def train(self, task_id, training_set, testing_set=None, **kwargs):
print 'vm trainer called!'
# connect to database manager
self.db_manager = MongoDBManager(HogSvmTrainer.dbname, ip_addr='128.2.213.107')
self.storage_manager = StorageManager('test1')
local_tmp_dir = os.path.abspath(HogSvmTrainer.local_tmp_dir)
# download images to cache and get all bounding_boxes in memory:
obj_image_bounding_box = \
MyUtils.downloadImgWithBx(local_tmp_dir, self.db_manager, self.storage_manager, training_set)
# create output dir structure
output_dir_prefix = os.path.abspath('./classifier/hog_svm_')
# create an output folder for each task
if 'id' in kwargs:
output_dir = output_dir_prefix + 'id'
else:
timestamp = time.strftime("%m_%d_%y_%H_%M_%S")
output_dir = output_dir_prefix + timestamp
MyUtils.create_dir(output_dir)
# generate vm specific input files
# for each object, create a folder for train.txt, test.txt, and final classifier svm
obj_output_dirs = {}
for each_obj, obj_info in obj_image_bounding_box.iteritems():
train_obj_info, test_obj_info = self.split_train_file(obj_info, 10)
cur_obj_dir = output_dir + '/' + each_obj
obj_output_dirs[each_obj] = cur_obj_dir
MyUtils.create_dir(cur_obj_dir)
self.genInputFileForObj(each_obj, train_obj_info, cur_obj_dir+'/' + 'train_'+each_obj+'.xml')
self.genInputFileForObj(each_obj, test_obj_info, cur_obj_dir+'/' + 'test_'+each_obj+'.xml')
# split the training file randomly for generating testing file
for each_obj, each_obj_dir in obj_output_dirs.iteritems():
print 'calling dlib to train at folder {}'.format(each_obj_dir)
detector_name = each_obj + '.svm'
detector_path = each_obj_dir + '/' + detector_name
accuracy = self.train_with_dlib(each_obj_dir, detector_path, 'train_'+each_obj +'.xml', 'test_'+each_obj+'.xml')
# save the classifier into s3 and database
accuracy = "Testing accuracy: {}".format(accuracy)
MyUtils.zipdir(output_dir)
zip_file = output_dir + '.zip'
print 'uploading file to s3...'
key = self.storage_manager.uploadFile(zip_file)
print 'updating database...'
# TODO: maybe send this information to controller?
# add meta data info to database
classifier_metadata={'name': key,
'training_set':training_set,
'testing_set':testing_set,
'accuracy': 'see log',
'filepath': key}
self.db_manager.addClassifier(classifier_metadata)
return 'succesfully added ' + str(classifier_metadata)
def train(self, task_id, training_set, testing_set, **kwargs):
print 'caffe train called'
self.output_dir_prefix = os.path.abspath('./classifier/caffenet_')
# create an output folder for each task
if None != task_id:
self.output_dir = self.output_dir_prefix + str(task_id)
else:
timestamp = time.strftime("%m_%d_%y_%H_%M_%S")
