elif conf.model == 'shz_fusion':
from lib.shz_models.rel_model_fusion import RelModel
elif conf.model == 'shz_fusion_beta':
from lib.shz_models.rel_model_fusion_beta import RelModel
# --
else:
raise ValueError()
# -- Create Tensorboard summary writer
writer = SummaryWriter(comment='_run#' + conf.save_dir.split('/')[-1])
# -- Create dataset splits and dataset loader
train, val, _ = VG.splits(
num_val_im=conf.val_size,
filter_duplicate_rels=True,
use_proposals=conf.use_proposals,
filter_non_overlap=conf.mode == 'sgdet',
# -- Depth dataset parameters
use_depth=conf.load_depth,
three_channels_depth=conf.pretrained_depth)
train_loader, val_loader = VGDataLoader.splits(
train,
val,
mode='rel',
batch_size=conf.batch_size,
num_workers=conf.num_workers,
num_gpus=conf.num_gpus,
# -- Depth dataset parameters
use_depth=conf.load_depth)
# -- Create the specified Relation-Detection model
from lib.evaluation.sg_eval import BasicSceneGraphEvaluator
from tqdm import tqdm
from config import BOX_SCALE, IM_SCALE
import dill as pkl
import os
conf = ModelConfig()
if conf.model == 'motifnet':
from lib.rel_model import RelModel
elif conf.model == 'stanford':
from lib.rel_model_stanford import RelModelStanford as RelModel
else:
raise ValueError()
train, val, test = VG.splits(num_val_im=conf.val_size, filter_duplicate_rels=True,
use_proposals=conf.use_proposals,
filter_non_overlap=conf.mode == 'sgdet')
if conf.test:
val = test
if conf.train:
val = train
train_loader, val_loader = VGDataLoader.splits(train, val, mode='rel',
batch_size=conf.batch_size,
num_workers=conf.num_workers,
num_gpus=conf.num_gpus)
detector = RelModel(classes=train.ind_to_classes, rel_classes=train.ind_to_predicates,
num_gpus=conf.num_gpus, mode=conf.mode, require_overlap_det=True,
use_resnet=conf.use_resnet, order=conf.order,
nl_edge=conf.nl_edge, nl_obj=conf.nl_obj, hidden_dim=conf.hidden_dim,
use_proposals=conf.use_proposals,
"""
SCRIPT TO MAKE MEMES. this was from an old version of the code, so it might require some fixes to get working.
"""
from dataloaders.visual_genome import VG
# import matplotlib
# # matplotlib.use('Agg')
from tqdm import tqdm
import seaborn as sns
import numpy as np
from lib.fpn.box_intersections_cpu.bbox import bbox_overlaps
from collections import defaultdict
train, val, test = VG.splits(filter_non_overlap=False, num_val_im=2000)
count_threshold = 50
pmi_threshold = 10
o_type = []
f = open("object_types.txt")
for line in f.readlines():
tabs = line.strip().split("\t")
t = tabs[1].split("_")[0]
o_type.append(t)
r_type = []
f = open("relation_types.txt")
for line in f.readlines():
tabs = line.strip().split("\t")
t = tabs[1].split("_")[0]
r_type.append(t)
def main():
args = 'X -m predcls -model motifnet -order leftright -nl_obj 2 -nl_edge 4 -b 6 -clip 5 -p 100 -hidden_dim 512 -pooling_dim 4096 -lr 1e-3 -ngpu 1 -test -ckpt checkpoints/vgrel-motifnet-sgcls.tar -nepoch 50 -use_bias -multipred -cache motifnet_predcls1'
sys.argv = args.split(' ')
conf = ModelConfig()
if conf.model == 'motifnet':
from lib.rel_model import RelModel
elif conf.model == 'stanford':
from lib.rel_model_stanford import RelModelStanford as RelModel
else:
raise ValueError()
train, val, test = VG.splits(
num_val_im=conf.val_size, filter_duplicate_rels=True,
use_proposals=conf.use_proposals,
filter_non_overlap=conf.mode == 'sgdet',
)
if conf.test:
val = test
