Python chainer.links.LSTM Examples
The following are 30
code examples of chainer.links.LSTM().
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
chainer.links
, or try the search function
.
Example #1
Source File: model.py From chainer with MIT License | 6 votes |
def __init__(self, vocab_size, hidden_size, dropout_ratio, ignore_label): super(LSTMLanguageModel, self).__init__() with self.init_scope(): self.embed_word = L.EmbedID( vocab_size, hidden_size, initialW=initializers.Normal(1.0), ignore_label=ignore_label ) self.embed_img = L.Linear( hidden_size, initialW=initializers.Normal(0.01) ) self.lstm = L.LSTM(hidden_size, hidden_size) self.out_word = L.Linear( hidden_size, vocab_size, initialW=initializers.Normal(0.01) ) self.dropout_ratio = dropout_ratio
Example #2
Source File: model.py From pfio with MIT License | 6 votes |
def step(self, hx, cx, xs): """Batch of word tokens to word tokens and hidden LSTM states. Predict the next set of tokens given previous tokens. """ # Concatenate all input captions and pass them through the model in a # single pass caption_lens = [len(x) for x in xs] caption_sections = np.cumsum(caption_lens[:-1]) xs = F.concat(xs, axis=0) xs = self.embed_word(xs) xs = F.split_axis(xs, caption_sections, axis=0) hx, cx, ys = self.lstm(hx, cx, xs) ys = F.concat(ys, axis=0) ys = F.dropout(ys, self.dropout_ratio) ys = self.decode_caption(ys) return hx, cx, ys
Example #3
Source File: model.py From pfio with MIT License | 6 votes |
def __init__(self, vocab_size, hidden_size, dropout_ratio, ignore_label): super(LSTMLanguageModel, self).__init__() with self.init_scope(): self.embed_word = L.EmbedID( vocab_size, hidden_size, initialW=initializers.Normal(1.0), ignore_label=ignore_label ) self.embed_img = L.Linear( hidden_size, initialW=initializers.Normal(0.01) ) self.lstm = L.LSTM(hidden_size, hidden_size) self.out_word = L.Linear( hidden_size, vocab_size, initialW=initializers.Normal(0.01) ) self.dropout_ratio = dropout_ratio
Example #4
Source File: fsns.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, target_shape, num_labels, num_timesteps, uses_original_data=False, dropout_ratio=0.5, use_dropout=False): super(FSNSRecognitionNet, self).__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1, stride=2) self.bn0 = L.BatchNormalization(32) self.conv1 = L.Convolution2D(32, 32, 3, pad=1) self.bn1 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.rs2 = ResnetBlock(64, filter_increase=True, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.rs3 = ResnetBlock(128, filter_increase=True, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.fc1 = L.Linear(None, 256) self.lstm = L.LSTM(None, 256) self.classifier = L.Linear(None, 134) self._train = True self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.uses_original_data = uses_original_data self.vis_anchor = None self.use_dropout = use_dropout self.dropout_ratio = dropout_ratio
Example #5
Source File: fsns.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, target_shape, num_labels, num_timesteps, uses_original_data=False, dropout_ratio=0.5, use_dropout=False, use_blstm=False): super().__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(64, filter_increase=True, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.rs3 = ResnetBlock(128, filter_increase=True, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.fc1 = L.Linear(None, 256) self.lstm = L.LSTM(None, 256) if use_blstm: self.blstm = L.LSTM(None, 256) self.classifier = L.Linear(None, 134) self._train = True self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.uses_original_data = uses_original_data self.vis_anchor = None self.use_dropout = use_dropout self.dropout_ratio = dropout_ratio self.use_blstm = use_blstm
Example #6
