error:mat1 and mat2 shapes cannot be multiplied (3584x28 and 784x128),when I want got a accuracy

[tms2003]

I wana to get train_acc_step just like the document,the code like this:

import os
import torch
from torch import nn
import torch.nn.functional as F
from torchvision.datasets import MNIST
from torch.utils.data import DataLoader, random_split
from torchvision import transforms
import pytorch_lightning as pl
import torchmetrics


class LitAutoEncoder(pl.LightningModule):
    def __init__(self):
        super().__init__()
        self.encoder = nn.Sequential(nn.Linear(28 * 28, 128), nn.ReLU(), nn.Linear(128, 3))
        self.decoder = nn.Sequential(nn.Linear(3, 128), nn.ReLU(), nn.Linear(128, 28 * 28))
        

    def forward(self, x):
        # in lightning, forward defines the prediction/inference actions
        embedding = self.encoder(x)
        return embedding

    def training_step(self, batch, batch_idx):
        # training_step defines the train loop. It is independent of forward
        x, y = batch
        preds = self(x)
        x = x.view(x.size(0), -1)
        z = self.encoder(x)
        x_hat = self.decoder(z)
        loss = F.mse_loss(x_hat, x)
        self.log("train_loss", loss)
        self.accuracy(preds, y)
        self.log("train_acc_step", self.accuracy, on_epoch=True)
        return loss

    def training_epoch_end(self, outs):
        
        self.log('train_acc_epoch', self.train_acc)

    def configure_optimizers(self):
        optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)
        return optimizer

dataset = MNIST(os.getcwd(), download=True, transform=transforms.ToTensor())
train, val = random_split(dataset, [55000, 5000])


autoencoder = LitAutoEncoder()
trainer = pl.Trainer()
trainer.fit(autoencoder, DataLoader(train,batch_size=128), DataLoader(val,batch_size=128))

but I got this error:

/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/data_connector.py:224: PossibleUserWarning: The dataloader, train_dataloader, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 32 which is the number of cpus on this machine) in the `DataLoader` init to improve performance.
  rank_zero_warn(
Epoch 0:   0%|                                                                                                                                      | 0/430 [00:00<?, ?it/s]Traceback (most recent call last):
  File "hello.py", line 65, in <module>
    trainer.fit(autoencoder, DataLoader(train,batch_size=128), DataLoader(val,batch_size=128))
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 582, in fit
    call._call_and_handle_interrupt(
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/call.py", line 38, in _call_and_handle_interrupt
    return trainer_fn(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 624, in _fit_impl
    self._run(model, ckpt_path=self.ckpt_path)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1061, in _run
    results = self._run_stage()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1140, in _run_stage
    self._run_train()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1163, in _run_train
    self.fit_loop.run()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/fit_loop.py", line 267, in advance
    self._outputs = self.epoch_loop.run(self._data_fetcher)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 214, in advance
    batch_output = self.batch_loop.run(kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/batch/training_batch_loop.py", line 88, in advance
    outputs = self.optimizer_loop.run(optimizers, kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 200, in advance
    result = self._run_optimization(kwargs, self._optimizers[self.optim_progress.optimizer_position])
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 247, in _run_optimization
    self._optimizer_step(optimizer, opt_idx, kwargs.get("batch_idx", 0), closure)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 357, in _optimizer_step
    self.trainer._call_lightning_module_hook(
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1305, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/core/module.py", line 1661, in optimizer_step
    optimizer.step(closure=optimizer_closure)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 169, in step
    step_output = self._strategy.optimizer_step(self._optimizer, self._optimizer_idx, closure, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/strategies/strategy.py", line 234, in optimizer_step
    return self.precision_plugin.optimizer_step(
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 121, in optimizer_step
    return optimizer.step(closure=closure, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/optim/optimizer.py", line 88, in wrapper
    return func(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/optim/adam.py", line 100, in step
    loss = closure()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 107, in _wrap_closure
    closure_result = closure()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 147, in __call__
    self._result = self.closure(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 133, in closure
    step_output = self._step_fn()
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 406, in _training_step
    training_step_output = self.trainer._call_strategy_hook("training_step", *kwargs.values())
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1443, in _call_strategy_hook
    output = fn(*args, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/pytorch_lightning/strategies/strategy.py", line 378, in training_step
    return self.model.training_step(*args, **kwargs)
  File "hello.py", line 27, in training_step
    preds = self(x)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "hello.py", line 21, in forward
    embedding = self.encoder(x)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 141, in forward
    input = module(input)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/incar/miniconda3/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 103, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (3584x28 and 784x128)
Epoch 0:   0%|          | 0/430 [00:00<?, ?it/s]                                                                                                                            

so,how to got I wanted? I think the document and video has outdate and lack of some complete examples. so could u help me?

[akihironitta]

@tms2003 Maybe you could check input size according to this error message and ensure the tensor size is batch_sizex784 instead of 3584x28

RuntimeError: mat1 and mat2 shapes cannot be multiplied (3584x28 and 784x128)