def get_set_up(model_name, route_iter, pre_pend, strs_append, split_num, model_num, train_pre = None, test_file = None, au = False):
# get_set_up(model_name, route_iter, pre_pend, strs_append, split_num, model_num, train_pre=train_pre, test_file = test_file ,au=True)
out_dir_meta = os.path.join('../experiments',model_name+str(route_iter))
out_dir_train = os.path.join(out_dir_meta,pre_pend+str(split_num)+strs_append)
# final_model_file = os.path.join(out_dir_train,'model_'+str(model_num)+'.pt')
if train_pre is None:
train_pre = os.path.join('../data/ck_96','train_test_files')
if test_file is None:
test_file = os.path.join(train_pre,'test_'+str(split_num)+'.txt')
else:
test_file = os.path.join(train_pre,test_file)
mean_file = os.path.join(train_pre,'train_'+str(split_num)+'_mean.png')
std_file = os.path.join(train_pre,'train_'+str(split_num)+'_std.png')
data_transforms = {}
data_transforms['val']= transforms.Compose([
transforms.ToTensor(),
lambda x: x*255.
])
if au:
test_data = dataset.Bp4d_Dataset_Mean_Std_Im(test_file, mean_file, std_file, resize= 96,transform = data_transforms['val'], binarize = True)
else:
test_data = dataset.CK_96_Dataset(test_file, mean_file, std_file, data_transforms['val'])
# if not au:
if au:
criterion = 'marginmulti'
else:
criterion = 'margin'
test_params = dict(out_dir_train = out_dir_train,
model_num = model_num,
train_data = None,
test_data = test_data,
gpu_id = 0,
model_name = model_name,
batch_size_val = 32,
criterion = criterion,
au=au
)
# num_iter = save_visualizations.save_routings(**test_params)
# print num_iter
# # else:
# # print 'HERE'
# # raw_input()
out_file_results = os.path.join(out_dir_train,'save_routings_single_batch_'+str(model_num))
print out_file_results
def get_class_variations(model_name, route_iter, pre_pend, strs_append, split_num, model_num, class_rel,type_exp,train_pre = None, test_file = None, au= False):
# out_dir_meta = os.path.join('../experiments',model_name+str(route_iter))
# out_dir_train = os.path.join(out_dir_meta,pre_pend+str(split_num)+strs_append)
# # final_model_file = os.path.join(out_dir_train,'model_'+str(model_num)+'.pt')
# train_pre = os.path.join('../data/ck_96','train_test_files')
# test_file = os.path.join(train_pre,'test_'+str(split_num)+'.txt')
# mean_file = os.path.join(train_pre,'train_'+str(split_num)+'_mean.png')
# std_file = os.path.join(train_pre,'train_'+str(split_num)+'_std.png')
# data_transforms = {}
# data_transforms['val']= transforms.Compose([
# transforms.ToTensor(),
# lambda x: x*255.
# ])
# test_data = dataset.CK_96_Dataset(test_file, mean_file, std_file, data_transforms['val'])
# test_params = dict(out_dir_train = out_dir_train,
# model_num = model_num,
# train_data = None,
# test_data = test_data,
# gpu_id = 0,
# model_name = model_name,
# batch_size_val = None,
# criterion = 'margin',
# class_rel = class_rel
# )
out_dir_meta = os.path.join('../experiments',model_name+str(route_iter))
out_dir_train = os.path.join(out_dir_meta,pre_pend+str(split_num)+strs_append)
# final_model_file = os.path.join(out_dir_train,'model_'+str(model_num)+'.pt')
if train_pre is None:
train_pre = os.path.join('../data/ck_96','train_test_files')
if test_file is None:
test_file = os.path.join(train_pre,'test_'+str(split_num)+'.txt')
else:
test_file = os.path.join(train_pre,test_file)
mean_file = os.path.join(train_pre,'train_'+str(split_num)+'_mean.png')
std_file = os.path.join(train_pre,'train_'+str(split_num)+'_std.png')
data_transforms = {}
data_transforms['val']= transforms.Compose([
transforms.ToTensor(),
lambda x: x*255.