Source File: fsns_resnet.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, target_shape, num_labels, num_timesteps, uses_original_data=False, dropout_ratio=0.5, use_dropout=False, use_blstm=False, use_attention=False): super().__init__() with self.init_scope(): self.resnet = FSNSResNetLayers('', 152) self.fc1 = L.Linear(None, 512) self.lstm = L.LSTM(None, 512) if use_blstm: self.blstm = L.LSTM(None, 512) self.classifier = L.Linear(None, 134) self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.uses_original_data = uses_original_data self.vis_anchor = None self.use_dropout = use_dropout self.dropout_ratio = dropout_ratio self.use_blstm = use_blstm self.use_attention = use_attention
Example #7
Source File: model.py From chainer with MIT License | 6 votes |
def step(self, hx, cx, xs): """Batch of word tokens to word tokens and hidden LSTM states. Predict the next set of tokens given previous tokens. """ # Concatenate all input captions and pass them through the model in a # single pass caption_lens = [len(x) for x in xs] caption_sections = np.cumsum(caption_lens[:-1]) xs = F.concat(xs, axis=0) xs = self.embed_word(xs) xs = F.split_axis(xs, caption_sections, axis=0) hx, cx, ys = self.lstm(hx, cx, xs) ys = F.concat(ys, axis=0) ys = F.dropout(ys, self.dropout_ratio) ys = self.decode_caption(ys) return hx, cx, ys
Example #8
Source File: svhn.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, dropout_ratio, num_timesteps, zoom=0.9): super(SVHNLocalizationNet, self).__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(48, filter_increase=True) self.rs3 = ResnetBlock(48) self.lstm = L.LSTM(None, 256) self.transform_2 = L.Linear(256, 6) # initialize transform self.transform_2.W.data[...] = 0 transform_bias = self.transform_2.b.data transform_bias[[0, 4]] = zoom transform_bias[[2, 5]] = 0 self.dropout_ratio = dropout_ratio self._train = True self.num_timesteps = num_timesteps self.vis_anchor = None self.width_encoding = None self.height_encoding = None
Example #9
Source File: svhn.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, target_shape, num_labels, num_timesteps, use_blstm=False): super(SVHNRecognitionNet, self).__init__() with self.init_scope(): self.data_bn = L.BatchNormalization(3) self.conv0 = L.Convolution2D(None, 32, 3, pad=1, stride=2) self.bn0 = L.BatchNormalization(32) self.conv1 = L.Convolution2D(32, 32, 3, pad=1) self.bn1 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(64, filter_increase=True) self.rs3 = ResnetBlock(128, filter_increase=True) self.fc1 = L.Linear(None, 256) self.lstm = L.LSTM(None, 256) if use_blstm: self.blstm = L.LSTM(None, 256) self.classifier = L.Linear(None, 11) self._train = True self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.vis_anchor = None self.use_blstm = use_blstm
Example #10
Source File: svhn.py From see with GNU General Public License v3.0 | 6 votes |
def __init__(self, target_shape, num_labels, num_timesteps): super(SVHNCTCRecognitionNet, self).__init__() with self.init_scope(): self.data_bn = L.BatchNormalization(3) self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(64, filter_increase=True) self.rs3 = ResnetBlock(128, filter_increase=True) self.fc1 = L.Linear(None, 256) self.lstm = L.LSTM(None, 256) self.classifier = L.Linear(None, 11) self._train = True self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.vis_anchor = None
Example #11
Source File: subword.py From vecto with Mozilla Public License 2.0 | 6 votes |
def __init__(self, vocab, vocab_ngram_tokens, n_units, n_units_char, dropout, subword): # dropout ratio, zero indicates no dropout super(RNN, self).__init__() with self.init_scope(): self.embed = L.EmbedID( len(vocab_ngram_tokens.lst_words) + 2, n_units_char, initialW=I.Uniform(1. / n_units_char)) # ngram tokens embedding plus 2 for OOV and end symbol. if 'lstm' in subword: self.mid = L.LSTM(n_units_char, n_units_char * 2) self.out = L.Linear(n_units_char * 2, n_units_char) # the feed-forward output layer if 'bilstm' in subword: self.mid_b = L.LSTM(n_units_char, n_units_char * 2) self.out_b = L.Linear(n_units_char * 2, n_units_char) self.n_ngram = vocab_ngram_tokens.metadata["max_gram"] - vocab_ngram_tokens.metadata["min_gram"] + 1 self.final_out = L.Linear(n_units * (self.n_ngram), n_units) self.dropout = dropout self.vocab = vocab self.vocab_ngram_tokens = vocab_ngram_tokens self.subword = subword