train_loader, val_loader = VGDataLoader.splits(
train, val, mode='rel', batch_size=conf.batch_size,
num_workers=conf.num_workers, num_gpus=conf.num_gpus
)
detector = RelModel(
classes=train.ind_to_classes, rel_classes=train.ind_to_predicates,
num_gpus=conf.num_gpus, mode=conf.mode, require_overlap_det=True,
use_resnet=conf.use_resnet, order=conf.order,
nl_edge=conf.nl_edge, nl_obj=conf.nl_obj, hidden_dim=conf.hidden_dim,
use_proposals=conf.use_proposals,
pass_in_obj_feats_to_decoder=conf.pass_in_obj_feats_to_decoder,
pass_in_obj_feats_to_edge=conf.pass_in_obj_feats_to_edge,
pooling_dim=conf.pooling_dim,
rec_dropout=conf.rec_dropout,
use_bias=conf.use_bias,
use_tanh=conf.use_tanh,
limit_vision=conf.limit_vision
)
detector.cuda()
ckpt = torch.load(conf.ckpt)
optimistic_restore(detector, ckpt['state_dict'])
evaluator = BasicSceneGraphEvaluator.all_modes(
multiple_preds=conf.multi_pred)
mode, N = 'test.multi_pred', 20
recs = pkl.load(open('{}.{}.pkl'.format(mode, N), 'rb'))
np.random.seed(0)
# sorted_idxs = np.argsort(recs)
selected_idxs = np.random.choice(range(len(recs)), size=100, replace=False)
sorted_idxs = selected_idxs[np.argsort(np.array(recs)[selected_idxs])]
print('Sorted idxs: {}'.format(sorted_idxs.tolist()))
save_dir = '/nethome/bamos/2018-intel/data/2018-07-31/sgs.multi'
for idx in selected_idxs:
gt_entry = {
'gt_classes': val.gt_classes[idx].copy(),
'gt_relations': val.relationships[idx].copy(),
'gt_boxes': val.gt_boxes[idx].copy(),
}
detector.eval()
det_res = detector[vg_collate([test[idx]], num_gpus=1)]
boxes_i, objs_i, obj_scores_i, rels_i, pred_scores_i = det_res
pred_entry = {
'pred_boxes': boxes_i * BOX_SCALE/IM_SCALE,
'pred_classes': objs_i,
'pred_rel_inds': rels_i,
'obj_scores': obj_scores_i,
'rel_scores': pred_scores_i,
}
unique_cnames = get_unique_cnames(gt_entry, test)
save_img(idx, recs, test, gt_entry, det_res, unique_cnames, save_dir)
save_gt_graph(idx, test, gt_entry, det_res, unique_cnames, save_dir)
save_pred_graph(idx, test, pred_entry, det_res,
unique_cnames, save_dir,
multi_pred=conf.multi_pred, n_pred=20)
import pandas as pd
import time
import os
from config import ModelConfig, FG_FRACTION, RPN_FG_FRACTION, IM_SCALE, BOX_SCALE
from torch.nn import functional as F
from lib.fpn.box_utils import bbox_loss
import torch.backends.cudnn as cudnn
from pycocotools.cocoeval import COCOeval
from lib.pytorch_misc import optimistic_restore, clip_grad_norm
from torch.optim.lr_scheduler import ReduceLROnPlateau
cudnn.benchmark = True
conf = ModelConfig()
train, val, _ = VG.splits(num_val_im=conf.val_size,
filter_non_overlap=False,
filter_empty_rels=False,
use_proposals=conf.use_proposals)
train_loader, val_loader = VGDataLoader.splits(train,
val,
batch_size=conf.batch_size,
num_workers=conf.num_workers,
num_gpus=conf.num_gpus)
detector = ObjectDetector(
classes=train.ind_to_classes,
num_gpus=conf.num_gpus,
mode='rpntrain' if not conf.use_proposals else 'proposals',
use_resnet=conf.use_resnet)
detector.cuda()
# Note: if you're doing the stanford setup, you'll need to change this to freeze the lower layers
type=str,
default='caches/kern_sgcls.pkl')
args = parser.parse_args()
os.makedirs(args.save_dir, exist_ok=True)
image_dir = os.path.join(args.save_dir, 'images')
graph_dir = os.path.join(args.save_dir, 'graphs')
os.makedirs(image_dir, exist_ok=True)
os.makedirs(graph_dir, exist_ok=True)
