I have the answer now. At the very beginning, I was confused with the hidden state and input state of the second lstm layer.
Thus, for stacked lstm with num_layers=2, we initialize the hidden states with the number of 2, since each lstm layer needs the initial hidden state, while the second lstm layer takes the output hidden state of the first lstm layer as its input.
And for the model containing individual lstm, since, for the above-stacked lstm model, each lstm layer has the initial hidden states being 0, thus, we should initialize the two individual lstms to both have zero hidden states.
In addition, I made a mistake to initialize the weight and bias values.
As a result, to make the above two methods have the same outputs, I use the following codes:
the first method:
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
torch.manual_seed(1)
lstm = nn.LSTM(3, 3,2) # Input dim is 3, output dim is 3
inputs = [torch.randn(1, 3) for _ in range(5)] # make a sequence of length 5
weight_ih_0=None
weight_hh_0=None
# bias_ih_0=None
# bias_hh_0=None
weight_ih_1=None
weight_hh_1=None
# bias_ih_1=None
# bias_hh_1=None
for name, param in lstm.named_parameters():
if 'bias' in name:
# print(f'bias {name} before init: {param}')
nn.init.constant_(param, 0.0)
# print(f'bias {name} after init: {param}')
elif 'weight' in name:
# print(f'weight {name} before init: {param}')
nn.init.xavier_normal_(param)
print(f'weight {name} after init: {param}')
for name, param in lstm.named_parameters():
if 'weight_ih_l0' in name:
weight_ih_0=param
if 'weight_hh_l0' in name:
weight_hh_0=param
if 'weight_ih_l1' in name:
weight_ih_1=param
if 'weight_hh_l1' in name:
weight_hh_1=param
print(f'inputs: {inputs}')
# initialize the hidden state.
hidden = (torch.zeros(2, 1, 3),
torch.zeros(2, 1, 3))
idx=0
for i in inputs:
print(f'idx: {idx}')
# print(f'i: {i}')
idx+=1
# Step through the sequence one element at a time.
# after each step, hidden contains the hidden
out, hidden = lstm(i.view(1, 1, -1), hidden)
print(out)
# print(hidden)
print("==========")
And the output is:
weight weight_ih_l0 after init: Parameter containing:
tensor([[ 0.6025, -0.1577, -0.0990],
[-0.5255, 0.4554, 0.4651],
[ 0.1428, 0.1414, -0.0291],
[ 0.1248, 0.3465, -0.5053],
[ 0.6295, -0.8635, -0.3394],
[ 0.1072, 0.0786, 0.3427],
[ 0.5352, -0.2032, 0.8816],
[ 0.3727, -0.1608, -0.6332],
[-0.3745, 0.1903, -0.1654],
[-0.0460, -0.2148, 0.7737],
[-0.1980, -0.8980, -0.3470],
[-0.1130, 0.6074, 0.1844]], requires_grad=True)
weight weight_hh_l0 after init: Parameter containing:
tensor([[-0.0719, -0.0122, 0.2626],
[ 0.3887, -0.3044, -0.4356],
[-0.8422, 0.2204, 0.1151],
[ 0.4171, 0.1116, -0.2114],
[ 0.2061, -0.3204, -0.0983],
[ 0.4791, -0.5683, -0.3928],
[-0.3196, -0.1726, -0.0732],
[-0.3058, -0.5667, -0.0211],
[-0.0832, -0.3168, 0.1241],
[-0.4197, 0.0525, 0.0741],
[ 0.3849, 0.0481, -0.3130],
[ 0.5788, 0.6312, -0.3627]], requires_grad=True)
weight weight_ih_l1 after init: Parameter containing:
tensor([[ 3.6955e-02, 7.1276e-02, -4.3073e-01],