Example #12
Source File: rnn_network.py From turf-tipster with GNU Affero General Public License v3.0 | 6 votes |
def __init__(self, n_horses, n_jockeys): n_units_h, n_units_v, n_units_j, n_units_r, n_units_d = nn_nodes super(Turf_Tipster_NN, self).__init__() with self.init_scope(): # 馬モデルのステータス(モデルを保存できるようにParameterで保持しておく) self.vc = chainer.Parameter(np.zeros((n_horses, n_units_v), dtype=np.float32)) self.vh = chainer.Parameter(np.zeros((n_horses, n_units_v), dtype=np.float32)) # 馬モデルのレイヤー self.le = L.EmbedID(n_horses, n_horses) self.l1 = L.Linear(n_horses, n_units_h) self.l2 = L.LSTM(n_units_h, n_units_v) # 騎手モデルのレイヤー self.re = L.EmbedID(n_jockeys, n_jockeys) self.r1 = L.Linear(n_jockeys, n_units_j) # レースモデルのレイヤー self.m1 = L.EmbedID(11, 11) self.m2 = L.EmbedID(8, 8) self.m3 = L.EmbedID(4, 4) self.m4 = L.EmbedID(4, 4) self.j1 = L.Linear(n_units_v + n_units_j + 11 + 8 + 4 + 4, n_units_r) self.j2 = L.Linear(n_units_r, n_units_r) self.j3 = L.Linear(n_units_r, n_units_d) # 引数は(レースメタ情報, グリッド情報)で着順になっている
Example #13
Source File: basetest_pgt.py From chainerrl with MIT License | 6 votes |
def make_model(self, env): n_dim_obs = env.observation_space.low.size n_dim_action = env.action_space.low.size n_hidden_channels = 50 policy = Sequence( L.Linear(n_dim_obs, n_hidden_channels), F.relu, L.Linear(n_hidden_channels, n_hidden_channels), F.relu, L.LSTM(n_hidden_channels, n_hidden_channels), policies.FCGaussianPolicy( n_input_channels=n_hidden_channels, action_size=n_dim_action, min_action=env.action_space.low, max_action=env.action_space.high) ) q_func = q_function.FCLSTMSAQFunction( n_dim_obs=n_dim_obs, n_dim_action=n_dim_action, n_hidden_layers=2, n_hidden_channels=n_hidden_channels) return chainer.Chain(policy=policy, q_function=q_func)
Example #14
Source File: optnets.py From models with MIT License | 5 votes |
def __init__(self, n_units=20, n_classes=10, out_scale=0.1, do_preprocess=True): super(LSTMOptNet, self).__init__() with self.init_scope(): n_input = 2 if do_preprocess else 1 self.l1 = L.LSTM(n_input, 20, forget_bias_init=0) self.l2 = L.LSTM(20, 20, forget_bias_init=0) self.lout = L.Linear(20, 1) # self.ldirect = L.Linear(n_input, 1) self.do_preprocess = do_preprocess self.out_scale = out_scale
Example #15
Source File: context_models.py From context2vec with Apache License 2.0 | 5 votes |
def __init__(self, deep, gpu, word2index, in_units, hidden_units, out_units, loss_func, train, drop_ratio=0.0): n_vocab = len(word2index) l2r_embedding=L.EmbedID(n_vocab, in_units) r2l_embedding=L.EmbedID(n_vocab, in_units) if deep: super(BiLstmContext, self).__init__( l2r_embed=l2r_embedding, r2l_embed=r2l_embedding, loss_func=loss_func, l2r_1 = L.LSTM(in_units, hidden_units), r2l_1 = L.LSTM(in_units, hidden_units), l3 = L.Linear(2*hidden_units, 2*hidden_units), l4 = L.Linear(2*hidden_units, out_units), ) else: super(BiLstmContext, self).__init__( l2r_embed=l2r_embedding, r2l_embed=r2l_embedding, loss_func=loss_func, l2r_1 = L.LSTM(in_units, hidden_units), r2l_1 = L.LSTM(in_units, hidden_units), lp_l2r = L.Linear(hidden_units, int(out_units/2)), lp_r2l = L.Linear(hidden_units, int(out_units/2)) ) if gpu >=0: self.to_gpu() l2r_embedding.W.data = self.xp.random.normal(0, math.sqrt(1. / l2r_embedding.W.data.shape[0]), l2r_embedding.W.data.shape).astype(np.float32) r2l_embedding.W.data = self.xp.random.normal(0, math.sqrt(1. / r2l_embedding.W.data.shape[0]), r2l_embedding.W.data.shape).astype(np.float32) self.word2index = word2index self.train = train self.deep = deep self.drop_ratio = drop_ratio
Example #16
