Python config.model_type() Examples
The following are 6
code examples of config.model_type().
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
config
, or try the search function
.
Example #1
Source File: RelGAN_G.py From TextGAN-PyTorch with MIT License | 6 votes |
def __init__(self, mem_slots, num_heads, head_size, embedding_dim, hidden_dim, vocab_size, max_seq_len, padding_idx, gpu=False): super(RelGAN_G, self).__init__(embedding_dim, hidden_dim, vocab_size, max_seq_len, padding_idx, gpu) self.name = 'relgan' self.temperature = 1.0 # init value is 1.0 self.embeddings = nn.Embedding(vocab_size, embedding_dim, padding_idx=padding_idx) if cfg.model_type == 'LSTM': # LSTM self.hidden_dim = hidden_dim self.lstm = nn.LSTM(embedding_dim, self.hidden_dim, batch_first=True) self.lstm2out = nn.Linear(self.hidden_dim, vocab_size) else: # RMC self.hidden_dim = mem_slots * num_heads * head_size self.lstm = RelationalMemory(mem_slots=mem_slots, head_size=head_size, input_size=embedding_dim, num_heads=num_heads, return_all_outputs=True) self.lstm2out = nn.Linear(self.hidden_dim, vocab_size) self.init_params() pass
Example #2
Source File: pixel_link_symbol.py From pixel_link with MIT License | 5 votes |
def _build_network(self): import config if config.model_type == MODEL_TYPE_vgg16: from nets import vgg with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, weights_regularizer=slim.l2_regularizer(config.weight_decay), weights_initializer= tf.contrib.layers.xavier_initializer(), biases_initializer = tf.zeros_initializer()): with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME') as sc: self.arg_scope = sc self.net, self.end_points = vgg.basenet( inputs = self.inputs) elif config.model_type == MODEL_TYPE_vgg16_no_dilation: from nets import vgg with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, weights_regularizer=slim.l2_regularizer(config.weight_decay), weights_initializer= tf.contrib.layers.xavier_initializer(), biases_initializer = tf.zeros_initializer()): with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME') as sc: self.arg_scope = sc self.net, self.end_points = vgg.basenet( inputs = self.inputs, dilation = False) else: raise ValueError('model_type not supported:%s'%(config.model_type))
Example #3
Source File: RelGAN_G.py From TextGAN-PyTorch with MIT License | 5 votes |
def init_hidden(self, batch_size=cfg.batch_size): if cfg.model_type == 'LSTM': h = torch.zeros(1, batch_size, self.hidden_dim) c = torch.zeros(1, batch_size, self.hidden_dim) if self.gpu: return h.cuda(), c.cuda() else: return h, c else: """init RMC memory""" memory = self.lstm.initial_state(batch_size) memory = self.lstm.repackage_hidden(memory) # detch memory at first return memory.cuda() if self.gpu else memory
Example #4
Source File: pixel_link_symbol.py From HUAWEIOCR-2019 with MIT License | 5 votes |
def _build_network(self): import config if config.model_type == MODEL_TYPE_vgg16: from nets import vgg with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, weights_regularizer=slim.l2_regularizer(config.weight_decay), weights_initializer= tf.contrib.layers.xavier_initializer(), biases_initializer = tf.zeros_initializer()): with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME') as sc: self.arg_scope = sc self.net, self.end_points = vgg.basenet( inputs = self.inputs) elif config.model_type == MODEL_TYPE_vgg16_no_dilation: from nets import vgg with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, weights_regularizer=slim.l2_regularizer(config.weight_decay), weights_initializer= tf.contrib.layers.xavier_initializer(), biases_initializer = tf.zeros_initializer()): with slim.arg_scope([slim.conv2d, slim.max_pool2d], padding='SAME') as sc: self.arg_scope = sc self.net, self.end_points = vgg.basenet( inputs = self.inputs, dilation = False) else: raise ValueError('model_type not supported:%s'%(config.model_type))
