I am fairly new to machine learning. I learned to write this code from youtube tutorials but I keep getting this error
Traceback (most recent call last):
File "<input>", line 1, in <module>
File "/Applications/PyCharm.app/Contents/plugins/python/helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "/Applications/PyCharm.app/Contents/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/Users/aniket/Desktop/DeepLearning/PythonLearningPyCharm/CatVsDogs.py", line 109, in <module>
optimizer = optim.Adam(net.parameters(), lr=0.001) # tweaks the weights from what I understand
AttributeError: 'Net' object has no attribute 'parameters'
this is the Net class
class Net():
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(1,32,5)
self.conv2 = nn.Conv2d(32,64,5)
self.conv3 = nn.Conv2d(64,128,5)
self.to_linear = None
x = torch.randn(50,50).view(-1,1,50,50)
self.Conv2d_Linear_Link(x)
self.fc1 = nn.Linear(self.to_linear, 512)
self.fc2 = nn.Linear(512, 2)
def Conv2d_Linear_Link(self , x):
x = F.max_pool2d(F.relu(self.conv1(x)),(2,2))
x = F.max_pool2d(F.relu(self.conv2(x)),(2,2))
x = F.max_pool2d(F.relu(self.conv3(x)),(2,2))
if self.to_linear is None :
self.to_linear = x[0].shape[0]*x[0].shape[1]*x[0].shape[2]
return x
def forward(self, x):
x = self.Conv2d_Linear_Link(x)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.softmax(x, dim=1)
and this is the function train
def train():
for epoch in range(epochs):
for i in tqdm(range(0,len(X_train), batch)):
batch_x = train_X[i:i + batch].view(-1, 1, 50, 50)
batch_y = train_y[i:i + batch]
net.zero_grad() # i don't understand why we do this but we do we don't want the probabilites adding up
output = net(batch_x)
loss = loss_function(output, batch_y)
loss.backward()
optimizer.step()
print(loss)
and the optimizer and loss functions and data
optimizer = optim.Adam(net.parameters(), lr=0.001) # tweaks the weights from what I understand
loss_function = nn.MSELoss() # gives the loss
You're not subclassing nn.Module. It should look like this:
class Net(nn.Module):
def __init__(self):
super().__init__()
This allows your network to inherit all the properties of the nn.Module class, such as the parameters attribute.
You may have a spelling problem and you should look to Net which parameters has.
You need to import optim from torch
from torch import optim
Related
I am making a simple recurrent neural network architecture for CIFAR10 image classification. I am not interested not use pre-defined RNN class in PyTorch because i am implementing from scratch according to figure. I am getting input tensor errors in the same device. I am not sure whether my code is right or wrong. Any simple way to write FC layer without defining shape and hard coded parameters.
Figure
Code
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, output_size, num_classes):
super(RNN, self).__init__()
self.hidden_size = hidden_size
self.input_to_hidden = nn.Linear(in_features=input_size + hidden_size, out_features=output_size)
self.input_to_output = nn.Linear(in_features=input_size + hidden_size, out_features=output_size)
self.softmax = nn.LogSoftmax(dim=1)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, input_tensor):
combined = torch.cat((input_tensor, torch.zeros(input_tensor.size(0))), 1)
hidden = self.input_to_hidden(combined)
output = self.input_to_output(combined)
output = self.softmax(output)
return output, hidden
Trackback
Traceback (most recent call last):
File "/media/cvpr/CM_1/tutorials/rnn.py", line 81, in <module>
outputs = model(images)
File "/home/cvpr/anaconda3/envs/tutorials/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/cvpr/CM_1/tutorials/rnn.py", line 33, in forward
combined = torch.cat((input_tensor, torch.zeros(input_tensor.size(0))), 1)
RuntimeError: All input tensors must be on the same device. Received cuda:0 and cpu
You need to make sure the tensors are on the same device (cpu/gpu) before you are contacting them
you can add a device parameter to your class and use it:
class RNN(nn.Module):
def __init__(self, input_size, hidden_size, output_size, num_classes, device='cuda'):
super(RNN, self).__init__()
self.device = device
self.hidden_size = hidden_size
self.input_to_hidden = nn.Linear(in_features=input_size + hidden_size, out_features=output_size)
self.input_to_output = nn.Linear(in_features=input_size + hidden_size, out_features=output_size)
self.softmax = nn.LogSoftmax(dim=1)
self.fc = nn.Linear(hidden_size, num_classes)
def forward(self, input_tensor):
combined = torch.cat((input_tensor.to(device), torch.zeros(input_tensor.size(0), device=self.device)), 1)
hidden = self.input_to_hidden(combined)
output = self.input_to_output(combined)
output = self.softmax(output)
return output, hidden
I am working on cardiac CT data(axial, sagittal, coronal). I am using
the pre-trained model vgg_16. But got the following error. According
to this error, my dimension is not correct but according to my code,
I write things coreectly Can somebody guide me regarding this I try
to correct my code already but got the same error? Below is Error and
Code.
