I need to save configuration file of the bert model with CNN. I will this file to visualize bert. so any suggestion to do that?
my model:
class MixModel(nn.Module):
def __init__(self,pre_trained='bert-base-uncased'):
super().__init__()
config = BertConfig.from_pretrained('bert-base-uncased', output_hidden_states=True)
self.bert = BertModel.from_pretrained('bert-base-uncased',config=config)
self.hidden_size = self.bert.config.hidden_size
self.conv = nn.Conv1d(in_channels=3072, out_channels=256, kernel_size=5, stride=1)
self.relu = nn.ReLU()
self.pool = nn.MaxPool1d(kernel_size= 64- 5 + 1)
self.dropout = nn.Dropout(0.3)
self.flat=nn.Flatten()
self.clf1 = nn.Linear(256,256)
self.clf2= nn.Linear(256,6)
def forward(self,inputs, mask , labels):
inputs=torch.tensor(inputs)
mask=torch.tensor(mask)
labels=torch.tensor(labels)
x = self.bert(input_ids=inputs,attention_mask=mask, return_dict= True)
x = self.conv(x)
x = self.relu(x)
x = self.pool(x)
x = self.dropout(x)
x = self.flat(x)
x = self.clf1(x)
x = self.clf2(x)
return x
Note That: save_pretrained() function can't work with fine-tuned bert model with CNN
class MixModel(nn.Module):
def __init__(self,pre_trained='bert-base-uncased'):
super().__init__()
config = BertConfig.from_pretrained('bert-base-uncased', output_hidden_states=True)
self.bert = BertModel.from_pretrained('bert-base-uncased',config=config)
self.hidden_size = self.bert.config.hidden_size
self.conv = nn.Conv1d(in_channels=3072, out_channels=256, kernel_size=5, stride=1)
self.relu = nn.ReLU()
self.pool = nn.MaxPool1d(kernel_size= 64- 5 + 1)
self.dropout = nn.Dropout(0.3)
self.flat=nn.Flatten()
self.clf1 = nn.Linear(256,256)
self.clf2= nn.Linear(256,6)
def forward(self,inputs, mask , labels):
inputs=torch.tensor(inputs)
mask=torch.tensor(mask)
labels=torch.tensor(labels)
x = self.bert(input_ids=inputs,attention_mask=mask, return_dict= True)
x = self.conv(x)
x = self.relu(x)
x = self.pool(x)
x = self.dropout(x)
x = self.flat(x)
x = self.clf1(x)
x = self.clf2(x)
return x
I want to save model,weights and config file for my model after training. after searching I found that model.save_pretrained function is good solution for me but I got an error that model called mixmodel has no function called save_pretrained
so how can I save config file for my model mixmodel?
I think that "state_dict" is what you need.
There's good tutorial for PyTorch in the documentation
https://pytorch.org/tutorials/beginner/saving_loading_models.html
I am using the following pre-trained resnet18 code to make a classification based on some input images.
The code is working properly with RGB images, but I want to make the needed changes to let it accept grey images (1 channel images).
I modified part of the code as following:
self.conv1 = nn.Conv2d(1, self.inplanes, kernel_size=7, stride=2, padding=3,
bias=False)
but I got the following error:
RuntimeError: Error(s) in loading state_dict for ResNet:
size mismatch for conv1.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from
checkpoint, the shape in current model is torch.Size([64, 1, 7, 7]).
Can you tell me please how I can solve this problem?
Thanks in advance.
Here is the code:
import torch.nn as nn
import torch.utils.model_zoo as model_zoo
from torch.utils.model_zoo import load_url as load_state_dict_from_url
# from .utils import load_state_dict_from_url
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
'wide_resnet50_2', 'wide_resnet101_2']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, groups=groups, bias=False, dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(BasicBlock, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError('BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(Bottleneck, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.)) * groups
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
groups=1, width_per_group=64, replace_stride_with_dilation=None,
norm_layer=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.output_dim = num_classes
print('Output layer dim = ' + str(self.output_dim))
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
dilate=replace_stride_with_dilation[0])
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
dilate=replace_stride_with_dilation[1])
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
dilate=replace_stride_with_dilation[2])
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, self.output_dim)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
norm_layer = self._norm_layer
downsample = None
previous_dilation = self.dilation
if dilate:
self.dilation *= stride
stride = 1
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
norm_layer(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation, norm_layer))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, dilation=self.dilation,
norm_layer=norm_layer))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.reshape(x.size(0), -1)
x = self.fc(x)
return x
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
model = ResNet(block, layers, **kwargs)
if pretrained:
state_dict = load_state_dict_from_url(model_urls[arch],
progress=progress)
# print(state_dict.keys())
# print(model.fc.weight)
for key in kwargs:
if key == 'num_classes':
num_classes = kwargs[key]
if num_classes != 1000:
state_dict['fc.weight'] = nn.init.xavier_normal_(model.fc.weight, gain=1)
state_dict['fc.bias'] = nn.init.constant_(model.fc.bias, val=0)
model.load_state_dict(state_dict)
return model
I have implemented an autoencoder in Pytorch and wish to extract the representations (output) from a specified encoding layer. This setup is similar to making predictions using sub-models that we used to have in Keras.
