Python utils.assert_eq() Examples
The following are 16
code examples of utils.assert_eq().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
utils
, or try the search function
.
Example #1
Source File: dataset.py From Attention-on-Attention-for-VQA with MIT License | 6 votes |
def _load_dataset(dataroot, name, img_id2val): """Load entries img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val' """ question_path = os.path.join( dataroot, 'v2_OpenEnded_mscoco_%s2014_questions.json' % name) questions = sorted(json.load(open(question_path))['questions'], key=lambda x: x['question_id']) answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name) answers = cPickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] entries.append(_create_entry(img_id2val[img_id], question, answer)) return entries
Example #2
Source File: dataset_cp_v2.py From VQA_ReGAT with MIT License | 6 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad to the back of the sentence padding = [self.dictionary.padding_idx] * \ (max_length - len(tokens)) tokens = tokens + padding utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #3
Source File: dataset.py From VQA_ReGAT with MIT License | 6 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad to the back of the sentence padding = [self.dictionary.padding_idx] * \ (max_length - len(tokens)) tokens = tokens + padding utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #4
Source File: dataset.py From bottom-up-attention-vqa with GNU General Public License v3.0 | 6 votes |
def _load_dataset(dataroot, name, img_id2val): """Load entries img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val' """ question_path = os.path.join( dataroot, 'v2_OpenEnded_mscoco_%s2014_questions.json' % name) questions = sorted(json.load(open(question_path))['questions'], key=lambda x: x['question_id']) answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name) answers = cPickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] entries.append(_create_entry(img_id2val[img_id], question, answer)) return entries
Example #5
Source File: dataset.py From bottom-up-attention-tf with MIT License | 6 votes |
def _load_dataset(dataroot, name, img_id2val): """Load entries img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val' """ question_path = os.path.join( dataroot, 'v2_OpenEnded_mscoco_%s2014_questions.json' % name) questions = sorted(json.load(open(question_path))['questions'], key=lambda x: x['question_id']) answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name) answers = pickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] entries.append(_create_entry(img_id2val[img_id], question, answer)) return entries
Example #6
Source File: dataset.py From Attention-on-Attention-for-VQA with MIT License | 5 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = padding + tokens utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #7
Source File: eval.py From VQA_ReGAT with MIT License | 5 votes |
def make_json(logits, qIds, dataloader): utils.assert_eq(logits.size(0), len(qIds)) results = [] for i in range(logits.size(0)): result = {} result['question_id'] = qIds[i].item() result['answer'] = get_answer(logits[i], dataloader) results.append(result) return results
Example #8
Source File: dataset_cp_v2.py From VQA_ReGAT with MIT License | 5 votes |
def _load_dataset(dataroot, name, coco_train_img_id2val, coco_val_img_id2val, label2ans): """Load entries coco_train_img_id2val/coco_val_img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val' """ question_path = os.path.join( dataroot, 'cp_v2_questions/vqacp_v2_%s_questions.json' % name) questions = sorted(json.load(open(question_path)), key=lambda x: x['question_id']) answer_path = os.path.join(dataroot, 'cache', 'cp_v2_%s_target.pkl' % name) answers = pickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] coco_split = question["coco_split"] index = coco_train_img_id2val[img_id]\ if coco_split == "train2014" else coco_val_img_id2val[img_id] if not COUNTING_ONLY \ or is_howmany(question['question'], answer, label2ans): entries.append(_create_entry(index, question, answer)) return entries
Example #9
Source File: dataset.py From VQA_ReGAT with MIT License | 5 votes |
def _load_dataset(dataroot, name, img_id2val, label2ans): """Load entries img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val', 'test-dev2015', test2015' """ question_path = os.path.join( dataroot, 'Questions/v2_OpenEnded_mscoco_%s_questions.json' % (name + '2014' if 'test' != name[:4] else name)) questions = sorted(json.load(open(question_path))['questions'], key=lambda x: x['question_id']) # train, val if 'test' != name[:4]: answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name) answers = pickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] if not COUNTING_ONLY \ or is_howmany(question['question'], answer, label2ans): entries.append(_create_entry(img_id2val[img_id], question, answer)) # test2015 else: entries = [] for question in questions: img_id = question['image_id'] if not COUNTING_ONLY \ or is_howmany(question['question'], None, None): entries.append(_create_entry(img_id2val[img_id], question, None)) return entries
Example #10
Source File: dataset.py From bottom-up-attention-vqa with GNU General Public License v3.0 | 5 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = padding + tokens utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #11
Source File: dataset.py From bottom-up-attention-tf with MIT License | 5 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = padding + tokens utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #12
Source File: test.py From ban-vqa with MIT License | 5 votes |
def make_json(logits, qIds, dataloader): utils.assert_eq(logits.size(0), len(qIds)) results = [] for i in range(logits.size(0)): result = {} result['question_id'] = qIds[i].item() result['answer'] = get_answer(logits[i], dataloader) results.append(result) return results
Example #13
Source File: dataset.py From ban-vqa with MIT License | 5 votes |
def _load_dataset(dataroot, name, img_id2val, label2ans): """Load entries img_id2val: dict {img_id -> val} val can be used to retrieve image or features dataroot: root path of dataset name: 'train', 'val', 'test-dev2015', test2015' """ question_path = os.path.join( dataroot, 'v2_OpenEnded_mscoco_%s_questions.json' % \ (name + '2014' if 'test'!=name[:4] else name)) questions = sorted(json.load(open(question_path))['questions'], key=lambda x: x['question_id']) if 'test'!=name[:4]: # train, val answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name) answers = cPickle.load(open(answer_path, 'rb')) answers = sorted(answers, key=lambda x: x['question_id']) utils.assert_eq(len(questions), len(answers)) entries = [] for question, answer in zip(questions, answers): utils.assert_eq(question['question_id'], answer['question_id']) utils.assert_eq(question['image_id'], answer['image_id']) img_id = question['image_id'] if not COUNTING_ONLY or is_howmany(question['question'], answer, label2ans): entries.append(_create_entry(img_id2val[img_id], question, answer)) else: # test2015 entries = [] for question in questions: img_id = question['image_id'] if not COUNTING_ONLY or is_howmany(question['question'], None, None): entries.append(_create_entry(img_id2val[img_id], question, None)) return entries
Example #14
Source File: dataset.py From ban-vqa with MIT License | 5 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = tokens + padding utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #15
Source File: dataset.py From ban-vqa with MIT License | 5 votes |
def tokenize(self, max_length=14): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['question'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = tokens + padding utils.assert_eq(len(tokens), max_length) entry['q_token'] = tokens
Example #16
Source File: dataset.py From ban-vqa with MIT License | 5 votes |
def tokenize(self, max_length=82): """Tokenizes the questions. This will add q_token in each entry of the dataset. -1 represent nil, and should be treated as padding_idx in embedding """ for entry in self.entries: tokens = self.dictionary.tokenize(entry['sentence'], False) tokens = tokens[:max_length] if len(tokens) < max_length: # Note here we pad in front of the sentence padding = [self.dictionary.padding_idx] * (max_length - len(tokens)) tokens = tokens + padding utils.assert_eq(len(tokens), max_length) entry['p_token'] = tokens