Source File: lstm.py From deel with MIT License | 5 votes |
def __init__(self, n_input_units=1000,n_vocab=100, n_units=100, train=True): super(RNNLM, self).__init__( inputVector= L.Linear(n_input_units, n_units), embed=L.EmbedID(n_vocab, n_units), l1=L.LSTM(n_units, n_units), l2=L.LSTM(n_units, n_units), l3=L.Linear(n_units, n_vocab), ) self.train = train
Example #17
Source File: ram.py From ram with MIT License | 5 votes |
def __init__( self, g_size=8, n_steps=6, n_scales=1, var=0.03, use_lstm=False ): d_glm = 128 d_core = 256 super(RAM, self).__init__( emb_l=L.Linear(2, d_glm), emb_x=L.Linear(g_size*g_size*n_scales, d_glm), fc_lg=L.Linear(d_glm, d_core), fc_xg=L.Linear(d_glm, d_core), fc_ha=L.Linear(d_core, 10), fc_hl=L.Linear(d_core, 2), fc_hb=L.Linear(d_core, 1), ) if use_lstm: self.add_link(name='core_lstm', link=L.LSTM(d_core, d_core)) else: self.add_link(name='core_hh', link=L.Linear(d_core, d_core)) self.add_link(name='core_gh', link=L.Linear(d_core, d_core)) self.use_lstm = use_lstm self.d_core = d_core self.g_size = g_size self.n_steps = n_steps self.n_scales = n_scales self.var = var
Example #18
Source File: lstm_text_localizer.py From kiss with GNU General Public License v3.0 | 5 votes |
def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) with self.init_scope(): self.lstm = L.LSTM(None, 1024) self.param_predictor = L.Linear(1024, 6) # params = self.param_predictor.b.data # params[...] = 0 # params[[0, 4]] = 0.8 # self.param_predictor.W.data[...] = 0
Example #19
Source File: text_recognizer.py From kiss with GNU General Public License v3.0 | 5 votes |
def __init__(self, num_chars, num_classes, **kwargs): super().__init__() with self.init_scope(): self.feature_extractor = ResNet(kwargs.pop('num_layers', 18)) # self.lstm = L.LSTM(None, 1024) self.classifier = L.Linear(None, num_classes) self.num_chars = num_chars chainer.global_config.user_text_recognition_grayscale_input = False
Example #20
Source File: dern.py From der-network with MIT License | 5 votes |
def __init__(self, vocab, args): def get_initialW_X(shape): return np.random.normal(0, (2.0/(sum(shape)))**0.5, shape).astype(np.float32) super(DERN, self).__init__( # Word Embedding embed=L.EmbedID(len(vocab), args.n_units), # bi-LSTMs f_LSTM=L.LSTM(args.n_units, args.n_units), # for article b_LSTM=L.LSTM(args.n_units, args.n_units), Q_f_LSTM=L.LSTM(args.n_units, args.n_units), # for query Q_b_LSTM=L.LSTM(args.n_units, args.n_units), # Matrices and vectors W_hd=L.Linear(4*args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, 4*args.n_units))), W_dm=L.Linear(args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, args.n_units))), m=L.Linear(args.n_units, 1, initialW=get_initialW_X((1, args.n_units))), W_hq=L.Linear(4 * args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, 4*args.n_units))), W_hu=L.Linear(4 * args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, 4*args.n_units))), W_dv=L.Linear(args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, args.n_units))), W_dx=L.Linear(args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, args.n_units))), W_dxQ=L.Linear(args.n_units, args.n_units, initialW=get_initialW_X((args.n_units, args.n_units))), b_v2=L.Linear(1, args.n_units, initialW=get_initialW_X((args.n_units, 1))) ) self.args = args self.n_vocab = len(vocab) self.n_units = args.n_units self.dropout_ratio = args.d_ratio self.PH_id = vocab["@placeholder"] self.eos_id = vocab["<eos>"] self.bos_id = vocab["<bos>"] self.boq_id = vocab["<boq>"] self.BOQ_tok_batch = self.xp.array([self.boq_id], dtype=np.int32) self.NULL_id = vocab["NULL_tok"] self.NULL_tok = self.xp.array(self.NULL_id, dtype=np.int32) self.initialize_additionally()
Example #21
Source File: ic_stn.py From see with GNU General Public License v3.0 | 5 votes |
