You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The reason will be displayed to describe this comment to others. Learn more.
Dear sir,
I am running this exact code.
But during training of model, I got "ValueError: expected 5D input (got 4D input)". Will you please me to resolve this error.
The reason will be displayed to describe this comment to others. Learn more.
Sir please help me..
My data is already in 5D format. As you suggested like [batch_size, num_channel, Video_length, height, width], so where it is going wrong.
Please reply.
The reason will be displayed to describe this comment to others. Learn more.
Dear sir,
I am trying to run your code for basic understanding about video
classification. And really it's so helpful for practical implementation
that what I want. But I am getting stuck during training. That's because of
the pytorch version of LightingModule I have used. I tried with older
version too, 'torch 1.8.1' but it gave me the same error from more than
last 15 days. I am not getting what to do.
Here I am going to share my file along with the errors.
NotImplementedError: Support for `training_epoch_end` has been removed
in v2.0.0. `OurModel` implements this method. You can use the
`on_train_epoch_end` hook instead. To access outputs, save them
in-memory as instance attributes. You can find migration examples in
Lightning-AI/pytorch-lightning#16520.
I tried to change as suggested by using 'on_', but gives the another errors as,
TypeError: OurModel.on_validation_epoch_end() missing 1 required
positional argument: 'outputs',
I tried to create an attribute but was not done.
Will you please help me to solve this problem?
I hope you do so.
Thanks you!
On Fri, 2 Jun 2023, 3:19 pm pallaviyn, ***@***.***> wrote:
Dear sir,
I am trying to run your code for basic understanding about video
classification. And really it's so helpful for practical implementation
that what I want. But I am getting stuck during training. That's because of
the pytorch version of LightingModule I have used. I tried with older
version too, 'torch 1.8.1' but it gave me the same error from more than
last 15 days. I am not getting what to do.
Here I am going to share my file along with the errors.
NotImplementedError: Support for `training_epoch_end` has been removed
in v2.0.0. `OurModel` implements this method. You can use the
`on_train_epoch_end` hook instead. To access outputs, save them
in-memory as instance attributes. You can find migration examples in
Lightning-AI/pytorch-lightning#16520.
I tried to change as suggested by using 'on_', but gives the another
errors as,
TypeError: OurModel.on_validation_epoch_end() missing 1 required
positional argument: 'outputs',
I tried to create an attribute but was not done.
Will you please help me to solve this problem?
I hope you do so.
Thanks you!
On Thu, May 25, 2023 at 4:31 PM Talha Anwar ***@***.***>
wrote:
> if you can share a sample data and code, I can look into it
>
> —
> Reply to this email directly, view it on GitHub
> <
b6f500e#commitcomment-114944045
>,
> or unsubscribe
> <
https://github.com/notifications/unsubscribe-auth/AZQQUBLKPYXYG3SU33AW5JDXH43Y5ANCNFSM6AAAAAAYLNY5ZA
>
> .
> You are receiving this because you commented.Message ID:
>
<talhaanwarch/youtube-tutorials/commit/b6f500e1dc6faa86468ac7d1146dff896becd429/114944045
> @github.com>
>
—
Reply to this email directly, view it on GitHub
<b6f500e#commitcomment-116156457>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AI5FYOY46TOFEFF7KEN6PCTXJG42TANCNFSM6AAAAAAYLNY5ZA>
.
You are receiving this because you commented.Message ID:
<talhaanwarch/youtube-tutorials/commit/b6f500e1dc6faa86468ac7d1146dff896becd429/116156457
@github.com>
The reason will be displayed to describe this comment to others. Learn more.
sir, will you please suggest something about this implementation:
how much epochs needed for stable model
and any documentation of efficient_x3d_xs
pls reply..
Thankyou
On Sat, Jun 3, 2023 at 2:02 PM Talha Anwar ***@***.***> wrote:
Can you try 1.5 version
On Fri, 2 Jun 2023, 3:19 pm pallaviyn, ***@***.***> wrote:
> Dear sir,
> I am trying to run your code for basic understanding about video
> classification. And really it's so helpful for practical implementation
> that what I want. But I am getting stuck during training. That's because
of
> the pytorch version of LightingModule I have used. I tried with older
> version too, 'torch 1.8.1' but it gave me the same error from more than
> last 15 days. I am not getting what to do.
>
> Here I am going to share my file along with the errors.
>
> NotImplementedError: Support for `training_epoch_end` has been removed
> in v2.0.0. `OurModel` implements this method. You can use the
> `on_train_epoch_end` hook instead. To access outputs, save them
> in-memory as instance attributes. You can find migration examples in
> Lightning-AI/pytorch-lightning#16520.
>
>
> I tried to change as suggested by using 'on_', but gives the another
> errors as,
>
> TypeError: OurModel.on_validation_epoch_end() missing 1 required
> positional argument: 'outputs',
>
>
> I tried to create an attribute but was not done.
>
>
> Will you please help me to solve this problem?
> I hope you do so.
>
> Thanks you!
>
>
>
>
>
>
>
>
>
> On Thu, May 25, 2023 at 4:31 PM Talha Anwar ***@***.***>
> wrote:
>
> > if you can share a sample data and code, I can look into it
> >
> > —
> > Reply to this email directly, view it on GitHub
> > <
>
b6f500e#commitcomment-114944045
> >,
> > or unsubscribe
> > <
>
https://github.com/notifications/unsubscribe-auth/AZQQUBLKPYXYG3SU33AW5JDXH43Y5ANCNFSM6AAAAAAYLNY5ZA
> >
> > .
> > You are receiving this because you commented.Message ID:
> >
>
<talhaanwarch/youtube-tutorials/commit/b6f500e1dc6faa86468ac7d1146dff896becd429/114944045
> > @github.com>
> >
>
> —
> Reply to this email directly, view it on GitHub
> <
b6f500e#commitcomment-116156457
>,
> or unsubscribe
> <
https://github.com/notifications/unsubscribe-auth/AI5FYOY46TOFEFF7KEN6PCTXJG42TANCNFSM6AAAAAAYLNY5ZA
>
> .
> You are receiving this because you commented.Message ID:
>
<talhaanwarch/youtube-tutorials/commit/b6f500e1dc6faa86468ac7d1146dff896becd429/116156457
> @github.com>
>
—
Reply to this email directly, view it on GitHub
<b6f500e#commitcomment-116285862>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AZQQUBJWLOOPVQOZDFEXDC3XJLZAJANCNFSM6AAAAAAYLNY5ZA>
.
You are receiving this because you commented.Message ID:
<talhaanwarch/youtube-tutorials/commit/b6f500e1dc6faa86468ac7d1146dff896becd429/116285862
@github.com>
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Dear sir,
I am running this exact code.
But during training of model, I got "ValueError: expected 5D input (got 4D input)". Will you please me to resolve this error.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
your data should be of 5D ie batch, channels, video length, height, width
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
My data size is, (torch.Size([4, 3, 20, 224, 224]) still it gives me this error.
How can I rectify this error.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sir please help me..
My data is already in 5D format. As you suggested like [batch_size, num_channel, Video_length, height, width], so where it is going wrong.
Please reply.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
if you can share a sample data and code, I can look into it
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks a lot sir, I have tried with 1.11.0 version and its solved.
But when the num_workers ==0, once I set num_workers>0 it gives me, "TypeError: cannot pickle 'torch._C.Generator' object".
How can I rectify this, pls suggest something.
b6f500e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.