Traceback (most recent call last):
File "ct_pretrained.py", line 199, in <module>
loss, metric = train(model, train_loader, optimizer)
File "ct_pretrained.py", line 57, in train
output = model(axial, sagittal, coronal, emr)
File "/root/miniconda/lib/python3.8/site->packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/heart_ct/torch/models/test.py", line 38, in forward
axial_feature = self.axial_model(axial)
File "/root/miniconda/lib/python3.8/site->packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/miniconda/lib/python3.8/site->packages/torchvision/models/vgg.py", line 46, in forward
x = self.classifier(x)
File "/root/miniconda/lib/python3.8/site->packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/miniconda/lib/python3.8/site->packages/torch/nn/modules/linear.py", line 93, in forward
return F.linear(input, self.weight, self.bias)
File "/root/miniconda/lib/python3.8/site-> packages/torch/nn/functional.py", line 1690, in linear
ret = torch.addmm(bias, input, weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0
The code is:
import torch
import torch.nn as nn
from torchvision import models
__all__ = ['VGG']
class VGG(nn.Module):
def __init__(self, is_emr=False, mode='sum'):
super().__init__()
self.is_emr = is_emr
self.mode = mode
in_dim = 45
self.axial_model = models.vgg16(pretrained=True)
out_channels = self.axial_model.features[0].out_channels
self.axial_model.features[0] = nn.Conv2d(1, out_channels, kernel_size=7, stride=1, padding=0, bias=False)
self.axial_model.features[3] = nn.MaxPool2d(1)
num_ftrs = self.axial_model.classifier.in_features #error in this line of code
self.axial_model.classifier = nn.Linear(num_ftrs, 15)
self.sa_co_model = models.vgg16(pretrained=True)
self.sa_co_model.features[0] = nn.Conv2d(1, out_channels, kernel_size=7, stride=1, padding=(3,0), bias=False)
self.sa_co_model.features[3] = nn.MaxPool2d(1)
self.sa_co_model.classifier = nn.Linear(num_ftrs, 15)
if self.is_emr:
self.emr_model = EMRModel()
if self.mode == 'concat': in_dim = 90
self.classifier = Classifier(in_dim)
def forward(self, axial, sagittal, coronal, emr):
axial = axial[:,:,:-3,:-3]
sagittal = sagittal[:,:,:,:-3]
coronal = coronal[:,:,:,:-3]
axial_feature = self.axial_model(axial)
sagittal_feature = self.sa_co_model(sagittal)
coronal_feature = self.sa_co_model(coronal)
out = torch.cat([axial_feature, sagittal_feature, coronal_feature], dim=1)
if self.is_emr:
emr_feature = self.emr_model(emr)
if self.mode == 'concat':
out = torch.cat([out, emr_feature], dim=1)
elif self.mode == 'sum':
out += emr_feature
out = self.classifier(out)
return out
As the error suggests: there's a mismatch between the dimension of the computed features out of your backbones and the dimensions of the classification layer of self.classifier.
