def main(): parser = argparse.ArgumentParser(description='Execute different functions of our system') parser.add_argument('mode', choices=[ 'window_stats', 'evaluate_metaparams', 'evaluate_jw', 'evaluate_get_pos_windows', 'train_svm', 'extract_sift','extract_assignments','extract_codebook', 'evaluate_jw_grid', 'final_metaparams', 'assemble_dpm_dets','ctfdet','assemble_ctf_dets' ]) parser.add_argument('--test_dataset', choices=['val','test','train'], default='test', help='dataset to use for testing. the training dataset \ is automatically inferred (val->train and test->trainval).') parser.add_argument('--first_n', type=int, help='only take the first N images in the datasets') parser.add_argument('--bounds', type=str, help='the start_time and deadline_time for the ImagePolicy and corresponding evaluation. ex: (1,5)') parser.add_argument('--name', help='name for this run') parser.add_argument('--priors', default='random', help= \ "list of choice for the policy for selecting the next action. choose from random, oracle,fixed_order, no_smooth, backoff. ex: --priors=random,oracle,no_smooth") parser.add_argument('--compare_evals', action='store_true', default=False, help='plot all the priors modes given on same plot'), parser.add_argument('--detector', choices=['perfect','perfect_with_noise', 'dpm','ctf'], default='perfect', help='detector type') parser.add_argument('--force', action='store_true', default=False, help='force overwrite') parser.add_argument('--gist', action='store_true', default=False, help='use GIST as one of the actions') parser.add_argument('--clear_tmp', action='store_true', default=False, help='clear the cached windows folder before running'), parser.add_argument('--feature_type', choices=['sift','dsift'], default='dsift', help='use this feature type'), parser.add_argument('--kernel', choices=['chi2','rbf'], default='chi2', help='kernel to train svm on'), args = parser.parse_args() if args.priors: args.priors = args.priors.split(',') if args.bounds: args.bounds = [float(x) for x in re.findall(r'\d+', args.bounds)] assert(len(args.bounds)==2) print(args) # Load the dataset dataset = Dataset('full_pascal_'+args.test_dataset) if args.first_n: dataset.images = dataset.images[:args.first_n] # Infer train_dataset if args.test_dataset=='test': train_dataset = Dataset('full_pascal_trainval') elif args.test_dataset=='val': train_dataset = Dataset('full_pascal_train') else: print("Impossible, setting train_dataset to dataset") train_dataset = dataset # Create window generator sw = SlidingWindows(dataset,train_dataset) if args.clear_tmp: dirname = config.get_sliding_windows_cached_dir(train_dataset.get_name()) shutil.rmtree(dirname) dirname = config.get_sliding_windows_cached_dir(dataset.get_name()) shutil.rmtree(dirname) if args.mode=='assemble_dpm_dets': policy = DatasetPolicy(dataset,train_dataset,sw) dets = policy.load_ext_detections(dataset,suffix='dpm_may25') if args.mode=='assemble_ctf_dets': policy = DatasetPolicy(dataset,train_dataset,sw) dets = policy.load_ext_detections(dataset,'ctf','ctf_default') dets = policy.load_ext_detections(dataset,'ctf','ctf_nohal') dets = policy.load_ext_detections(dataset,'ctf', 'ctf_halfsize') if args.mode=='evaluate_get_pos_windows': evaluate_get_pos_windows(train_dataset) return if args.mode=='window_stats': "Compute and plot the statistics of ground truth window parameters." results = SlidingWindows.get_dataset_window_stats(train_dataset,plot=True) if args.mode=='ctfdet': """Run Pedersoli's detector on the dataset and assemble into one Table.""" run_pedersoli(dataset) if args.mode=='evaluate_jw': """ Evaluate the jumping window approach by producing plots of recall vs. #windows. """ # TODO hack: both sw and jw should subclass something like WindowGenerator jw = JumpingWindowsDetector(use_scale=True) sw.jw = jw #classes = dataset.classes classes = ['car'] # classes = ['bicycle' ,'car','horse', 'sofa',\ # 'bird', 'chair', 'motorbike', 'train',\ # 'boat', 'cow', 'person', 'tvmonitor',\ # 'bottle','diningtable', 'pottedplant',\ # 