我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用chainer.serializers.load_hdf5()。
def load_model(dirname): model_filename = dirname + "/model.hdf5" param_filename = dirname + "/params.json" if os.path.isfile(param_filename): print("loading {} ...".format(param_filename)) with open(param_filename, "r") as f: try: params = json.load(f) except Exception as e: raise Exception("could not load {}".format(param_filename)) model = seq2seq(**params) if os.path.isfile(model_filename): print("loading {} ...".format(model_filename)) serializers.load_hdf5(model_filename, model) return model else: return None
def load_model(dirname): model_filename = dirname + "/model.hdf5" param_filename = dirname + "/params.json" if os.path.isfile(param_filename): print("loading {} ...".format(param_filename)) with open(param_filename, "r") as f: try: params = json.load(f) except Exception as e: raise Exception("could not load {}".format(param_filename)) qrnn = RNNModel(**params) if os.path.isfile(model_filename): print("loading {} ...".format(model_filename)) serializers.load_hdf5(model_filename, qrnn) return qrnn else: return None
def load(self): filename = "fc_value.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.fc_value) print "model fc_value loaded successfully." filename = "fc_advantage.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.fc_advantage) print "model fc_advantage loaded successfully." filename = "fc_value.optimizer" if os.path.isfile(filename): serializers.load_hdf5(filename, self.optimizer_fc_value) print "optimizer fc_value loaded successfully." filename = "fc_advantage.optimizer" if os.path.isfile(filename): serializers.load_hdf5(filename, self.optimizer_fc_advantage) print "optimizer fc_advantage loaded successfully."
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = convert_word_list(l.split(), word_vocab) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit), phrase_vocab, semiterminal_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) embed_cache = {} trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = to_vram_words(convert_word_list(l.split(), word_vocab)) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit, embed_cache), phrase_vocab, semiterminal_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semi_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if USE_GPU: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = convert_word_list(l.split(), word_vocab) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit), phrase_vocab, semi_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) embed_cache = {} parser.reset() trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = to_vram_words(convert_word_list(l.split(), word_vocab)) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit, embed_cache), phrase_vocab, semiterminal_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = convert_word_list(l.split(), word_vocab) tree = combine_xbar( restore_labels( parser.forward_test(word_list, args.unary_limit), phrase_vocab, semiterminal_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semi_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if USE_GPU: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = convert_word_list(l.split(), word_vocab) tree = restore_labels( parser.forward(word_list, None, args.unary_limit), phrase_vocab, semi_vocab ) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semi_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = convert_word_list(l.split(), word_vocab) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit), phrase_vocab, semi_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(args): trace('loading model ...') word_vocab = Vocabulary.load(args.model + '.words') phrase_vocab = Vocabulary.load(args.model + '.phrases') semiterminal_vocab = Vocabulary.load(args.model + '.semiterminals') parser = Parser.load_spec(args.model + '.spec') if args.use_gpu: parser.to_gpu() serializers.load_hdf5(args.model + '.weights', parser) trace('generating parse trees ...') with open(args.source) as fp: for l in fp: word_list = to_vram_words(convert_word_list(l.split(), word_vocab)) tree = combine_xbar( restore_labels( parser.forward(word_list, None, args.unary_limit), phrase_vocab, semiterminal_vocab)) print('( ' + tree_to_string(tree) + ' )') trace('finished.')
def test(model, test_data, vocab, inv_vocab, modelfile_to_load, params): print('Testing ...') print('Beam size: {}'.format(params.beam_size)) print('print output to file:', out_test_filename) serializers.load_hdf5(modelfile_to_load, model) batch_test = utils_seq2seq.gen_batch_test(test_data, args.feature, 1, vocab, xp) output_file = open(out_test_filename, mode='w') for vid_batch, caption_batch, id_batch in batch_test: output = predict(model, params, vocab, inv_vocab, vid_batch, batch_size=1, beam_size=params.beam_size) print('%s %s' % (id_batch[0], output)) output_file.write(id_batch[0] + '\t' + output + '\n') output_file.close() utils_coco.convert(out_test_filename, eval_test_filename) eval_coco.eval_coco(args.cocotest, eval_test_filename)
def test_batch(model, test_data, vocab, inv_vocab, modelfile_to_load): print('Testing (beam size = 1)...') print('print output to file: {}'.format(out_test_filename)) serializers.load_hdf5(modelfile_to_load, model) batch_test = \ utils_seq2seq.gen_batch_test(test_data, args.feature, params.batch_size_val, vocab, xp) caption_out = [] output_file = open(out_test_filename, mode='w') for vid_batch_test, caption_batch_test, id_batch_test in batch_test: output_test = forward(model, params, vocab, inv_vocab, vid_batch_test, caption_batch_test, 'test-on-train', args.batchsizeval) for ii in range(args.batchsizeval): caption_out.append({'image_id': id_batch_test[ii], 'caption': output_test[ii]}) print('%s %s' % (id_batch_test[ii], output_test[ii])) output_file.write(id_batch_test[ii] + '\t' + output_test[ii] + '\n') output_file.close() with open(eval_test_filename, mode='w') as f: json.dump(caption_out, f) eval_coco.eval_coco(args.cocotest, eval_test_filename)
