_set[1]); numberOfN=None; for layer in layers: file_name_l=file_name+'_'+layer+'_all_distances'; indices,conf_matrix=script_nearestNeigbourExperiment.doNN(img_paths,gt_labels,vals[layer],numberOfN=numberOfN,distance='cosine',algo='brute',conf_matrix=False,distances=True) pickle.dump([img_paths,gt_labels,indices,conf_matrix],open(file_name_l+'.p','wb'));
def script_runNNOnPascalExcludedInTraining(): path_to_file = '../../data/ilsvrc12/synset_words.txt' val_ids = imagenet.readLabelsFile(path_to_file) val_just_ids = list(zip(*val_ids)[0]) val_just_labels = list(zip(*val_ids)[1]) pascal_ids_file = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt' pascal_ids = imagenet.readLabelsFile(pascal_ids_file) pascal_just_ids = list(zip(*pascal_ids)[0]) to_exclude = imagenet.removeClassesWithOverlap(val_just_ids, pascal_just_ids, keepMapping=True) val_gt_file = '../../data/ilsvrc12/val.txt' list_of_ids_im = [id for id_list in to_exclude for id in id_list] mapping_file = '../../data/ilsvrc12/synsets.txt' print len(list_of_ids_im) list_of_ids, _ = imagenet.getImagenetIdToTrainingIdMapping( mapping_file, list_of_ids_im) print len(list_of_ids) # print list_of_ids[0] list_of_ids_pascal = [] for id_no in range(len(to_exclude)): list_of_ids_pascal = list_of_ids_pascal + [id_no] * len( to_exclude[id_no]) path_to_val = '/disk2/imagenet/val' test_set = imagenet.selectTestSetByID(val_gt_file, list_of_ids, path_to_val) # out_dir='/disk2/octoberExperiments/nn_performance_without_pascal/notrained' out_dir = '/disk2/novemberExperiments/nn_imagenet_top5/trained' if not os.path.exists(out_dir): os.mkdir(out_dir) layers = ['pool5', 'fc6', 'fc7'] gpu_no = 1 path_to_classify = '..' numberOfN = 5 relativePaths = ['/disk2', '../../../..'] # deployFile='/disk2/octoberExperiments/nn_performance_without_pascal/deploy.prototxt' # meanFile='/disk2/octoberExperiments/nn_performance_without_pascal/mean.npy' # modelFile='/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel' modelFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel' deployFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/deploy.prototxt' meanFile = '/home/maheenrashid/Downloads/caffe/caffe-rc2/python/caffe/imagenet/ilsvrc_2012_mean.npy' # modelFile='/disk2/novemberExperiments/network_no_pascal/snapshots/snapshot_iter_450000.caffemodel'; # deployFile='/disk2/novemberExperiments/network_no_pascal/deploy.prototxt'; # meanFile='/disk2/novemberExperiments/network_no_pascal/mean.npy'; # out_file=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers,deployFile=deployFile,meanFile=meanFile,modelFile=modelFile) # return # file_name='/disk2/octoberExperiments/nn_performance_without_pascal/notrained/20151026132705' # file_name='/disk2/novemberExperiments/nn_imagenet_top5/notrained/20151130193757'; file_name = '/disk2/novemberExperiments/nn_imagenet_top5/trained/20151130230243' file_text_labels = '../../data/ilsvrc12/synset_words.txt' text_labels = np.loadtxt(file_text_labels, str, delimiter='\t') vals = np.load(file_name + '.npz') test_set = sorted(test_set, key=lambda x: x[0]) test_set = zip(*test_set) img_paths = list(test_set[0]) gt_labels = list(test_set[1]) gt_labels_pascal = [ list_of_ids_pascal[list_of_ids.index(gt_label)] for gt_label in gt_labels ] for layer in layers: print layer file_name_l = file_name + '_' + layer indices = script_nearestNeigbourExperiment.doNN(img_paths, gt_labels, vals[layer], numberOfN=numberOfN, distance='cosine', algo='brute') conf_matrix = 0 pickle.dump([img_paths, gt_labels, indices, conf_matrix], open(file_name_l + '.p', 'wb')) file_text_labels_pascal = '/disk2/octoberExperiments/nn_performance_without_pascal/pascal_classes.txt' text_labels_pascal = np.loadtxt(file_text_labels_pascal, str, delimiter='\t') for layer in layers: print layer file_name_l = file_name + '_' + layer [img_paths, gt_labels, indices, _] = pickle.load(open(file_name_l + '.p', 'rb')) img_paths_curr = [ x.replace(relativePaths[0], relativePaths[1]) for x in img_paths ] im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid( img_paths_curr, gt_labels, indices, text_labels) script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html', im_paths, captions) no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches( indices, gt_labels) print no_correct with open(file_name_l + '.txt', 'wb') as f: for no_correct_curr in no_correct: f.write(str(no_correct_curr) + ' ') file_name_l = file_name + '_' + layer + '_pascal' im_paths, captions = script_nearestNeigbourExperiment.createImageAndCaptionGrid( img_paths_curr, gt_labels_pascal, indices, text_labels_pascal) script_nearestNeigbourExperiment.writeHTML(file_name_l + '.html', im_paths, captions) no_correct, _ = script_nearestNeigbourExperiment.getNumberOfCorrectNNMatches( indices, gt_labels_pascal) with open(file_name_l + '.txt', 'wb') as f: for no_correct_curr in no_correct: f.write(str(no_correct_curr) + ' ') print no_correct