'bus','dog' ,'sheep'] for cls_idx in range(comm_rank, len(classes), comm_size): #for cls in dataset.classes: cls = classes[cls_idx] dirname = config.get_jumping_windows_dir(dataset.get_name()) filename = os.path.join(dirname,'%s'%cls) sw.evaluate_recall(cls, filename, metaparams=None, mode='jw', plot=True) if args.mode=='evaluate_jw_grid': """ Evaluate the jumping window approach by producing plots of recall vs. #windows. """ sw = SlidingWindows(dataset,train_dataset) jw = JumpingWindowsDetectorGrid() sw.jw = jw for cls in dataset.classes: dirname = config.get_jumping_windows_dir(dataset.get_name()) filename = os.path.join(dirname,'%s'%cls) if os.path.isfile(config.data_dir + 'JumpingWindows/'+cls): sw.evaluate_recall(cls, filename, metaparams=None, mode='jw', plot=True) if args.mode=='train_svm': randomize = not os.path.exists('/home/tobibaum') d = Dataset('full_pascal_train') dtest = Dataset('full_pascal_val') e = Extractor() classes = config.pascal_classes num_words = 3000 iters = 5 feature_type = 'dsift' codebook_samples = 15 num_pos = 'max' testsize = 'max' if args.first_n: num_pos = args.first_n testsize = 1.5*num_pos kernel = args.kernel if comm_rank == 0: ut.makedirs(config.data_dir + 'features/' + feature_type + '/times/') ut.makedirs(config.data_dir + 'features/' + feature_type + '/codebooks/times/') ut.makedirs(config.data_dir + 'features/' + feature_type + '/svms/train_times/') for cls_idx in range(comm_rank, len(classes), comm_size): #for cls in classes: cls = classes[cls_idx] codebook = e.get_codebook(d, feature_type) pos_arr = d.get_pos_windows(cls) neg_arr = d.get_neg_windows(pos_arr.shape[0], cls, max_overlap=0) if not num_pos == 'max': if not randomize: pos_arr = pos_arr[:num_pos] neg_arr = pos_arr[:num_pos] else: rand = np.random.random_integers(0, pos_arr.shape[0] - 1, size=num_pos) pos_arr = pos_arr[rand] rand = np.random.random_integers(0, neg_arr.shape[0] - 1, size=num_pos) neg_arr = neg_arr[rand] pos_table = Table(pos_arr, ['x','y','w','h','img_ind']) neg_table = Table(neg_arr, pos_table.cols) train_with_hard_negatives(d, dtest, num_words,codebook_samples,codebook,\ cls, pos_table, neg_table,feature_type, \ iterations=iters, kernel=kernel, L=2, \ testsize=testsize,randomize=randomize) if args.mode=='evaluate_metaparams': """ Grid search over metaparams values for get_windows_new, with the AUC of recall vs. # windows evaluation. """ sw.grid_search_over_metaparams() return if args.mode=='final_metaparams': dirname = config.get_sliding_windows_metaparams_dir(train_dataset.get_name()) # currently these are the best auc/complexity params best_params_for_classes = [ (62,15,12,'importance',0), #aeroplane (83,15,12,'importance',0), #bicycle (62,15,12,'importance',0), #bird (62,15,12,'importance',0), #boat (125,12,12,'importance',0), #bottle (83,12,9,'importance',0), #bus (125,15,9,'importance',0), #car (125,12,12,'linear',0), #cat (125,15,9,'importance',0), #chair (125,9,6,'importance',0), #cow (125,15,6,'linear',0), #diningtable (62,15,12,'importance',0), #dog (83,15,6,'importance',0), #horse (83,12,6,'importance',0), #motorbike (83,15,12,'importance',0), #person (83,15,6,'importance',0), #pottedplant (83,15,12,'importance',0), #sheep (83,9,6,'importance',0), #sofa (62,12,6,'importance',0), #train (62,12,12,'importance',0), #tvmonitor (125,9,12,'importance',0) #all ] # ACTUALLY THEY ARE ALL THE SAME! cheap_params = (62, 9, 6, 'importance', 0) for i in range(comm_rank,dataset.num_classes(),comm_size): cls = dataset.classes[i] best_params = best_params_for_classes[i] #samples,num_scales,num_ratios,mode,priority,cls = cheap_params metaparams = { 'samples_per_500px': samples, 'num_scales': num_scales, 'num_ratios': num_ratios, 'mode': mode, 'priority': 0 } filename = '%s_%d_%d_%d_%s_%d'%( cls, metaparams['samples_per_500px'], metaparams['num_scales'], metaparams['num_ratios'], metaparams['mode'], metaparams['priority']) filename = os.path.join(dirname,filename) tables = sw.evaluate_recall(cls,filename,metaparams,'sw',plot=True,force=False) metaparams = { 