def __init__(self, x_data, y_data, feature, initmodel, gpu = -1): self.N = 5000 self.N_test = 766 self.total = self.N + self.N_test self.emotion_weight = {0: self.total / 716, 1: self.total / 325, 2: self.total / 1383, 3: self.total / 743, 4: self.total / 2066, 5: self.total / 74, 6: self.total / 17, 7: self.total / 35, 8: self.total / 404, 9: self.total / 3} self.x_data = x_data.astype(np.float32) self.x_data = np.vstack((self.x_data, self.x_data)) self.y_data = y_data.astype(np.int32) self.y_data = np.vstack((self.y_data, self.y_data)) if feature == "IS2009": self.input_layer = 384 elif feature == "IS2010": self.input_layer = 1582 self.n_units = 256 self.output_layer = 10 self.model = L.Classifier(net.EmotionRecognitionVoice(self.input_layer, self.n_units, self.output_layer)) self.gpu = gpu self.__set_cpu_or_gpu() self.emotion = {0: "Anger", 1: "Happiness", 2: "Excited", 3: "Sadness", 4: "Frustration", 5: "Fear", 6: "Surprise", 7: "Other", 8: "Neutral state", 9: "Disgust"} # Init/Resume serializers.load_hdf5(initmodel, self.model)
def load(self): dir = "model" filename = dir + "/bddqn_shared_fc.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.shared_fc) print "model shared_fc loaded successfully." filename = dir + "/bddqn_head_fc.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.head_fc) print "model head_fc loaded successfully." filename = dir + "/bddqn_shared_fc.optimizer" if os.path.isfile(filename): serializers.load_hdf5(filename, self.optimizer_shared_fc) print "optimizer shared_fc loaded successfully." filename = dir + "/bddqn_head_fc.optimizer" if os.path.isfile(filename): serializers.load_hdf5(filename, self.optimizer_head_fc) print "optimizer head_fc loaded successfully."
def predict(modelfn, model_vargs, data, batchsize=128, gpu=0): assert gpu >= 0, "CPU support not yet implemented" model = ResNet(**model_vargs) serializers.load_hdf5(modelfn, model) model.to_gpu() N = data.shape[0] prediction = np.zeros(N, dtype='int') for i in range(0, N, batchsize): x_batch = data[i:i+batchsize] x_var = Variable(cuda.to_gpu(x_batch)) prediction[i:i+batchsize] = cuda.to_cpu(model.predict(x_var)) if N % batchsize != 0: x_batch = data[N - N % batchsize:] x_var = Variable(cuda.to_gpu(x_batch)) prediction[N - N % batchsize:] = cuda.to_cpu(model.predict(x_var)) return prediction
def load(self): filename = "conv.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.conv) print "convolutional network loaded." if self.fcl_eliminated is False: filename = "fc.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.fc) print "fully-connected network loaded."
def load_model(self, model_filename): """Load a network model form a file """ serializers.load_hdf5(model_filename, self.model) copy_param.copy_param(target_link=self.model, source_link=self.shared_model) opt_filename = model_filename + '.opt' if os.path.exists(opt_filename): print('WARNING: {0} was not found, so loaded only a model'.format( opt_filename)) serializers.load_hdf5(model_filename + '.opt', self.optimizer)
def load(self, filename): if os.path.isfile(filename): print("Loading {} ...".format(filename)) serializers.load_hdf5(filename, self) return True return False
def load(self): filename = "fc.model" if os.path.isfile(filename): serializers.load_hdf5(filename, self.fc) print "model loaded successfully." filename = "fc.optimizer" if os.path.isfile(filename): serializers.load_hdf5(filename, self.optimizer_fc) print "optimizer loaded successfully."
def LoadFineTnModel(self, folder, epoch, batch): print('Loading model') serializers.load_hdf5('{}/network_epoch{}_batch{}.model'.format(folder, epoch, batch), self.Networks[0]) self.Networks[0].finetune_network() return
def LoadResumeModel(self, folder, epoch, batch): print('Loading model') serializers.load_hdf5('{}/network_epoch{}_batch{}.model'.format(folder, epoch, batch), self.Networks[0]) return
def LoadTraining(self, folder, epoch, batch): print('Loading optimizer') serializers.load_hdf5('{}/network_epoch{}_batch{}.state'.format(folder, epoch, batch), self.Optimizer) return
def __init__(self, net_size, model_filename, optimizer_filename): """ Create the underlying neural network model """ self.model = L.Classifier(BaseNetwork(net_size)) if (model_filename != ""): serializers.load_hdf5(model_filename, self.model) """ Create the underlying optimizer """ self.optimizer = optimizers.Adam() self.optimizer.setup(self.model) if (optimizer_filename != ""): serializers.load_hdf5(optimizer_filename, self.optimizer)
def load_state(self,path,epoch): print "==> loading state %s epoch %s"%(path,epoch) serializers.load_hdf5('./states/%s/net_model_classifier_%s.h5'%(path,epoch), self.network) return int(epoch)
def load_state(self,path,epoch): print "==> loading state %s epoch %s"%(path,epoch) serializers.load_hdf5('./states/%s/net_model_enc_%s.h5'%(path,epoch), self.enc) serializers.load_hdf5('./states/%s/net_model_dec_%s.h5'%(path,epoch), self.dec) return int(epoch)
def load(self, filename): if os.path.isfile(filename): print("loading {} ...".format(filename)) serializers.load_hdf5(filename, self) else: print(filename, "not found.")