def __init__(self, dropout_ratio, num_timesteps, num_refinement_steps, target_shape, zoom=0.9, do_parameter_refinement=False): super().__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.conv0_1 = L.Convolution2D(None, 32, 3, pad=1) self.bn0_1 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(48, filter_increase=True) self.rs3 = ResnetBlock(48) self.rs4 = ResnetBlock(32) self.rs5 = ResnetBlock(48, filter_increase=True) self.lstm = L.LSTM(None, 256) self.transform_2 = L.Linear(256, 6) self.refinement_transform = L.Linear(2352, 6) for transform_param_layer in [self.transform_2, self.refinement_transform]: # initialize transform transform_param_layer.W.data[...] = 0 transform_bias = transform_param_layer.b.data transform_bias[[0, 4]] = zoom transform_bias[[2, 5]] = 0 self.refinement_transform.b.data[[0, 4]] = 0.1 self.dropout_ratio = dropout_ratio self.num_timesteps = num_timesteps self.num_refinement_steps = num_refinement_steps self.target_shape = target_shape self.do_parameter_refinement = do_parameter_refinement self.vis_anchor = None
Example #22
Source File: fsns.py From see with GNU General Public License v3.0 | 5 votes |
def __init__(self, target_shape, num_labels, num_timesteps, uses_original_data=False, dropout_ratio=0.5, use_dropout=False, use_blstm=False, use_attention=False): super().__init__() with self.init_scope(): self.data_bn = L.BatchNormalization(3) self.conv0 = L.Convolution2D(None, 64, 7, stride=2, pad=3, nobias=True) self.bn0 = L.BatchNormalization(64) self.rs1_1 = ResnetBlock(64) self.rs1_2 = ResnetBlock(64) self.rs2_1 = ResnetBlock(128, filter_increase=True) self.rs2_2 = ResnetBlock(128) self.rs3_1 = ResnetBlock(256, filter_increase=True) self.rs3_2 = ResnetBlock(256) self.rs4_1 = ResnetBlock(512, filter_increase=True) self.rs4_2 = ResnetBlock(512) self.fc1 = L.Linear(None, 512) self.lstm = L.LSTM(None, 512) if use_blstm: self.blstm = L.LSTM(None, 512) if use_attention: self.transform_encoded_features = L.Linear(512, 512, nobias=True) self.transform_out_lstm_feature = L.Linear(512, 512, nobias=True) self.generate_attended_feat = L.Linear(512, 1) self.out_lstm = L.LSTM(512, 512) self.classifier = L.Linear(None, 134) self._train = True self.target_shape = target_shape self.num_labels = num_labels self.num_timesteps = num_timesteps self.uses_original_data = uses_original_data self.vis_anchor = None self.use_dropout = use_dropout self.dropout_ratio = dropout_ratio self.use_blstm = use_blstm self.use_attention = use_attention
Example #23
Source File: dern.py From der-network with MIT License | 5 votes |
def encode_tokens(self, x_datas, i2sD, train=True): # Embed, dropout, split into each token (batchsize=1) h0L = list(F.split_axis( F.dropout( self.embed(chainer.Variable(self.xp.array(x_datas, dtype=np.int32), volatile=not train)), ratio=self.dropout_ratio, train=train), len(x_datas), axis=0)) # Replace embedding with dynamic entity representation for i in i2sD.keys(): h0L[i] = self.W_dx(i2sD[i]) # LSTM. forward order forward_outL = [] self.f_LSTM.reset_state() for h0 in h0L: state = self.f_LSTM(h0) forward_outL.append(state) # LSTM. backward order backward_outL = [] self.b_LSTM.reset_state() for h0 in reversed(h0L): state = self.b_LSTM(h0) backward_outL.append(state) return forward_outL, backward_outL
Example #24
Source File: fsns.py From see with GNU General Public License v3.0 | 5 votes |
def __init__(self, dropout_ratio, num_timesteps, zoom=0.9, use_dropout=False): super(FSNSSingleSTNLocalizationNet, self).__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.rs2 = ResnetBlock(48, filter_increase=True, use_dropout=use_dropout, dropout_ratio=dropout_ratio) self.rs3 = ResnetBlock(48) # self.rs4 = ResnetBlock(16, filter_increase=True) self.lstm = L.LSTM(None, 256) self.transform_2 = L.LSTM(256, 6) self.dropout_ratio = dropout_ratio self.use_dropout = use_dropout self._train = True self.num_timesteps = num_timesteps # initialize transform # self.transform_2.W.data[...] = 0 # # transform_bias = self.transform_2.b.data # transform_bias[[0, 4]] = zoom # transform_bias[[2, 5]] = 0 self.visual_backprop = VisualBackprop() self.vis_anchor = None self.width_encoding = None self.height_encoding = None