'samples_per_500px': samples, 'num_scales': num_scales, 'num_ratios': num_ratios, 'mode': mode, 'priority': 1 } filename = '%s_%d_%d_%d_%s_%d'%( cls, metaparams['samples_per_500px'], metaparams['num_scales'], metaparams['num_ratios'], metaparams['mode'], metaparams['priority']) filename = os.path.join(dirname,filename) tables = sw.evaluate_recall(cls,filename,metaparams,'sw',plot=True,force=False) return if args.mode=='extract_sift': e=Extractor() e.extract_all(['sift'], ['full_pascal_trainval','full_pascal_test'], 0, 0) if args.mode=='extract_assignments': e=Extractor() feature_type = 'sift' for image_set in ['full_pascal_trainval','full_pascal_test']: d = Dataset(image_set) codebook = e.get_codebook(d, feature_type) print 'codebook loaded' for img_ind in range(comm_rank,len(d.images),comm_size): img = d.images[img_ind] #for img in d.images: e.get_assignments(np.array([0,0,img.size[0],img.size[1]]), feature_type, \ codebook, img) if args.mode=='extract_codebook': d = Dataset('full_pascal_trainval') e = Extractor() codebook = e.get_codebook(d, args.feature_type)
def get_windows_new(self, image, cls, metaparams=None, with_time=False, at_most=200000, force=False): """ Generate windows by using ground truth window stats and metaparams. metaparams must contain keys 'samples_per_500px', 'num_scales', 'num_ratios', 'mode' metaparams['mode'] can be 'linear' or 'importance' and refers to the method of sampling intervals per window parameter. If with_time=True, return tuple of (windows, time_elapsed). """ if not metaparams: metaparams = { 'samples_per_500px': 83, 'num_scales': 12, 'num_ratios': 6, 'mode': 'importance', 'priority': 0 } t = time.time() x_samples = int(image.width / 500. * metaparams['samples_per_500px']) y_samples = int(image.height / 500. * metaparams['samples_per_500px']) # check for cached windows and return if found dirname = config.get_sliding_windows_cached_dir(self.train_name) filename = '%s_%d_%d_%s_%s_%d_%d_%d.npy' % ( cls, metaparams['samples_per_500px'], metaparams['num_scales'], metaparams['num_ratios'], metaparams['mode'], metaparams['priority'], x_samples, y_samples) filename = os.path.join(dirname, filename) if os.path.exists(filename) and not force: windows = np.load(filename) else: # fine, we'll figure out the windows again # load the kde for x_scaled,y_scaled,scale,log_ratio stats = self.get_stats() kde = stats['%s_kde' % cls] x_frac = kde.dataset[0, :] y_frac = kde.dataset[1, :] scale = kde.dataset[2, :] log_ratio = kde.dataset[3, :] # given the metaparameters, sample points to generate the complete list of # parameter combinations if metaparams['mode'] == 'linear': x_points = np.linspace(x_frac.min(), x_frac.max(), x_samples) y_points = np.linspace(y_frac.min(), y_frac.max(), y_samples) scale_points = np.linspace(scale.min(), scale.max(), metaparams['num_scales']) ratio_points = np.linspace(log_ratio.min(), log_ratio.max(), metaparams['num_ratios']) elif metaparams['mode'] == 'importance': x_points = ut.importance_sample( x_frac, x_samples, stats['%s_%s_kde' % (cls, 'x_frac')]) y_points = ut.importance_sample( y_frac, y_samples, stats['%s_%s_kde' % (cls, 'y_frac')]) scale_points = ut.importance_sample( scale, metaparams['num_scales'], stats['%s_%s_kde' % (cls, 'scale')]) ratio_points = ut.importance_sample( log_ratio, metaparams['num_ratios'], stats['%s_%s_kde' % (cls, 'log_ratio')]) else: raise RuntimeError("Invalid mode") combinations = [ x for x in itertools.product(x_points, y_points, scale_points, ratio_points) ] combinations = np.array(combinations).T # only take the top-scoring detections if metaparams['priority']: t22 = time.time() scores = kde(combinations) # (so slow!) print("kde took %.3f s" % (time.time() - t22)) sorted_inds = np.argsort(-scores) max_num = min(at_most, sorted_inds.size) combinations = combinations[:, sorted_inds[:max_num]] # convert to x,y,scale,ratio,w,h scale = combinations[2, :] # x = x_frac*img_width x = combinations[0, :] * img_width # ratio = exp(log_ratio) ratio = np.exp(combinations[3, :]) # y = y_frac*img_height y = combinations[1, :] * img_height # w = scale*min_width w = scale * SlidingWindows.MIN_WIDTH # h = w*ratio h = w * ratio combinations[0, :] = x combinations[1, :] = y combinations[2, :] = w combinations[3, :] = h windows = combinations.T windows = BoundingBox.clipboxes_arr(windows, (0, 0, img_width, img_height)) np.save(filename, windows ) # does not take more than 0.5 sec even for 10**6 windows time_elapsed = time.time() - t print("get_windows_new() got %d windows in %.3fs" % (windows.shape[0], time_elapsed)) if with_time: return (windows, time_elapsed) else: return windows