])
if au:
test_data = dataset.Bp4d_Dataset_Mean_Std_Im(test_file, mean_file, std_file, resize= 96,transform = data_transforms['val'], binarize = True)
else:
test_data = dataset.CK_96_Dataset(test_file, mean_file, std_file, data_transforms['val'])
# if not au:
if au:
criterion = 'marginmulti'
else:
criterion = 'margin'
test_params = dict(out_dir_train = out_dir_train,
model_num = model_num,
train_data = None,
test_data = test_data,
gpu_id = 0,
model_name = model_name,
batch_size_val = 128,
criterion = criterion,
au=au,
class_rel = class_rel
)
if type_exp ==0 :
save_visualizations.save_class_as_other(**test_params)
# save_routings(**test_params)
out_file_results = os.path.join(out_dir_train,'save_class_as_other_single_batch_'+str(model_num))
out_file_html = os.path.join(out_file_results,'visualizing_class_variations_'+str(class_rel)+'.html')
# os.path.join('../scratch/ck_test','save_routings_single_batch_'+str(model_num))
elif type_exp==1:
save_visualizations.save_class_vary_mag(**test_params)
# save_routings(**test_params)
out_file_results = os.path.join(out_dir_train,'save_class_vary_mag_single_batch_'+str(model_num))
out_file_html = os.path.join(out_file_results,'visualizing_vary_mag_'+str(class_rel)+'.html')
# os.path.join('../scratch/ck_test','save_routings_single_batch_'+str(model_num))
elif type_exp ==2:
save_visualizations.save_class_vary_attr(**test_params)
out_file_results = os.path.join(out_dir_train,'save_class_vary_attr_single_batch_'+str(model_num)+'_'+str(class_rel))
out_file_html = os.path.join(out_file_results,'visualizing_vary_attr_'+str(class_rel)+'.html')
else:
save_visualizations.save_class_vary_mag_class_rel(**test_params)
# save_routings(**test_params)
out_file_results = os.path.join(out_dir_train,'save_class_vary_mag_single_batch_'+str(model_num)+'_'+str(class_rel))
out_file_html = os.path.join(out_file_results,'visualizing_vary_mag_'+str(class_rel)+'.html')
# os.path.join('../scratch/ck_test','save_routings_single_batch_'+str(model_num))
return
im_files = np.load(os.path.join(out_file_results,'ims_all.npy'))
captions = np.array(im_files)
im_files_new = []
captions_new = []
for r in range(im_files.shape[0]):
caption_row = []
im_row = []
for c in range(im_files.shape[1]):
file_curr = im_files[r,c]
caption_row.append(os.path.split(file_curr)[1][:file_curr.rindex('.')])
# print file_curr
# print file_curr.replace(str_replace[0],str_replace[1])
# print util.getRelPath(file_curr.replace(str_replace[0],str_replace[1]),dir_server)
im_row.append(util.getRelPath(file_curr.replace(str_replace[0],str_replace[1]),dir_server))
# im_files[r,c] =
# print im_files[r,c]
# raw_input()
im_files_new.append(im_row)
captions_new.append(caption_row)
visualize.writeHTML(out_file_html,im_files_new,captions_new,96,96)
print out_file_html.replace(str_replace[0],str_replace[1]).replace(dir_server,click_str)
def train_gray(wdecay,
lr,
route_iter,
folds=[4, 9],
model_name='vgg_capsule_bp4d',
epoch_stuff=[30, 60],
res=False,
class_weights=False,
reconstruct=False,
loss_weights=None,
exp=False,
disfa=False,
vgg_base_file=None,
vgg_base_file_str=None,
mean_file=None,
std_file=None,
aug_more=False,
align=True):
out_dirs = []
out_dir_meta = '../experiments/' + model_name + str(route_iter)
num_epochs = epoch_stuff[1]
epoch_start = 0
if exp:
dec_after = ['exp', 0.96, epoch_stuff[0], 1e-6]
else:
dec_after = ['step', epoch_stuff[0], 0.1]
lr = lr
im_resize = 110
# 256
im_size = 96
save_after = 1
if disfa:
dir_files = '../data/disfa'
# type_data = 'train_test_10_6_method_110_gray_align'; n_classes = 10;
type_data = 'train_test_8_au_all_method_110_gray_align'
