Ufdjrw

Is there an Impartial Brexit Deal comparison site?

Are there any comparative studies done between Ashtavakra Gita and Buddhim?

Efficiently merge handle parallel feature branches in SFDX

Teaching indefinite integrals that require special-casing

Will it be accepted, if there is no ''Main Character" stereotype?

Products and sum of cubes in Fibonacci

Why did Kant, Hegel, and Adorno leave some words and phrases in the Greek alphabet?

Is there a good way to store credentials outside of a password manager?

Using parameter substitution on a Bash array

What is the term when two people sing in harmony, but they aren't singing the same notes?

What is the oldest known work of fiction?

Is there a problem with hiding "forgot password" until it's needed?

What's the purpose of "true" in bash "if sudo true; then"

Where in the Bible does the greeting ("Dominus Vobiscum") used at Mass come from?

Coordinate position not precise

Bash method for viewing beginning and end of file

How do I keep an essay about "feeling flat" from feeling flat?

Is there any reason not to eat food that's been dropped on the surface of the moon?

How does it work when somebody invests in my business?

Is it okay / does it make sense for another player to join a running game of Munchkin?

Can a monster with multiattack use this ability if they are missing a limb?

What will be the benefits of Brexit?

Your magic is very sketchy

Why is delta-v is the most useful quantity for planning space travel?

cuDNN error: CUDNN_STATUS_BAD_PARAM.Can someone explain why i am getting this error and how can i correct it?

How to verify CuDNN installation?multi-variable linear regression with pytorchCUDNN Error in backprop for big batchesCUDNN error using pretrained vgg16 modelAttributeError: 'builtin_function_or_method' object has no attribute 'requires_grad'Implementing a custom dataset with PyTorchcupy.cuda.cudnn.CuDNNError: CUDNN_STATUS_INTERNAL_ERRORType Conversionssize mismatch, m1: [3584 x 28], m2: [784 x 128] at /pytorch/aten/src/TH/generic/THTensorMath.cpp:940PyTorch why does the forward function run multiple times and can I change the input shape?

1

I am trying to implement a Character LSTM using Pytorch.But I am getting cudnn_status_bad_params errors.This is the training loop.I getting error on line output = model(input_seq).

for epoch in tqdm(range(epochs)):
 for i in range(len(seq)//batch_size):
 sidx = i*batch_size
 eidx = sidx + batch_size
 x = seq[sidx:eidx]
 x = torch.tensor(x).cuda()
 input_seq =torch.nn.utils.rnn.pack_padded_sequence(x,seq_lengths,batch_first = True)
 y = out_seq[sidx:eidx]
 output = model(input_seq)
 loss = criterion(output,y)
 loss.backward()
 optimizer.step()
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
 487 result = self._slow_forward(*input, **kwargs)
 488 else:
--> 489 result = self.forward(*input, **kwargs)
 490 for hook in self._forward_hooks.values():
 491 hook_result = hook(self, input, result) 
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
 180 else:
 181 result = _impl(input, batch_sizes, hx, self._flat_weights, self.bias,
--> 182 self.num_layers, self.dropout, self.training, self.bidirectional)
 183 output = result[0]
 184 hidden = result[1:] if self.mode == 'LSTM' else result[1]

 RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

pytorch cudnn

share|improve this question

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

add a comment | 

1

I am trying to implement a Character LSTM using Pytorch.But I am getting cudnn_status_bad_params errors.This is the training loop.I getting error on line output = model(input_seq).

for epoch in tqdm(range(epochs)):
 for i in range(len(seq)//batch_size):
 sidx = i*batch_size
 eidx = sidx + batch_size
 x = seq[sidx:eidx]
 x = torch.tensor(x).cuda()
 input_seq =torch.nn.utils.rnn.pack_padded_sequence(x,seq_lengths,batch_first = True)
 y = out_seq[sidx:eidx]
 output = model(input_seq)
 loss = criterion(output,y)
 loss.backward()
 optimizer.step()
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
 487 result = self._slow_forward(*input, **kwargs)
 488 else:
--> 489 result = self.forward(*input, **kwargs)
 490 for hook in self._forward_hooks.values():
 491 hook_result = hook(self, input, result) 
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
 180 else:
 181 result = _impl(input, batch_sizes, hx, self._flat_weights, self.bias,
--> 182 self.num_layers, self.dropout, self.training, self.bidirectional)
 183 output = result[0]
 184 hidden = result[1:] if self.mode == 'LSTM' else result[1]

 RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

pytorch cudnn

share|improve this question

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

add a comment | 

I am trying to implement a Character LSTM using Pytorch.But I am getting cudnn_status_bad_params errors.This is the training loop.I getting error on line output = model(input_seq).

for epoch in tqdm(range(epochs)):
 for i in range(len(seq)//batch_size):
 sidx = i*batch_size
 eidx = sidx + batch_size
 x = seq[sidx:eidx]
 x = torch.tensor(x).cuda()
 input_seq =torch.nn.utils.rnn.pack_padded_sequence(x,seq_lengths,batch_first = True)
 y = out_seq[sidx:eidx]
 output = model(input_seq)
 loss = criterion(output,y)
 loss.backward()
 optimizer.step()
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
 487 result = self._slow_forward(*input, **kwargs)
 488 else:
--> 489 result = self.forward(*input, **kwargs)
 490 for hook in self._forward_hooks.values():
 491 hook_result = hook(self, input, result) 
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
 180 else:
 181 result = _impl(input, batch_sizes, hx, self._flat_weights, self.bias,
--> 182 self.num_layers, self.dropout, self.training, self.bidirectional)
 183 output = result[0]
 184 hidden = result[1:] if self.mode == 'LSTM' else result[1]

 RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

pytorch cudnn

share|improve this question

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

for epoch in tqdm(range(epochs)):
 for i in range(len(seq)//batch_size):
 sidx = i*batch_size
 eidx = sidx + batch_size
 x = seq[sidx:eidx]
 x = torch.tensor(x).cuda()
 input_seq =torch.nn.utils.rnn.pack_padded_sequence(x,seq_lengths,batch_first = True)
 y = out_seq[sidx:eidx]
 output = model(input_seq)
 loss = criterion(output,y)
 loss.backward()
 optimizer.step()
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
 487 result = self._slow_forward(*input, **kwargs)
 488 else:
--> 489 result = self.forward(*input, **kwargs)
 490 for hook in self._forward_hooks.values():
 491 hook_result = hook(self, input, result) 
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in forward(self, input, hx)
 180 else:
 181 result = _impl(input, batch_sizes, hx, self._flat_weights, self.bias,
--> 182 self.num_layers, self.dropout, self.training, self.bidirectional)
 183 output = result[0]
 184 hidden = result[1:] if self.mode == 'LSTM' else result[1]

 RuntimeError: cuDNN error: CUDNN_STATUS_BAD_PARAM

share|improve this question

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

share|improve this question

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

edited Mar 7 at 15:49

talonmies

59.8k17131199

edited Mar 7 at 15:49

talonmies

59.8k17131199

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

asked Mar 7 at 11:40

Sarthak MittalSarthak Mittal

62

1 Answer
1

active

oldest

votes

0

I got the same error, if you switch to CPU, you'll get a much better description of the error. In my case the problem was in type of input that I was giving to the network. I was sending I guess long, while the model needed float. I made the following changes and the code worked. Basically switching to cpu gives better error descriptions.

input_seq = input_seq.float().cuda()

share|improve this answer

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function ()
StackExchange.using("externalEditor", function ()
StackExchange.using("snippets", function ()
StackExchange.snippets.init();
);
);
, "code-snippets");

StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "1"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);

else
createEditor();

);

function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);



);

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f55042931%2fcudnn-error-cudnn-status-bad-param-can-someone-explain-why-i-am-getting-this-er%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

I got the same error, if you switch to CPU, you'll get a much better description of the error. In my case the problem was in type of input that I was giving to the network. I was sending I guess long, while the model needed float. I made the following changes and the code worked. Basically switching to cpu gives better error descriptions.

input_seq = input_seq.float().cuda()

share|improve this answer

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

add a comment | 

0

I got the same error, if you switch to CPU, you'll get a much better description of the error. In my case the problem was in type of input that I was giving to the network. I was sending I guess long, while the model needed float. I made the following changes and the code worked. Basically switching to cpu gives better error descriptions.

input_seq = input_seq.float().cuda()

share|improve this answer

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

add a comment | 

I got the same error, if you switch to CPU, you'll get a much better description of the error. In my case the problem was in type of input that I was giving to the network. I was sending I guess long, while the model needed float. I made the following changes and the code worked. Basically switching to cpu gives better error descriptions.

input_seq = input_seq.float().cuda()

share|improve this answer

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

input_seq = input_seq.float().cuda()

share|improve this answer

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1

answered Mar 16 at 23:13

Prateek RawatPrateek Rawat

1