[-5.2666e-01, 2.7323e-02, 1.2894e-01],
[ 3.7136e-01, 3.3969e-01, 1.9601e-01],
[ 3.5802e-01, -4.3600e-01, -1.7962e-01],
[ 8.3209e-01, 1.7189e-01, 2.2195e-01],
[-2.1302e-02, -1.6867e-01, -1.3460e-01],
[ 1.3446e-01, 1.7708e-01, -5.6676e-01],
[-2.3697e-01, -2.8254e-02, -2.2063e-01],
[-2.0928e-01, 3.4973e-01, 3.5858e-04],
[-5.0565e-01, -6.8619e-02, 3.7702e-01],
[-9.0796e-02, -1.7238e-01, 4.7868e-01],
[-1.1565e-01, -6.7956e-02, -2.1049e-01]], requires_grad=True)
weight weight_hh_l1 after init: Parameter containing:
tensor([[-0.3017, -0.0811, -0.6554],
[ 0.2665, -0.2052, -0.0577],
[ 0.5493, -0.5094, 0.2167],
[ 0.1210, -0.3868, -0.2293],
[-0.0991, 0.6744, -0.0114],
[-0.0343, -0.6136, 0.4856],
[ 0.0505, 0.3920, -0.1662],
[ 0.1163, -0.1296, 0.2505],
[-0.1373, -0.8803, -0.4666],
[-0.0230, -0.0346, -0.8451],
[ 0.2032, 0.1847, -0.0758],
[ 0.2533, 0.1532, 0.8224]], requires_grad=True)
inputs: [tensor([[1.5381, 1.4673, 1.5951]]), tensor([[-1.5279, 1.0156, -0.2020]]), tensor([[-1.2865, 0.8231, -0.6101]]), tensor([[-1.2960, -0.9434, 0.6684]]), tensor([[ 1.1628, -0.3229, 1.8782]])]
idx: 0
tensor([[[ 0.0374, -0.0085, -0.0240]]], grad_fn=<StackBackward>)
==========
idx: 1
tensor([[[ 0.0073, -0.0110, -0.0296]]], grad_fn=<StackBackward>)
==========
idx: 2
tensor([[[-0.0314, -0.0147, -0.0136]]], grad_fn=<StackBackward>)
==========
idx: 3
tensor([[[-0.0458, -0.0118, -0.0254]]], grad_fn=<StackBackward>)
==========
idx: 4
tensor([[[-0.0096, -0.0281, -0.0440]]], grad_fn=<StackBackward>)
==========
The second method:
torch.manual_seed(1)
lstm = nn.LSTM(3, 3,1) # Input dim is 3, output dim is 3
lstm2 = nn.LSTM(3, 3,1) # Input dim is 3, output dim is 3
inputs = [torch.randn(1, 3) for _ in range(5)] # make a sequence of length 5
print(f'inputs: {inputs}')
# initialize the hidden state.
hidden1 = (torch.zeros(1, 1, 3),
torch.zeros(1, 1, 3))
hidden2 = (torch.zeros(1, 1, 3),
torch.zeros(1, 1, 3))
for name, param in lstm.named_parameters():
if 'bias' in name:
# print(f'lstm bias {name} before init: {param}')
nn.init.constant_(param, 0.0)
# print(f'lstm bias {name} after init: {param}')
elif 'weight' in name:
# print(f'lstm weight {name} before init: {param}')
if 'weight_ih' in name:
lstm.weight_ih_l0.data=weight_ih_0
print(f'lstm {name} after init: {param}')
if 'weight_hh' in name:
lstm.weight_hh_l0.data=weight_hh_0
print(f'lstm {name} after init: {param}')
for name, param in lstm2.named_parameters():
if 'bias' in name:
# print(f'lstm2 bias {name} before init: {param}')
nn.init.constant_(param, 0.0)
# print(f'lstm2 bias {name} after init: {param}')
elif 'weight' in name:
# print(f'lstm2 weight {name} before init: {param}')
if 'weight_ih' in name:
lstm2.weight_ih_l0.data=weight_ih_1
print(f'lstm2 {name} after init: {param}')
if 'weight_hh' in name:
lstm2.weight_hh_l0.data=weight_hh_1
print(f'lstm2 {name} after init: {param}')
for name, param in lstm2.named_parameters():
if 'weight' in name:
# print(f'lstm2 weight {name} before init: {param}')
print(f'lstm2 {name} after init: {param}')
idx=0
for i in inputs:
print(f'idx: {idx}')