Try to inspect (in debug mode, or using print) the shape and dimensions of out and what is in_dim of the classifier layer.
I'm trying to build a semantic segmentation model with pytorch. However, I encounter this error and do not know how to fix it.
This is the model:
class SegmentationNN(pl.LightningModule):
def __init__(self, num_classes=23, hparams=None):
super().__init__()
self.hparams = hparams
self.model=models.alexnet(pretrained=True).features
self.conv=nn.Conv2d(256, 3, kernel_size=1)
self.upsample = nn.Upsample(size=(240,240))
def forward(self, x):
print('Input:', x.shape)
x = self.model(x)
print('After Alexnet convs:', x.shape)
x = self.conv(x)
print('After 1-conv:', x.shape)
x = self.upsample(x)
print('After upsampling:', x.shape)
return x
def training_step(self, batch, batch_idx):
images, targets = batch
# targets = targets.view(targets.size(0), -1)
out = self.forward(images)
loss_func = nn.CrossEntropyLoss(ignore_index=-1, reduction='mean')
loss = loss_func(out, targets.unsqueeze(0))
tensorboard_logs = {'loss': loss}
return {'loss': loss, 'log':tensorboard_logs}
def validation_step(self, batch, batch_idx):
images, targets = batch
# targets = targets.view(targets.size(0), -1)
out = self.forward(images)
loss_func = nn.CrossEntropyLoss(ignore_index=-1, reduction='mean')
loss = loss_func(out, targets.unsqueeze(0))
tensorboard_logs = {'loss': loss}
return {'loss': loss, 'log':tensorboard_logs}
def configure_optimizers(self):
optim = torch.optim.Adam(self.parameters(), lr=self.hparams['learning_rate'])
return optim
And this is the training and fit:
train_dataloader = DataLoader(train_data, batch_size=hparams['batch_size'])
val_dataloader = DataLoader(val_data, batch_size=hparams['batch_size'])
trainer = pl.Trainer(
max_epochs=50,
gpus=1 if torch.cuda.is_available() else None
)
pass
trainer.fit(model, train_dataloader, val_dataloader)
These are the sizes of the tensor after each layer:
Input: torch.Size([59, 3, 240, 240])
After Alexnet convs: torch.Size([59, 256, 6, 6])
After 1-conv: torch.Size([59, 3, 6, 6])
After upsampling: torch.Size([59, 3, 240, 240])
I am pretty a beginner with Pytorch and Pytorch Lightning so every advice would be apprreciated!
Can you delete the unsqueeze(0) part here : loss = loss_func(out, targets.unsqueeze(0))
I am trying to implement a NiN model. Basically trying to replicate code from d2l Here is my code.
import pandas as pd
import torch
from torch import nn
import torchmetrics
from torchvision import transforms
from torch.utils.data import DataLoader, random_split
import pytorch_lightning as pl
from torchvision.datasets import FashionMNIST
import wandb
from pytorch_lightning.loggers import WandbLogger
wandb.login()
## class definition
class Lightning_nin(pl.LightningModule):
def __init__(self):
super().__init__()
self.accuracy = torchmetrics.Accuracy(top_k=1)
self.model = nn.Sequential(
self.nin_block(1, 96, kernel_size=11, strides=4, padding=0),
nn.MaxPool2d(3, stride=2),
self.nin_block(96, 256, kernel_size=5, strides=1, padding=2),
nn.MaxPool2d(3, stride=2),
self.nin_block(256, 384, kernel_size=3, strides=1, padding=1),
nn.MaxPool2d(3, stride=2), nn.Dropout(0.5),
# There are 10 label classes
self.nin_block(384, 10, kernel_size=3, strides=1, padding=1),
nn.AdaptiveAvgPool2d((1, 1)),
# Transform the four-dimensional output into two-dimensional output with a
# shape of (batch size, 10)
nn.Flatten())
for layer in self.model:
if type(layer) == nn.Linear or type(layer) == nn.Conv2d:
nn.init.xavier_uniform_(layer.weight)
def nin_block(self,in_channels, out_channels, kernel_size, strides, padding):