Example #5
Source File: infer.py From text-classifier with Apache License 2.0 | 4 votes |
def infer_classic(model_type='xgboost_lr', model_save_path='', label_vocab_path='', test_data_path='', pred_save_path='', feature_vec_path='', col_sep='\t', feature_type='tfidf_word'): # load data content data_set, true_labels = data_reader(test_data_path, col_sep) # init feature feature = Feature(data=data_set, feature_type=feature_type, feature_vec_path=feature_vec_path, is_infer=True) # get data feature data_feature = feature.get_feature() # load model if model_type == 'xgboost_lr': model = XGBLR(model_save_path) else: model = load_pkl(model_save_path) # predict pred_label_probs = model.predict_proba(data_feature) # label id map label_id = load_vocab(label_vocab_path) id_label = {v: k for k, v in label_id.items()} pred_labels = [id_label[prob.argmax()] for prob in pred_label_probs] pred_output = [id_label[prob.argmax()] + col_sep + str(prob.max()) for prob in pred_label_probs] logger.info("save infer label and prob result to:%s" % pred_save_path) save_predict_result(pred_output, ture_labels=None, pred_save_path=pred_save_path, data_set=data_set) # evaluate if true_labels: try: print(classification_report(true_labels, pred_labels)) print(confusion_matrix(true_labels, pred_labels)) except UnicodeEncodeError: true_labels_id = [label_id[i] for i in true_labels] pred_labels_id = [label_id[i] for i in pred_labels] print(classification_report(true_labels_id, pred_labels_id)) print(confusion_matrix(true_labels_id, pred_labels_id)) except Exception: print("error. no true labels") # analysis lr model if model_type == "logistic_regression": feature_weight_dict = load_dict(config.lr_feature_weight_path) pred_labels = cal_multiclass_lr_predict(data_set, feature_weight_dict, id_label) print(pred_labels[:5])
Example #6
Source File: infer.py From text-classifier with Apache License 2.0 | 4 votes |
def infer_deep_model(model_type='cnn', data_path='', model_save_path='', label_vocab_path='', max_len=300, batch_size=128, col_sep='\t', pred_save_path=None): from keras.models import load_model # load data content data_set, true_labels = data_reader(data_path, col_sep) # init feature # han model need [doc sentence dim] feature(shape 3); others is [sentence dim] feature(shape 2) if model_type == 'han': feature_type = 'doc_vectorize' else: feature_type = 'vectorize' feature = Feature(data_set, feature_type=feature_type, is_infer=True, max_len=max_len) # get data feature data_feature = feature.get_feature() # load model model = load_model(model_save_path) # predict, in keras, predict_proba same with predict pred_label_probs = model.predict(data_feature, batch_size=batch_size) # label id map label_id = load_vocab(label_vocab_path) id_label = {v: k for k, v in label_id.items()} pred_labels = [prob.argmax() for prob in pred_label_probs] pred_labels = [id_label[i] for i in pred_labels] pred_output = [id_label[prob.argmax()] + col_sep + str(prob.max()) for prob in pred_label_probs] logger.info("save infer label and prob result to: %s" % pred_save_path) save_predict_result(pred_output, ture_labels=None, pred_save_path=pred_save_path, data_set=data_set) if true_labels: # evaluate assert len(pred_labels) == len(true_labels) for label, prob in zip(true_labels, pred_label_probs): logger.debug('label_true:%s\tprob_label:%s\tprob:%s' % (label, id_label[prob.argmax()], prob.max())) print('total eval:') try: print(classification_report(true_labels, pred_labels)) print(confusion_matrix(true_labels, pred_labels)) except UnicodeEncodeError: true_labels_id = [label_id[i] for i in true_labels] pred_labels_id = [label_id[i] for i in pred_labels] print(classification_report(true_labels_id, pred_labels_id)) print(confusion_matrix(true_labels_id, pred_labels_id))