n_classes = 8
pre_pend = 'disfa_' + type_data + '_'
binarize = True
else:
dir_files = '../data/bp4d'
if align:
type_data = 'train_test_files_110_gray_align'
n_classes = 12
else:
type_data = 'train_test_files_110_gray_nodetect'
n_classes = 12
pre_pend = 'bp4d_' + type_data + '_'
binarize = False
criterion = 'marginmulti'
criterion_str = criterion
init = False
aug_str = aug_more
# if aug_more:
# aug_str = 'cropkhAugNoColor'
# else:
# aug_str = 'flipCrop'
strs_append = '_' + '_'.join([
str(val) for val in [
'reconstruct', reconstruct, class_weights, aug_str, criterion_str,
init, 'wdecay', wdecay, num_epochs
] + dec_after + lr + ['lossweights'] + loss_weights +
[vgg_base_file_str]
])
lr_p = lr[:]
for split_num in folds:
if res:
# strs_appendc = '_'+'_'.join([str(val) for val in ['reconstruct',reconstruct,True,'flipCrop',criterion_str,init,'wdecay',wdecay,10,'exp',0.96,350,1e-6]+['lossweights']+loss_weights])
# dec_afterc = dec_after
strs_appendc = '_' + '_'.join([
str(val) for val in [
'reconstruct', reconstruct, True, aug_str, criterion_str,
init, 'wdecay', wdecay, 10
] + dec_after + lr + ['lossweights'] + loss_weights +
[vgg_base_file_str]
])
out_dir_train = os.path.join(
out_dir_meta, pre_pend + str(split_num) + strs_appendc)
model_file = os.path.join(out_dir_train, 'model_9.pt')
epoch_start = 10
# lr =[0.1*lr_curr for lr_curr in lr_p]
else:
model_file = None
margin_params = None
out_dir_train = os.path.join(out_dir_meta,
pre_pend + str(split_num) + strs_append)
final_model_file = os.path.join(out_dir_train,
'model_' + str(num_epochs - 1) + '.pt')
if os.path.exists(final_model_file):
print 'skipping', final_model_file
# raw_input()
# continue
else:
print 'not skipping', final_model_file
# raw_input()
# continue
train_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '.txt')
test_file = os.path.join(dir_files, type_data,
'test_' + str(split_num) + '.txt')
if vgg_base_file is None:
mean_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '_mean.png')
std_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '_std.png')
print train_file
print test_file
print mean_file
print std_file
# raw_input()
class_weights = util.get_class_weights_au(
util.readLinesFromFile(train_file))
data_transforms = {}
if aug_more == 'cropkhAugNoColor':
train_resize = None
print 'AUGING MORE'
list_of_todos = ['flip', 'rotate', 'scale_translate']
data_transforms['train'] = transforms.Compose([
lambda x: augmenters.random_crop(x, im_size),
lambda x: augmenters.augment_image(x, list_of_todos),
# lambda x: augmenters.horizontal_flip(x),
transforms.ToTensor(),
lambda x: x * 255,
])
elif aug_more == 'cropFlip':
train_resize = None
data_transforms['train'] = transforms.Compose([
lambda x: augmenters.random_crop(x, im_size),
lambda x: augmenters.horizontal_flip(x),
transforms.ToTensor(),
lambda x: x * 255,
])
elif aug_more == 'NONE':
train_resize = im_size
data_transforms['train'] = transforms.Compose([
transforms.ToTensor(),
lambda x: x * 255,
])
else:
raise ValueError('aug_more is problematic')
data_transforms['val'] = transforms.Compose([
transforms.ToTensor(),
lambda x: x * 255,
])
train_data = dataset.Bp4d_Dataset_Mean_Std_Im(
train_file,
mean_file,
std_file,
transform=data_transforms['train'],
binarize=binarize,
resize=train_resize)
test_data = dataset.Bp4d_Dataset_Mean_Std_Im(
test_file,
mean_file,
std_file,
resize=im_size,
transform=data_transforms['val'],
binarize=binarize)
# train_data = dataset.Bp4d_Dataset_Mean_Std_Im(test_file, mean_file, std_file, resize= im_size, transform = data_transforms['val'])
network_params = dict(n_classes=n_classes,