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size, strides, padding),
nn.ReLU(), nn.Conv2d(out_channels, out_channels, kernel_size=1),
nn.ReLU(), nn.Conv2d(out_channels, out_channels, kernel_size=1),
nn.ReLU())
def forward(self, x):
x = self.model(x)
return x
def loss_fn(self,logits,y):
loss = nn.CrossEntropyLoss()
return loss(logits,y)
def training_step(self,train_batch,batch_idx):
X, y = train_batch
logits = self.forward(X)
loss = self.loss_fn(logits,y)
self.log('train_loss',loss)
m = nn.Softmax(dim=1)
output = m(logits)
self.log('train_acc',self.accuracy(output,y))
return loss
def validation_step(self,val_batch,batch_idx):
X,y = val_batch
logits = self.forward(X)
loss = self.loss_fn(logits,y)
self.log('test_loss',loss)
m = nn.Softmax(dim=1)
output = m(logits)
self.log('test_acc',self.accuracy(output,y))
def configure_optimizers(self):
optimizer = torch.optim.SGD(self.model.parameters(),lr= 0.1)
return optimizer
class Light_DataModule(pl.LightningDataModule):
def __init__(self,resize= None):
super().__init__()
if resize:
self.resize = resize
def setup(self, stage):
# transforms for images
trans = [transforms.ToTensor()]
if self.resize:
trans.insert(0, transforms.Resize(self.resize))
trans = transforms.Compose(trans)
# prepare transforms standard to MNIST
self.mnist_train = FashionMNIST(root="../data", train=True, download=True, transform=trans)
self.mnist_test = FashionMNIST(root="../data", train=False, download=True, transform=trans)
def train_dataloader(self):
return DataLoader(self.mnist_train, batch_size=128,shuffle=True,num_workers=4)
def val_dataloader(self):
return DataLoader(self.mnist_test, batch_size=128,num_workers=4)
## Train model
data_module = Light_DataModule(resize=224)
wandb_logger = WandbLogger(project="d2l",name ='NIN')
model = Lightning_nin()
trainer = pl.Trainer(logger=wandb_logger,max_epochs=4,gpus=1,progress_bar_refresh_rate =1)
trainer.fit(model, data_module)
wandb.finish()
After running the code I am only getting an accuracy of 0.1. Not sure where I am going wrong. I have been able to implement other CNN (like VGG) using the same template. Not sure where I am going wrong. The accuracy should be close to 0.9 after 10 epochs.
The kernel_size & strides are very big for the image size of 224. It will drastically reduce the information that is passed on to subsequent layers. Try reducing them. Also, VGG was a very carefully designed architecture.
import torch
import torch.nn as nn
from torch.autograd import Variable
import torchvision.models as models
class AlexSal(nn.Module):
def __init__(self):
super(AlexSal, self).__init__()
self.features = nn.Sequential(*list(torch.load('alexnet_places365.pth.tar').features.children())[:-2])
self.relu = nn.ReLU()
self.sigmoid = nn.Sigmoid()
self.conv6 = nn.Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
def forward(self, x):
x = self.relu(self.features(x))
x = self.sigmoid(self.conv6(x))
x = x.squeeze(1)
return x
model = AlexSal().cuda()
Traceback (most recent call last):
File "main.py", line 23, in <module>
model = AlexSal().cuda()
File "main.py", line 13, in __init__
self.features = nn.Sequential(*list(torch.load('alexnet_places365.pth.tar').features.children())[:-2])
AttributeError: 'dict' object has no attribute 'features'
I got this piece of code from internet , i downloaded alexnet_places365.pth.tar ,and when i am running this , it is showing the above error
It looks like torch.load('alexnet_places365.pth.tar') does not contain an object with a member features, but instead a state dict as described here.
I would suggest you print out the result of torch.load('alexnet_places365.pth.tar') and then look for an entry features.