def __init__(self,
env_list=None,
instr_negatives=False,
instr_negatives_similar_only=False,
seg_level=False,
img_scale=1,
yaw_rand_range=0,
pos_rand_range=0
):
# If data is already loaded in memory, use it
self.env_list = env_list
self.train_instr, self.dev_instr, self.test_instr, corpus = get_all_instructions()
self.all_instr = {**self.train_instr, **self.dev_instr, **self.test_instr}
self.token2term, self.word2token = get_word_to_token_map(corpus)
self.thesaurus = load_thesaurus()
self.include_instr_negatives = instr_negatives
if instr_negatives:
self.similar_instruction_map = load_similar_instruction_map()
self.instr_negatives_similar_only = instr_negatives_similar_only
self.img_scale = img_scale
self.yaw_rand_range = yaw_rand_range
self.pos_rand_range = pos_rand_range
self.pos_rand_image = 0
# If the data is supposed to be at seg level (not nested envs + segs), then we can support batching
# but we need to correctly infer the dataset size
self.seg_level = seg_level
if seg_level:
self.seg_list = []
for env in self.env_list:
for set_idx, set in enumerate(self.all_instr[env]):
for seg_idx, seg in enumerate(set["instructions"]):
self.seg_list.append([env, set_idx, seg_idx])
def __init__(self,
env_list=None,
instr_negatives=False,
instr_negatives_similar_only=False,
seg_level=False,
yaw_rand_range=0,
img_w=512,
img_h=512,
map_w=None,
map_h=None,
incl_path=True,
incl_endpoint=False,
use_semantic_maps=False):
# If data is already loaded in memory, use it
self.cuda = False
self.env_list = env_list
self.train_instr, self.dev_instr, self.test_instr, corpus = get_all_instructions()
self.all_instr = {**self.train_instr, **self.dev_instr, **self.test_instr}
self.token2term, self.word2token = get_word_to_token_map(corpus)
self.thesaurus = load_thesaurus()
self.include_instr_negatives = instr_negatives
#if instr_negatives:
# self.similar_instruction_map = load_similar_instruction_map()
self.instr_negatives_similar_only = instr_negatives_similar_only
self.use_semantic_maps = use_semantic_maps
self.img_w = img_w
self.img_h = img_h
if map_w is None:
self.map_w = self.img_w
self.map_h = self.img_h
else:
self.map_w = map_w
self.map_h = map_h
self.yaw_rand_range = yaw_rand_range
self.latest_img_dbg = None
self.latest_rot_img_dbg = None
self.incl_endpoint = incl_endpoint
self.incl_path = incl_path
# If the data is supposed to be at seg level (not nested envs + segs), then we can support batching
# but we need to correctly infer the dataset size
self.seg_level = seg_level
if seg_level:
self.seg_list = []
for env in self.env_list:
for set_idx, set in enumerate(self.all_instr[env]):
for seg_idx, seg in enumerate(set["instructions"]):
self.seg_list.append([env, set_idx, seg_idx])
print("Initialzied dataset!")
print(" yaw range : " + str(self.yaw_rand_range))
print(" map size: ", self.map_w, self.map_h)
print(" img size: ", self.img_w, self.img_h)
def __init__(self):
super(AuxLabelsNL, self).__init__()
self.thesaurus = load_thesaurus()
train_instructions, dev_instructions, test_instructions, corpus = get_all_instructions(
)
self.all_instructions = {
**train_instructions,
**dev_instructions,
**test_instructions
}
self.corpus = corpus
self.word2token, self.token2term = get_word_to_token_map(corpus)
def get_mentioned_landmarks_nl(str_instruction):
thesaurus = load_thesaurus()
if thesaurus is None:
return [], []
split_instr = split_instruction(clean_instruction(str_instruction))
word2term = thesaurus["word2term"]
term_groundings = thesaurus["term_groundings"]
lm_name2index = get_landmark_name_to_index()
# Map each word in the instruction to it's corresponding term:
split_instr_terms = words_to_terms(split_instr, word2term)
mentioned_landmark_names = set()
# For each term, find all the landmarks that have been mentioned
for term in split_instr_terms:
for landmark_name in term_groundings[term]["landmarks"]:
mentioned_landmark_names.add(landmark_name)
mentioned_landmark_names = list(mentioned_landmark_names)
mentioned_landmark_indices = [
lm_name2index[name] for name in mentioned_landmark_names
]
return mentioned_landmark_names, mentioned_landmark_indices