The new notebook is giving some error:
in forward(self, xb)
10 out = xb.view(xb.size(0), -1)
11 # Get intermediate outputs using hidden layer
—> 12 out = self.linear1(xb)
13 # Apply activation function
14 out = F.relu(out)
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in call(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
–> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/linear.py in forward(self, input)
86 def forward(self, input):
—> 87 return F.linear(input, self.weight, self.bias)
89 def extra_repr(self):
/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py in linear(input, weight, bias)
1610 ret = torch.addmm(bias, input, weight.t())
-> 1612 output = input.matmul(weight.t())
1613 if bias is not None:
1614 output += bias
RuntimeError: size mismatch, m1: [24576 x 32], m2: [3072 x 500] at /opt/conda/conda-bld/pytorch_1587428398394/work/aten/src/THC/generic/THCTensorMathBlas.cu:283
Whats your model architecture?
There’s some problem with input sizes.
Generally when you get a mismatch error all you have to care about is b = c
[a x b] which is
[batch size x in features]
[c x d] which is
[in features x out features]
Thanks. I restarted and the problem seems to have gone away. Thanks for your reply.
Here is my attempt for assignment 3: Assignment 3 Notebook. I have tried different architectures(3,4,5 layer) but the test accuracy is around 50%. Its like the model don’t want learn anymore.
Hello guys, just want to ask a silly question how do i get the
DATASET_URL from kaggle ? Because what I normal did is open a notebook in kaggle .
Can anyone help ahha
Here is the link to my assignment 3.
I tried adding more hidden layers and tried different learning rates. I could not get beyond 52%. The more epochs I gave, the more it stayed constant. So I don’t think increasing epoch will help here.
Please check and provide feedback if any.
Here is a link: https://medium.com/analytics-vidhya/how-to-fetch-kaggle-datasets-into-google-colab-ea682569851a. I am assuming you want to use Kaggle data in Colab.
Alright, thanks ya. I guess is the same thing using jovian.ml notebook
Using Kaggle, I could not download the dataset at all, I don’t know how to go around this step
dataset = CIFAR10(root=‘data/’, download=True, transform=ToTensor())
test_dataset = CIFAR10(root=‘data/’, train=False, transform=ToTensor())
They failed again and again.
Here’s the link to my work!
Finally, by linking google account to Kaggle and add the cloudstorage and ml functions, the code works now.
Find my notebook
Coudn’t get past 56% accuracy.
Will try tuning more.
A post was merged into an existing topic: Share your work : June 1 - June 7
Hi guys, check out my assignment:
I have tried with to create two models with different architectures, the first one gives an accuracy of appx 40% and second model with 3 convulational layers added gives me an accuracy of 70%
Now I am working on my blog. Stay tuned
Here is my assignment 3, achieving over 50% accuracy in the end, with only 4 hidden layers
Hello everyone, I am working on the titanic data from kaggle competition, can any one suggest me how can I increase the accuracy further, I am currently at 0.84
Yes Vijay, you are absolutely correct. I should’ve been more alert since my validation accuracy and testing accuracy were the same.
Check your notebooks (versions) . The code is not getting reflected in the cells.