def preprocessImagesFromImagenet(imagenet_ids_to_test,
synset_words,
val_gt_file,
path_to_images_imagenet='',
all_files_info=None,
start_idx=1):
# class_ids=[];
ids, labels = zip(*imagenet.readLabelsFile(synset_words))
list_of_idx = [ids.index(id_curr) for id_curr in imagenet_ids_to_test]
test_set = imagenet.selectTestSetByID(val_gt_file,
list_of_idx,
path_to_val=path_to_images_imagenet)
if all_files_info is None:
all_files_info = []
for img_path, imagenet_idx in test_set:
dict_curr = {}
dict_curr['img_path'] = img_path
id_curr = ids[imagenet_idx]
dict_curr['class_idx'] = imagenet_ids_to_test.index(
id_curr) + start_idx
dict_curr['class_id'] = id_curr
dict_curr['azimuth'] = None
all_files_info.append(dict_curr)
return all_files_info
def preprocessImagesFromImagenet(imagenet_ids_to_test,synset_words,val_gt_file,path_to_images_imagenet='',all_files_info=None,start_idx=1):
# class_ids=[];
ids,labels=zip(*imagenet.readLabelsFile(synset_words));
list_of_idx=[ids.index(id_curr) for id_curr in imagenet_ids_to_test];
test_set=imagenet.selectTestSetByID(val_gt_file,list_of_idx,path_to_val=path_to_images_imagenet)
if all_files_info is None:
all_files_info=[];
for img_path,imagenet_idx in test_set:
dict_curr={}
dict_curr['img_path']=img_path;
id_curr=ids[imagenet_idx];
dict_curr['class_idx']=imagenet_ids_to_test.index(id_curr)+start_idx;
dict_curr['class_id']=id_curr;
dict_curr['azimuth']=None;
all_files_info.append(dict_curr);
return all_files_info
def script_runNNOnPascalIncludedInTraining():
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'
list_of_ids = imagenet.getImagenetIdToTrainingIdMapping(
mapping_file, list_of_ids_im)
print len(list_of_ids)
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/trained'
layers = ['pool5', 'fc6', 'fc7']
gpu_no = 0
path_to_classify = '..'
numberOfN = 5
relativePaths = ['/disk2', '../../../..']
# out_file=script_nearestNeigbourExperiment.runClassificationTestSet(test_set,out_dir,path_to_classify,gpu_no,layers)
file_name = '/disk2/octoberExperiments/nn_performance_without_pascal/trained/20151023153522'
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:
# file_name_l=file_name+'_'+layer;
# indices,conf_matrix=doNN(img_paths,gt_labels,vals[layer],numberOfN=numberOfN,distance='cosine',algo='brute')
# 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
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
def script_temp():
path_to_val = "/disk2/imagenet/val"
ext = "JPEG"
out_dir = "/disk2/novemberExperiments/nn_imagenet_try"
if not os.path.exists(out_dir):
os.mkdir(out_dir)
in_file_pre = "list_of_ims_for_nn"
in_file_pre = os.path.join(out_dir, in_file_pre)
path_to_classify = ".."
trainFlag = False
# caffe_model='/home/maheenrashid/Downloads/caffe/caffe-rc2/models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel';
caffe_model = "/disk2/octoberExperiments/nn_performance_without_pascal/snapshot_iter_450000.caffemodel"
caffe_deploy = "/disk2/octoberExperiments/nn_performance_without_pascal/deploy.prototxt"
caffe_mean = "/disk2/octoberExperiments/nn_performance_without_pascal/mean.npy"
gpu_no = 0
layers = ["pool5", "fc6", "fc7"]
out_file = "nn_non_trained"
out_file = os.path.join(out_dir, out_file)
db_path_out = "sqlite://///disk2/novemberExperiments/nn_imagenet/nn_imagenet.db"
synset_words = "../../data/ilsvrc12/synset_words.txt"
val_gt_file = "../../data/ilsvrc12/val.txt"
idx_chosen = pickle.load(open("/disk2/novemberExperiments/nn_imagenet/equal_mix_ids.p", "rb"))
im_files_gt_classes = imagenet.selectTestSetByID(val_gt_file, idx_chosen, path_to_val=path_to_val)
im_files = list(zip(*im_files_gt_classes)[0])
gt_classes = list(zip(*im_files_gt_classes)[1])
print len(im_files)
print len(gt_classes)
print len(set(gt_classes))
per_file = len(im_files)
# in_files,_=writeInputImageFiles(im_files,in_file_pre,per_file);
in_files = [in_file_pre + "_" + str(0) + ".txt"]
print in_files
out_files = []
for idx, in_file_curr in enumerate(in_files):
out_file_curr = out_file + "_" + str(idx)
out_files.append(
caffe_wrapper.saveFeaturesOfLayers(
in_file_curr,
path_to_classify,
gpu_no,
layers,
ext=ext,
out_file=out_file_curr,
meanFile=caffe_mean,
deployFile=caffe_deploy,
modelFile=caffe_model,
)
)
print in_files
print out_files
file_list_all = []
for in_file_curr in in_files:
with open(in_file_curr, "rb") as f:
file_list = f.readlines()
file_list_all.extend([file_curr.strip("\n") for file_curr in file_list])
print len(file_list_all)
imagenet_idx_mapped, imagenet_ids_mapped, imagenet_labels_mapped = imagenet.getMappingInfo(
file_list_all, synset_words, val_gt_file
)
print "about to combine"
t = time.time()
val_combined = combineDeepFeaturesFromFiles(out_files, layers)
print time.time() - t
for layer_curr in layers:
print "about to nn for ", layer_curr
t = time.time()
indices, distances = nearest_neighbor.doCosineDistanceNN(val_combined[layer_curr], numberOfN=None)
print time.time() - t
# break;
# return
print indices.shape
print distances.shape
print "writing to db"
mani = Imagenet_Manipulator(db_path_out)
mani.openSession()
for idx in range(len(file_list_all)):
if idx % 100 == 0:
print layer_curr, idx, len(file_list_all)
idx_out_file = idx / per_file
out_file_layers = out_file + "_" + str(idx_out_file) + ".npz"
mani.insert(
idx,
file_list_all[idx],
layer_curr,
out_file_layers,
trainFlag,
imagenet_idx_mapped[idx],
imagenet_ids_mapped[idx],
caffe_model,
class_label_imagenet=imagenet_labels_mapped[idx],
neighbor_index=indices[idx],
neighbor_distance=distances[idx],
)
mani.closeSession()