However, implementing something similar in Pytorch looks a bit challenging. I tried forward hooks as explained in How to get the output from a specific layer from a PyTorch model? and https://pytorch.org/tutorials/beginner/former_torchies/nnft_tutorial.html but to no avail.
Could you help me getting outputs from a specific layer?
I have attached my code below:
class Autoencoder(torch.nn.Module):
# Now defining the encoding and decoding layers.
def __init__(self):
super().__init__()
self.enc1 = torch.nn.Linear(in_features = 784, out_features = 256)
self.enc2 = torch.nn.Linear(in_features = 256, out_features = 128)
self.enc3 = torch.nn.Linear(in_features = 128, out_features = 64)
self.enc4 = torch.nn.Linear(in_features = 64, out_features = 32)
self.enc5 = torch.nn.Linear(in_features = 32, out_features = 16)
self.dec1 = torch.nn.Linear(in_features = 16, out_features = 32)
self.dec2 = torch.nn.Linear(in_features = 32, out_features = 64)
self.dec3 = torch.nn.Linear(in_features = 64, out_features = 128)
self.dec4 = torch.nn.Linear(in_features = 128, out_features = 256)
self.dec5 = torch.nn.Linear(in_features = 256, out_features = 784)
# Now defining the forward propagation step
def forward(self,x):
x = F.relu(self.enc1(x))
x = F.relu(self.enc2(x))
x = F.relu(self.enc3(x))
x = F.relu(self.enc4(x))
x = F.relu(self.enc5(x))
x = F.relu(self.dec1(x))
x = F.relu(self.dec2(x))
x = F.relu(self.dec3(x))
x = F.relu(self.dec4(x))
x = F.relu(self.dec5(x))
return x
autoencoder_network = Autoencoder()
I have to take the output from encoder layers marked enc1, enc2 .., enc5.
The simplest way is to explicitly return the activations you need:
def forward(self,x):
e1 = F.relu(self.enc1(x))
e2 = F.relu(self.enc2(e1))
e3 = F.relu(self.enc3(e2))
e4 = F.relu(self.enc4(e3))
e5 = F.relu(self.enc5(e4))
x = F.relu(self.dec1(e5))
x = F.relu(self.dec2(x))
x = F.relu(self.dec3(x))
x = F.relu(self.dec4(x))
x = F.relu(self.dec5(x))
return x, e1, e2, e3, e4, e5
You can define a global dictionary, like activations = {}, then in the forward function just assign values to it, like activations['enc1'] = x.clone().detach() and so on.
i have this model:
class model(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(in_channels=12,out_channels=64,kernel_size=3,stride= 1,padding=1)
# self.conv2 = nn.Conv2d(in_channels=64,out_channels=64,kernel_size=3,stride= 1,padding=1)
self.fc1 = nn.Linear(24576, 128)
self.bn = nn.BatchNorm1d(128)
self.dropout1 = nn.Dropout2d(0.5)
self.fc2 = nn.Linear(128, 10)
self.fc3 = nn.Linear(10, 3)
def forward(self, x):
x = F.relu(self.conv1(x))
# x = F.relu(self.conv2(x))
x = F.max_pool2d(x, (2,2))
# print(x.shape)
x = x.view(-1,24576)
x = self.bn(F.relu(self.fc1(x)))
x = self.dropout1(x)
embeding_stage = F.relu(self.fc2(x))
x = self.fc3(embeding_stage)
return x
and i want to save the embeding_stage layer like i save the model here:
model = model()
torch.save(model.state_dict(), 'C:\project\count_speakers\model_pytorch.h5')
thanks,
Ayal
I'm not sure I understand what you mean with "save the embedding_stage layer" but if you want to save fc2 or fc3 or something, then you can do that with torch.save().
Ex: to save fc3: torch.save(model.fc3),'C:\...\fc3.pt')
Edit:
Op wants to have the output of the embedding_stage.
You can do that in several ways:
load your model with model.load_state_dict(torch.load('C:\...\model_pytorch.h5'))
then model = nn.Sequential(*list(model.children())[:-1]). The output of model is the embeding_stage.
make a Model2(nn.Module), exactly the same as your first Model(), but replace return x in def forward(self, x): with return embeding_stage. Then load the state of your first model into your second model like this: model2.load_state_dict(torch.load('C:\...\model_pytorch.h5'))
Like this fc3 will be loaded, but not used. The output of model2(x) will be the embeding_stage.