Example #25
Source File: fsns.py From see with GNU General Public License v3.0 | 5 votes |
def __init__(self, dropout_factor, num_timesteps, zoom=0.9): super(FSNSMultipleSTNLocalizationNet, self).__init__() with self.init_scope(): self.conv0 = L.Convolution2D(None, 32, 3, pad=1) self.bn0 = L.BatchNormalization(32) self.rs1 = ResnetBlock(32) self.rs2 = ResnetBlock(48, filter_increase=True) self.rs3 = ResnetBlock(48) self.lstm = L.LSTM(None, 256) self.translation_transform = L.Linear(256, 6) self.rotation_transform = L.Linear(256, 6) self.transform_2 = L.LSTM(256, 6) self.dropout_factor = dropout_factor self._train = True self.num_timesteps = num_timesteps for transform in [self.translation_transform, self.rotation_transform]: transform_bias = transform.b.data transform_bias[[0, 4]] = zoom transform_bias[[2, 5]] = 0 transform.W.data[...] = 0 # self.transform_2.upward.b.data[...] = 0 # self.transform_2.upward.W.data[...] = 0 # self.transform_2.lateral.W.data[...] = 0 # self.transform.W.data[...] = 0 self.visual_backprop = VisualBackprop() self.vis_anchor = None
Example #26
Source File: train_a3c_ale.py From chainerrl with MIT License | 5 votes |
def __init__(self, n_actions): self.head = links.NIPSDQNHead() self.pi = policy.FCSoftmaxPolicy( self.head.n_output_channels, n_actions) self.v = v_function.FCVFunction(self.head.n_output_channels) self.lstm = L.LSTM(self.head.n_output_channels, self.head.n_output_channels) super().__init__(self.head, self.lstm, self.pi, self.v)
Example #27
Source File: train_ptb_custom_loop.py From chainer with MIT License | 5 votes |
def __init__(self, n_vocab, n_units): super(RNNForLMSlice, self).__init__() with self.init_scope(): self.embed = L.EmbedID(n_vocab, n_units) self.l1 = L.LSTM(n_units, n_units) self.l2 = L.LSTM(n_units, n_units) self.l3 = L.Linear(n_units, n_vocab) for param in self.params(): param.array[...] = np.random.uniform(-0.1, 0.1, param.shape)
Example #28
Source File: train_a3c_gym.py From chainerrl with MIT License | 5 votes |
def __init__(self, obs_size, action_size, hidden_size=200, lstm_size=128): self.pi_head = L.Linear(obs_size, hidden_size) self.v_head = L.Linear(obs_size, hidden_size) self.pi_lstm = L.LSTM(hidden_size, lstm_size) self.v_lstm = L.LSTM(hidden_size, lstm_size) self.pi = policies.FCGaussianPolicy(lstm_size, action_size) self.v = v_function.FCVFunction(lstm_size) super().__init__(self.pi_head, self.v_head, self.pi_lstm, self.v_lstm, self.pi, self.v)
Example #29
Source File: state_action_q_functions.py From chainerrl with MIT License | 5 votes |
def __init__(self, n_dim_obs, n_dim_action, n_hidden_channels, n_hidden_layers, nonlinearity=F.relu, last_wscale=1.): self.n_input_channels = n_dim_obs + n_dim_action self.n_hidden_layers = n_hidden_layers self.n_hidden_channels = n_hidden_channels self.nonlinearity = nonlinearity super().__init__() with self.init_scope(): self.fc = MLP(self.n_input_channels, n_hidden_channels, [self.n_hidden_channels] * self.n_hidden_layers, nonlinearity=nonlinearity, ) self.lstm = L.LSTM(n_hidden_channels, n_hidden_channels) self.out = L.Linear(n_hidden_channels, 1, initialW=LeCunNormal(last_wscale))
Example #30
Source File: state_q_functions.py From chainerrl with MIT License | 5 votes |
def __init__(self, n_dim_obs, n_dim_action, n_hidden_channels, n_hidden_layers): self.n_input_channels = n_dim_obs self.n_hidden_layers = n_hidden_layers self.n_hidden_channels = n_hidden_channels self.state_stack = [] super().__init__() with self.init_scope(): self.fc = MLP(in_size=self.n_input_channels, out_size=n_hidden_channels, hidden_sizes=[self.n_hidden_channels] * self.n_hidden_layers) self.lstm = L.LSTM(n_hidden_channels, n_hidden_channels) self.out = L.Linear(n_hidden_channels, n_dim_action)