self.output_dir = self.output_dir_prefix + timestamp
# TODO: changed to user input parameter?
max_iter = 500
if 'iteration' in kwargs:
max_iter = kwargs['iteration']
MyUtils.create_dir(self.output_dir)
# connect to database manager
self.db_manager = MongoDBManager(CaffeNetTrainer.dbname, ip_addr='128.2.213.107')
self.storage_manager = StorageManager('test1')
# make intermediate folder
self.ori_image_dir = CaffeNetTrainer.local_tmp_dir + '/' +'original'
self.crop_image_dir = CaffeNetTrainer.local_tmp_dir + '/' +'crop'
self.cache_manager = cacheManager(self.ori_image_dir)
MyUtils.create_dir(self.ori_image_dir)
MyUtils.create_dir(self.crop_image_dir)
# get image file list and bounding boxes
# get objects regardless of their videos, since same object in different video belongs to same identitfy
# summarize to get all objects
obj_set = {}
for obj, vid in training_set.iteritems():
if obj not in obj_set:
obj_set[obj] = []
obj_set[obj].extend(vid)
print obj_set
# for each object, get images
training_set_obj_file_path ={}
for obj, vids in obj_set.iteritems():
# 1. download image
# 2. crop image based on bounding boxes
obj_image_path = []
obj_bounding_boxes_with_image = {}
for vid in vids:
obj_bounding_boxes_each_vid = self.db_manager.getBoundingBoxWithImageByVidAndObj(vid, obj)
# TODO: probably can be a bit more efficient. right now is downloading vid repeatedly if it appears
# multiple times in train yaml
self.cache_manager.cacheImageFiles(vid, dir=False)
obj_bounding_boxes_with_image.update(obj_bounding_boxes_each_vid)
for image, bx_list in obj_bounding_boxes_with_image.iteritems():
# self.storage_manager.download(image, self.ori_image_dir)
idx =0
for bx in bx_list:
im = Image.open(self.ori_image_dir+'/'+image)
left_x = bx[0]
left_y = bx[1]
right_x = left_x + bx[2]
right_y = left_y + bx[3]
output_file_path = self.crop_image_dir + '/' +os.path.splitext(image)[0] + '_' + str(obj) + str(idx) \
+ os.path.splitext(image)[1]
im.crop((left_x,left_y, right_x, right_y)).save(output_file_path)
obj_image_path.append(output_file_path)
idx +=1
training_set_obj_file_path[obj] = obj_image_path
# generate training file
training_set_obj_file_path, testing_set_obj_file_path =self.split_train_file(training_set_obj_file_path, 10)
self.generate_caffe_train_file(training_set_obj_file_path, self.output_dir + '/train.txt')
self.generate_caffe_train_file(testing_set_obj_file_path, self.output_dir +'/test.txt')
# generate label file for corresponds label to object names
self.generate_caffe_label_file(training_set_obj_file_path, self.output_dir + '/label.txt')
# modify network prototxt
num_output_category = len(obj_set)
train_file_path = os.path.abspath(self.output_dir + '/train.txt')
test_file_path = os.path.abspath(self.output_dir + '/test.txt')
output_train_val_path = self.output_dir + '/' + 'train_val_custom.prototxt'
output_solver_path = self.output_dir + '/' + 'solver_custom.prototxt'
output_deploy_path = self.output_dir + '/' + 'deploy_custom.prototxt'
# fine-tuning output
self.custom_net_path = self.output_dir + '/train_val_custom.prototxt'
self.custom_snapshot_prefix= self.output_dir + '/caffenet_custom'
self.output_layer_name ="fc8_custom"
self.output_net_name="CaffeNetCustom"
# original model
self.original_output_layer_name ='fc8'
# reference design file locations
input_file_prefix = os.path.abspath('./bvlc_reference_caffenet')
train_file ='train_val.prototxt'
solver_file ='solver.prototxt'
deploy_file ='deploy.prototxt'
self.mod_caffe_net(input_file_prefix+'/' + train_file, num_output_category, train_file_path,
test_file_path, output_train_val_path)
self.mod_caffe_solver(input_file_prefix+ '/' +solver_file,
max_iter, output_solver_path)
self.mod_caffe_deploy(input_file_prefix + '/' + deploy_file,
num_output_category, output_deploy_path)
cmd ="/opt/caffe/build/tools/caffe train"
cmd += " -solver " + output_solver_path
cmd += " -weights ./bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel"
cmd += " | tee " + self.output_dir + '/' + 'log.txt'
print cmd
# issue train
os.system(cmd)
MyUtils.zipdir(self.output_dir)
zip_file = self.output_dir + '.zip'
print 'uploading file to s3...'
key = self.storage_manager.uploadFile(zip_file)
print 'updating database...'
# TODO: maybe send this information to controller?
# add meta data info to database
classifier_metadata={'name': key,
'training_set':training_set,
'testing_set':testing_set,
'accuracy': 'see log',
'filepath': key}
self.db_manager.addClassifier(classifier_metadata)
return
