hidden_size=HIDDEN_SIZE,
seq_len=SEQ_LEN,
batch_size=BATCH_SIZE,
vocab_size=VOCAB_SIZE,
num_layers=NUM_LAYERS,
dp_keep_prob=DP_KEEP_PROB)
model.load_state_dict(torch.load(load_path, map_location='cpu'))
hidden = model.init_hidden()
model.eval()
#--------------- GENERATE SAMPLES
first_words = torch.LongTensor(BATCH_SIZE).random_(0, 10000)
# samples = model.generate(torch.zeros(BATCH_SIZE).to(torch.long), hidden, generated_seq_len=GENERATED_SEQ_LEN)
samples = model.generate(first_words, hidden, generated_seq_len=GENERATED_SEQ_LEN)
#-------------- CONVERTING TO WORDS
data_path = "/Users/mlizaire/Codes/IFT6135/HW2/assignment2/data/"
filename = os.path.join(data_path, "ptb.train.txt")
word_2_id, id_2_word = _build_vocab(filename)
sequences = []
print("THIS IS RNN")
for i in range(15):
word_sequence = []
id_sequence = np.array(torch.t(samples)[i])
for index in id_sequence:
word = id_2_word[int(index)]
word_sequence.append(word)
#toy
#model.load_state_dict(torch.load("RNN_SGD_model=RNN_optimizer=SGD_initial_lr=1.0_batch_size=128_seq_len=35_hidden_size=512_num_layers=2_dp_keep_prob=0.8_num_epochs=1_save_best_0/best_params.pt"))
model.eval()
#print(model.out_layer.weight.data)
#also indices
inputs = torch.from_numpy(
np.random.randint(1, high=1000, size=10).astype(np.int64))
hidden = model.init_hidden()
model.zero_grad()
hidden = repackage_hidden(hidden)
samples = model.generate(inputs, hidden, 35) #returns indices
samples = samples.transpose(0, 1)
filename = "data/ptb.train.txt"
def _read_words(filename):
with open(filename, "r") as f:
return f.read().replace("\n", "<eos>").split()
def _build_vocab(filename):
data = _read_words(filename)
counter = collections.Counter(data)
#
# GENERATE DATA
#
###############################################################################
samples_id_with_inputs = []
samples_id = []
samples_words_with_inputs = []
samples_words = []
inputs = torch.from_numpy(np.random.randint(0, 10000, 128).astype(np.int64)).contiguous().to(device)
hidden = model.init_hidden()[0]
hidden = hidden.to(device)
samples_all = model.generate(inputs, hidden, SEQ_LEN)
print(samples_all[:, :10])
for i in range(10):
# print(samples_all[:,i])
# print(samples_all[:,:10].T)
# print(samples_all[:,:10].T.tolist())
samples_id_with_inputs.append([inputs[i].tolist()] + samples_all[:, i].T.tolist())
samples_id.append(samples_all[:, i].T.tolist())
print(len(samples_id_with_inputs))
print(len(samples_id_with_inputs[0]))
# print(samples_id)
# print(samples_id.shape)
for s, sentence in enumerate(samples_id_with_inputs):
samples_words_with_inputs.append([])