관심있는것들

unlike Language model we use only last output and put it into softmax to predict what kind of language is it we first extract ascii code and then we feed them to embedding matrix. def str2ascii_arr(msg): arr = [ord(c) for c in msg] return arr, len(arr) # pad sequences and sort the tensor def pad_sequences(vectorized_seqs, seq_lengths): seq_tensor = torch.zeros((len(vectorized_seqs), seq_lengths...

h = [1, 0, 0, 0] e = [0, 1, 0, 0] l = [0, 0, 1, 0] o = [0, 0, 0, 1] # One cell RNN input_dim (4) -> output_dim (2). sequence: 5 cell = nn.RNN(input_size=4, hidden_size=2, batch_first=True) # (num_layers * num_directions, batch, hidden_size) whether batch_first=True or False hidden = torch.randn(1, 1, 2) # Propagate input through RNN # Input: (batch, seq_len, input_size) when batch_first=True inp..

convolution use kernel matrix(filter) as weight parameter (keep changes as training goes on) with RGB (depth =3 ) picture we use kernel matrix depth 3 we can have mutiple kernel matrix and create depth of activation maps (feature maps) 28 comes from 5*5 , 6 comes from using 6 filters and all fiters have same depth as input max pooling class Net(nn.Module): def __init__(self): super(Net, self).__..

pytorch basic pattern 1. Design your model using class with Variables 2. Construct loss and optimzier (select form Pytorch API) 3. Training Cycle (1.forward , 2.backward , 3.update) Linear regression import torch.nn.functional from torch import tensor from torch import nn x_data = tensor([[1.0],[2.0],[3.0]]) y_data = tensor([[2.0],[4.0],[6.0]]) class Model(nn.Module): def __init__(self): super(M..