mode = 'sgcls' # this code is only for sgcls task
# train, val, test = VG.splits(num_val_im=conf.val_size, filter_duplicate_rels=True,
# use_proposals=conf.use_proposals,
# filter_non_overlap=conf.mode == 'sgdet')
train, val, test = VG.splits(num_val_im=5000,
filter_duplicate_rels=True,
use_proposals=False,
filter_non_overlap=False)
val = test
# train_loader, val_loader = VGDataLoader.splits(train, val, mode='rel',
# batch_size=conf.batch_size,
# num_workers=conf.num_workers,
# num_gpus=conf.num_gpus)
train_loader, val_loader = VGDataLoader.splits(train,
val,
mode='rel',
batch_size=1,
num_workers=1,
num_gpus=1)
ind_to_predicates = train.ind_to_predicates
ind_to_classes = train.ind_to_classes
import pandas as pd
import time
from tqdm import tqdm
from torch.nn.functional import cross_entropy as CE
from lib.pytorch_misc import *
from lib.evaluation.sg_eval import BasicSceneGraphEvaluator, calculate_mR_from_evaluator_list, eval_entry
import pickle
from lib.rel_model_stanford import RelModelStanford
EVAL_MODES = ['sgdet'] if conf.mode == 'sgdet' else ['predcls', 'sgcls']
assert conf.mode in EVAL_MODES, (conf.mode, 'other modes not supported')
train, val_splits = VG.splits(data_dir=conf.data,
num_val_im=conf.val_size,
min_graph_size=conf.min_graph_size,
max_graph_size=conf.max_graph_size,
mrcnn=conf.detector == 'mrcnn',
filter_non_overlap=conf.mode == 'sgdet',
exclude_left_right=conf.exclude_left_right)
train_loader, val_loaders = VGDataLoader.splits(train,
val_splits,
mode='rel',
batch_size=conf.batch_size,
num_workers=conf.num_workers,
num_gpus=conf.num_gpus)
val_loader, val_loader_zs, test_loader, test_loader_zs = val_loaders
detector = RelModelStanford(train_data=train,
num_gpus=conf.num_gpus,
mode=conf.mode,
import numpy as np
import torch
from config import ModelConfig
from lib.pytorch_misc import optimistic_restore
from lib.evaluation.sg_eval import BasicSceneGraphEvaluator
from tqdm import tqdm
from config import BOX_SCALE, IM_SCALE
from lib.fpn.box_utils import bbox_overlaps
from collections import defaultdict
from PIL import Image, ImageDraw, ImageFont
import os
from functools import reduce
conf = ModelConfig()
train, val, test = VG.splits(num_val_im=conf.val_size)
if conf.test:
val = test
train_loader, val_loader = VGDataLoader.splits(train, val, mode='rel',
batch_size=conf.batch_size,
num_workers=conf.num_workers,
num_gpus=conf.num_gpus)
detector = RelModel(classes=train.ind_to_classes, rel_classes=train.ind_to_predicates,
num_gpus=conf.num_gpus, mode=conf.mode, require_overlap_det=True,
use_resnet=conf.use_resnet, order=conf.order,
nl_edge=conf.nl_edge, nl_obj=conf.nl_obj, hidden_dim=conf.hidden_dim,
use_proposals=conf.use_proposals,
pass_in_obj_feats_to_decoder=conf.pass_in_obj_feats_to_decoder,
pass_in_obj_feats_to_edge=conf.pass_in_obj_feats_to_edge,
def __init__(self,
classes,
rel_classes,
embed_dim,
obj_dim,
inputs_dim,
hidden_dim,
pooling_dim,
recurrent_dropout_probability=0.2,
use_highway=True,
use_input_projection_bias=True,
use_vision=True,
use_bias=True,
use_tanh=True,
limit_vision=True,
sl_pretrain=False,
num_iter=-1):
"""
Initializes the RNN
:param embed_dim: Dimension of the embeddings
:param encoder_hidden_dim: Hidden dim of the encoder, for attention purposes
:param hidden_dim: Hidden dim of the decoder
:param vocab_size: Number of words in the vocab
:param bos_token: To use during decoding (non teacher forcing mode))