pool_type='max',
r=route_iter,
init=init,
class_weights=class_weights,
reconstruct=reconstruct,
loss_weights=loss_weights,
vgg_base_file=vgg_base_file)
batch_size = 128
batch_size_val = 128
util.makedirs(out_dir_train)
train_params = dict(out_dir_train=out_dir_train,
train_data=train_data,
test_data=test_data,
batch_size=batch_size,
batch_size_val=batch_size_val,
num_epochs=num_epochs,
save_after=save_after,
disp_after=1,
plot_after=10,
test_after=1,
lr=lr,
dec_after=dec_after,
model_name=model_name,
criterion=criterion,
gpu_id=0,
num_workers=0,
model_file=model_file,
epoch_start=epoch_start,
margin_params=margin_params,
network_params=network_params,
weight_decay=wdecay)
test_params = dict(out_dir_train=out_dir_train,
model_num=num_epochs - 1,
train_data=train_data,
test_data=test_data,
gpu_id=0,
model_name=model_name,
batch_size_val=batch_size_val,
criterion=criterion,
margin_params=margin_params,
network_params=network_params,
barebones=True)
# test_params_train = dict(**test_params)
# test_params_train['test_data'] = train_data_no_t
# test_params_train['post_pend'] = '_train'
print train_params
param_file = os.path.join(out_dir_train, 'params.txt')
all_lines = []
for k in train_params.keys():
str_print = '%s: %s' % (k, train_params[k])
print str_print
all_lines.append(str_print)
util.writeFile(param_file, all_lines)
# if reconstruct:
train_model_recon(**train_params)
test_model_recon(**test_params)
# test_model_recon(**test_params_train)
# else:
# train_model(**train_params)
# test_params = dict(out_dir_train = out_dir_train,
# model_num = num_epochs-1,
# train_data = train_data,
# test_data = test_data,
# gpu_id = 0,
# model_name = model_name,
# batch_size_val = batch_size_val,
# criterion = criterion,
# margin_params = margin_params,
# network_params = network_params)
# test_model(**test_params)
getting_accuracy.print_accuracy(out_dir_meta,
pre_pend,
strs_append,
folds,
log='log.txt')
def save_test_results(wdecay,
lr,
route_iter,
folds=[4, 9],
model_name='vgg_capsule_bp4d',
epoch_stuff=[30, 60],
res=False,
class_weights=False,
reconstruct=False,
loss_weights=None,
models_to_test=None,
exp=False,
disfa=False):
out_dirs = []
out_dir_meta = '../experiments/' + model_name + str(route_iter)
num_epochs = epoch_stuff[1]
epoch_start = 0
# dec_after = ['exp',0.96,epoch_stuff[0],1e-6]
if exp:
dec_after = ['exp', 0.96, epoch_stuff[0], 1e-6]
else:
dec_after = ['step', epoch_stuff[0], 0.1]
lr = lr
im_resize = 110
# 256
im_size = 96
# save_after = 1
if disfa:
dir_files = '../data/disfa'
# type_data = 'train_test_10_6_method_110_gray_align'; n_classes = 10;
type_data = 'train_test_8_au_all_method_110_gray_align'
n_classes = 8
pre_pend = 'disfa_' + type_data + '_'
binarize = True
else:
dir_files = '../data/bp4d'
type_data = 'train_test_files_110_gray_align'
n_classes = 12
pre_pend = 'bp4d_' + type_data + '_'
binarize = False
criterion = 'marginmulti'
criterion_str = criterion
init = False
strs_append = '_' + '_'.join([
str(val) for val in [
'reconstruct', reconstruct, class_weights, 'flipCrop',
criterion_str, init, 'wdecay', wdecay, num_epochs
] + dec_after + lr + ['lossweights'] + loss_weights
])
# pre_pend = 'bp4d_110_'
lr_p = lr[:]
for split_num in folds:
for model_num_curr in models_to_test:
margin_params = None
out_dir_train = os.path.join(
out_dir_meta, pre_pend + str(split_num) + strs_append)
final_model_file = os.path.join(
out_dir_train, 'model_' + str(num_epochs - 1) + '.pt')
if os.path.exists(
os.path.join(out_dir_train,
'results_model_' + str(model_num_curr))):