def get_windows_new(self, image, cls, metaparams=None, with_time=False, at_most=200000, force=False): """ Generate windows by using ground truth window stats and metaparams. metaparams must contain keys 'samples_per_500px', 'num_scales', 'num_ratios', 'mode' metaparams['mode'] can be 'linear' or 'importance' and refers to the method of sampling intervals per window parameter. If with_time=True, return tuple of (windows, time_elapsed). """ if not metaparams: metaparams = { 'samples_per_500px': 83, 'num_scales': 12, 'num_ratios': 6, 'mode': 'importance', 'priority': 0} t = time.time() x_samples = int(image.width/500. * metaparams['samples_per_500px']) y_samples = int(image.height/500. * metaparams['samples_per_500px']) # check for cached windows and return if found dirname = config.get_sliding_windows_cached_dir(self.train_name) filename = '%s_%d_%d_%s_%s_%d_%d_%d.npy'%( cls, metaparams['samples_per_500px'], metaparams['num_scales'], metaparams['num_ratios'], metaparams['mode'], metaparams['priority'], x_samples, y_samples) filename = os.path.join(dirname,filename) if os.path.exists(filename) and not force: windows = np.load(filename) else: # fine, we'll figure out the windows again # load the kde for x_scaled,y_scaled,scale,log_ratio stats = self.get_stats() kde = stats['%s_kde'%cls] x_frac = kde.dataset[0,:] y_frac = kde.dataset[1,:] scale = kde.dataset[2,:] log_ratio = kde.dataset[3,:] # given the metaparameters, sample points to generate the complete list of # parameter combinations if metaparams['mode'] == 'linear': x_points = np.linspace(x_frac.min(),x_frac.max(),x_samples) y_points = np.linspace(y_frac.min(),y_frac.max(),y_samples) scale_points = np.linspace(scale.min(),scale.max(),metaparams['num_scales']) ratio_points = np.linspace(log_ratio.min(),log_ratio.max(),metaparams['num_ratios']) elif metaparams['mode'] == 'importance': x_points = ut.importance_sample(x_frac,x_samples,stats['%s_%s_kde'%(cls,'x_frac')]) y_points = ut.importance_sample(y_frac,y_samples,stats['%s_%s_kde'%(cls,'y_frac')]) scale_points = ut.importance_sample(scale,metaparams['num_scales'],stats['%s_%s_kde'%(cls,'scale')]) ratio_points = ut.importance_sample(log_ratio,metaparams['num_ratios'],stats['%s_%s_kde'%(cls,'log_ratio')]) else: raise RuntimeError("Invalid mode") combinations = [x for x in itertools.product(x_points,y_points,scale_points,ratio_points)] combinations = np.array(combinations).T # only take the top-scoring detections if metaparams['priority']: t22=time.time() scores = kde(combinations) # (so slow!) print("kde took %.3f s"%(time.time()-t22)) sorted_inds = np.argsort(-scores) max_num = min(at_most,sorted_inds.size) combinations = combinations[:,sorted_inds[:max_num]] # convert to x,y,scale,ratio,w,h scale = combinations[2,:] # x = x_frac*img_width x = combinations[0,:]*img_width # ratio = exp(log_ratio) ratio = np.exp(combinations[3,:]) # y = y_frac*img_height y = combinations[1,:]*img_height # w = scale*min_width w = scale*SlidingWindows.MIN_WIDTH # h = w*ratio h = w * ratio combinations[0,:] = x combinations[1,:] = y combinations[2,:] = w combinations[3,:] = h windows = combinations.T windows = BoundingBox.clipboxes_arr(windows,(0,0,img_width,img_height)) np.save(filename,windows) # does not take more than 0.5 sec even for 10**6 windows time_elapsed = time.time()-t print("get_windows_new() got %d windows in %.3fs"%(windows.shape[0],time_elapsed)) if with_time: return (windows,time_elapsed) else: return windows