:param bos: beginning of sentence token
:param unk: unknown token (not used)
"""
super(DecoderRNN, self).__init__()
self.rel_embedding_dim = 100
self.classes = classes
self.rel_classes = rel_classes
embed_vecs = obj_edge_vectors(['start'] + self.classes, wv_dim=100)
self.obj_embed = nn.Embedding(len(self.classes), embed_dim)
self.obj_embed.weight.data = embed_vecs
embed_rels = obj_edge_vectors(self.rel_classes,
wv_dim=self.rel_embedding_dim)
self.rel_embed = nn.Embedding(len(self.rel_classes),
self.rel_embedding_dim)
self.rel_embed.weight.data = embed_rels
self.embed_dim = embed_dim
self.obj_dim = obj_dim
self.hidden_size = hidden_dim
self.inputs_dim = inputs_dim
self.pooling_dim = pooling_dim
self.nms_thresh = 0.3
self.use_vision = use_vision
self.use_bias = use_bias
self.use_tanh = use_tanh
self.limit_vision = limit_vision
self.sl_pretrain = sl_pretrain
self.num_iter = num_iter
self.recurrent_dropout_probability = recurrent_dropout_probability
self.use_highway = use_highway
# We do the projections for all the gates all at once, so if we are
# using highway layers, we need some extra projections, which is
# why the sizes of the Linear layers change here depending on this flag.
if use_highway:
self.input_linearity = torch.nn.Linear(
self.input_size,
6 * self.hidden_size,
bias=use_input_projection_bias)
self.state_linearity = torch.nn.Linear(self.hidden_size,
5 * self.hidden_size,
bias=True)
else:
self.input_linearity = torch.nn.Linear(
self.input_size,
4 * self.hidden_size,
bias=use_input_projection_bias)
self.state_linearity = torch.nn.Linear(self.hidden_size,
4 * self.hidden_size,
bias=True)
# self.obj_in_lin = torch.nn.Linear(self.rel_embedding_dim, self.rel_embedding_dim, bias=True)
self.out = nn.Linear(self.hidden_size, len(self.classes))
self.reset_parameters()
# For relation predication
embed_vecs2 = obj_edge_vectors(self.classes, wv_dim=embed_dim)
self.obj_embed2 = nn.Embedding(self.num_classes, embed_dim)
self.obj_embed2.weight.data = embed_vecs2.clone()
# self.post_lstm = nn.Linear(self.hidden_dim, self.pooling_dim * 2)
self.post_lstm = nn.Linear(self.obj_dim + 2 * self.embed_dim + 128,
self.pooling_dim * 2)
# Initialize to sqrt(1/2n) so that the outputs all have mean 0 and variance 1.
# (Half contribution comes from LSTM, half from embedding.
# In practice the pre-lstm stuff tends to have stdev 0.1 so I multiplied this by 10.
self.post_lstm.weight.data.normal_(
0, 10.0 * math.sqrt(1.0 / self.hidden_size)
) ######## there may need more consideration
self.post_lstm.bias.data.zero_()
self.rel_compress = nn.Linear(self.pooling_dim,
self.num_rels,
bias=True)
self.rel_compress.weight = torch.nn.init.xavier_normal(
self.rel_compress.weight, gain=1.0)
if self.use_bias:
self.freq_bias = FrequencyBias()
# simple relation model
from dataloaders.visual_genome import VG
from lib.get_dataset_counts import get_counts, box_filter
fg_matrix, bg_matrix = get_counts(train_data=VG.splits(
num_val_im=5000,
filter_non_overlap=True,
filter_duplicate_rels=True,
use_proposals=False)[0],
must_overlap=True)
prob_matrix = fg_matrix.astype(np.float32)
prob_matrix[:, :, 0] = bg_matrix
# TRYING SOMETHING NEW.
prob_matrix[:, :, 0] += 1
prob_matrix /= np.sum(prob_matrix, 2)[:, :, None]
# prob_matrix /= float(fg_matrix.max())
prob_matrix[:, :, 0] = 0 # Zero out BG
self.prob_matrix = prob_matrix