print 'exists', model_num_curr, split_num
print out_dir_train
# continue
else:
print 'does not exist', model_num_curr, split_num
# print 'bp4d_train_test_files_110_gray_align_0_reconstruct_True_True_flipCrop_marginmulti_False_wdecay_0_20_exp_0.96_350_1e-06_0.001_0.001_0.001_lossweights_1.0_1.0'
print out_dir_train
# raw_input()
# if os.path.exists(final_model_file):
# print 'skipping',final_model_file
# # raw_input()
# # continue
# else:
# print 'not skipping', final_model_file
# # raw_input()
# # continue
train_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '.txt')
test_file = os.path.join(dir_files, type_data,
'test_' + str(split_num) + '.txt')
mean_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '_mean.png')
std_file = os.path.join(dir_files, type_data,
'train_' + str(split_num) + '_std.png')
# train_file = os.path.join('../data/bp4d',type_data,'train_'+str(split_num)+'.txt')
# test_file = os.path.join('../data/bp4d',type_data,'test_'+str(split_num)+'.txt')
if model_name.startswith('vgg'):
mean_std = np.array([[93.5940, 104.7624, 129.1863],
[1., 1., 1.]]) #bgr
bgr = True
else:
# print 'ELSING'
# mean_std = np.array([[129.1863,104.7624,93.5940],[1.,1.,1.]])
mean_std = np.array([[0.485 * 255, 0.456 * 255, 0.406 * 255],
[0.229 * 255, 0.224 * 255, 0.225 * 255]])
# print mean_std
# raw_input()
bgr = False
# print mean_std
# mean_im = scipy.misc.imread(mean_file).astype(np.float32)
# std_im = scipy.misc.imread(std_file).astype(np.float32)
class_weights = util.get_class_weights_au(
util.readLinesFromFile(train_file))
data_transforms = {}
data_transforms['train'] = transforms.Compose([
lambda x: augmenters.random_crop(x, im_size),
lambda x: augmenters.horizontal_flip(x),
transforms.ToTensor(),
lambda x: x * 255,
])
data_transforms['val'] = transforms.Compose([
# transforms.ToPILImage(),
# transforms.Resize((im_size,im_size)),
# lambda x: augmenters.resize(x,im_size),
transforms.ToTensor(),
lambda x: x * 255,
])
# data_transforms = {}
# data_transforms['train']= transforms.Compose([
# transforms.ToPILImage(),
# # transforms.Resize((im_resize,im_resize)),
# transforms.RandomCrop(im_size),
# transforms.RandomHorizontalFlip(),
# transforms.RandomRotation(15),
# transforms.ColorJitter(),
# transforms.ToTensor(),
# lambda x: x*255,
# transforms.Normalize(mean_std[0,:],mean_std[1,:]),
# ])
# data_transforms['val']= transforms.Compose([
# transforms.ToPILImage(),
# transforms.Resize((im_size,im_size)),
# transforms.ToTensor(),
# lambda x: x*255,
# transforms.Normalize(mean_std[0,:],mean_std[1,:]),
# ])
# print train_file
# print test_file
# train_data = dataset.Bp4d_Dataset(train_file, bgr = bgr, transform = data_transforms['train'])
# test_data = dataset.Bp4d_Dataset(test_file, bgr = bgr, transform = data_transforms['val'])
train_data = dataset.Bp4d_Dataset_Mean_Std_Im(
train_file,
mean_file,
std_file,
transform=data_transforms['train'],
binarize=binarize)
test_data = dataset.Bp4d_Dataset_Mean_Std_Im(
test_file,
mean_file,
std_file,
resize=im_size,
transform=data_transforms['val'],
binarize=binarize)
network_params = dict(n_classes=n_classes,
pool_type='max',
r=route_iter,
init=init,
class_weights=class_weights,
reconstruct=reconstruct,
loss_weights=loss_weights)
batch_size = 96
batch_size_val = 96
util.makedirs(out_dir_train)
test_params = dict(out_dir_train=out_dir_train,
model_num=model_num_curr,
train_data=train_data,
test_data=test_data,
gpu_id=0,
model_name=model_name,
batch_size_val=batch_size_val,
criterion=criterion,
margin_params=margin_params,
network_params=network_params,
barebones=True)
test_model_recon(**test_params)