idx+=1
# Step through the sequence one element at a time.
# after each step, hidden contains the hidden
out, hidden1 = lstm(i.view(1, 1, -1), hidden1)
out, hidden2 = lstm2(out.view(1, 1, -1), hidden2)
print(out)
print("==========")
# print(hidden)
And the output is:
inputs: [tensor([[1.5381, 1.4673, 1.5951]]), tensor([[-1.5279, 1.0156, -0.2020]]), tensor([[-1.2865, 0.8231, -0.6101]]), tensor([[-1.2960, -0.9434, 0.6684]]), tensor([[ 1.1628, -0.3229, 1.8782]])]
lstm weight_ih_l0 after init: Parameter containing:
tensor([[ 0.6025, -0.1577, -0.0990],
[-0.5255, 0.4554, 0.4651],
[ 0.1428, 0.1414, -0.0291],
[ 0.1248, 0.3465, -0.5053],
[ 0.6295, -0.8635, -0.3394],
[ 0.1072, 0.0786, 0.3427],
[ 0.5352, -0.2032, 0.8816],
[ 0.3727, -0.1608, -0.6332],
[-0.3745, 0.1903, -0.1654],
[-0.0460, -0.2148, 0.7737],
[-0.1980, -0.8980, -0.3470],
[-0.1130, 0.6074, 0.1844]], requires_grad=True)
lstm weight_hh_l0 after init: Parameter containing:
tensor([[-0.0719, -0.0122, 0.2626],
[ 0.3887, -0.3044, -0.4356],
[-0.8422, 0.2204, 0.1151],
[ 0.4171, 0.1116, -0.2114],
[ 0.2061, -0.3204, -0.0983],
[ 0.4791, -0.5683, -0.3928],
[-0.3196, -0.1726, -0.0732],
[-0.3058, -0.5667, -0.0211],
[-0.0832, -0.3168, 0.1241],
[-0.4197, 0.0525, 0.0741],
[ 0.3849, 0.0481, -0.3130],
[ 0.5788, 0.6312, -0.3627]], requires_grad=True)
lstm2 weight_ih_l0 after init: Parameter containing:
tensor([[ 3.6955e-02, 7.1276e-02, -4.3073e-01],
[-5.2666e-01, 2.7323e-02, 1.2894e-01],
[ 3.7136e-01, 3.3969e-01, 1.9601e-01],
[ 3.5802e-01, -4.3600e-01, -1.7962e-01],
[ 8.3209e-01, 1.7189e-01, 2.2195e-01],
[-2.1302e-02, -1.6867e-01, -1.3460e-01],
[ 1.3446e-01, 1.7708e-01, -5.6676e-01],
[-2.3697e-01, -2.8254e-02, -2.2063e-01],
[-2.0928e-01, 3.4973e-01, 3.5858e-04],
[-5.0565e-01, -6.8619e-02, 3.7702e-01],
[-9.0796e-02, -1.7238e-01, 4.7868e-01],
[-1.1565e-01, -6.7956e-02, -2.1049e-01]], requires_grad=True)
lstm2 weight_hh_l0 after init: Parameter containing:
tensor([[-0.3017, -0.0811, -0.6554],
[ 0.2665, -0.2052, -0.0577],
[ 0.5493, -0.5094, 0.2167],
[ 0.1210, -0.3868, -0.2293],
[-0.0991, 0.6744, -0.0114],
[-0.0343, -0.6136, 0.4856],
[ 0.0505, 0.3920, -0.1662],
[ 0.1163, -0.1296, 0.2505],
[-0.1373, -0.8803, -0.4666],
[-0.0230, -0.0346, -0.8451],
[ 0.2032, 0.1847, -0.0758],
[ 0.2533, 0.1532, 0.8224]], requires_grad=True)
lstm2 weight_ih_l0 after init: Parameter containing:
tensor([[ 3.6955e-02, 7.1276e-02, -4.3073e-01],
[-5.2666e-01, 2.7323e-02, 1.2894e-01],
[ 3.7136e-01, 3.3969e-01, 1.9601e-01],
[ 3.5802e-01, -4.3600e-01, -1.7962e-01],
[ 8.3209e-01, 1.7189e-01, 2.2195e-01],
[-2.1302e-02, -1.6867e-01, -1.3460e-01],
[ 1.3446e-01, 1.7708e-01, -5.6676e-01],
[-2.3697e-01, -2.8254e-02, -2.2063e-01],
[-2.0928e-01, 3.4973e-01, 3.5858e-04],
[-5.0565e-01, -6.8619e-02, 3.7702e-01],
[-9.0796e-02, -1.7238e-01, 4.7868e-01],
[-1.1565e-01, -6.7956e-02, -2.1049e-01]], requires_grad=True)
lstm2 weight_hh_l0 after init: Parameter containing:
tensor([[-0.3017, -0.0811, -0.6554],
[ 0.2665, -0.2052, -0.0577],
[ 0.5493, -0.5094, 0.2167],
[ 0.1210, -0.3868, -0.2293],
[-0.0991, 0.6744, -0.0114],
[-0.0343, -0.6136, 0.4856],
[ 0.0505, 0.3920, -0.1662],
[ 0.1163, -0.1296, 0.2505],
[-0.1373, -0.8803, -0.4666],
[-0.0230, -0.0346, -0.8451],
[ 0.2032, 0.1847, -0.0758],
[ 0.2533, 0.1532, 0.8224]], requires_grad=True)
idx: 0
tensor([[[ 0.0374, -0.0085, -0.0240]]], grad_fn=<StackBackward>)
==========
idx: 1
tensor([[[ 0.0073, -0.0110, -0.0296]]], grad_fn=<StackBackward>)
==========
idx: 2
tensor([[[-0.0314, -0.0147, -0.0136]]], grad_fn=<StackBackward>)
==========
idx: 3
tensor([[[-0.0458, -0.0118, -0.0254]]], grad_fn=<StackBackward>)
==========
idx: 4
tensor([[[-0.0096, -0.0281, -0.0440]]], grad_fn=<StackBackward>)
==========