Error when training a computer-vision model

[shisirkha]

Sir I watch your videos to learn pytorch and it helps me much. sir but when I was practicing my knowledge as the exercise i'm having this problem.

Entier code:

import torch
import torchvision 
from torchvision.transforms import ToTensor
from torchvision.datasets import FashionMNIST
train_data = FashionMNIST("Model_dataset",True,download=True,)
test_data = FashionMNIST("Model_dataset",False,download=True,transform=ToTensor())

from torch.utils.data import DataLoader
BATCH_SIZE=32
train_dataloader = DataLoader(train_data,BATCH_SIZE,True,num_workers=2)
test_dataloader = DataLoader(test_data,BATCH_SIZE,True,num_workers=2)
len(train_dataloader),len(test_dataloader)

import torch.nn as nn
class puttingalltogether(nn.Module):
  def __init__(self,input_shape: int,hidden_units: int,output_shape: int):
    super().__init__()
    self.layer_1 = nn.Sequential(
        nn.Conv2d(input_shape,hidden_units,3,1,1),
        nn.ReLU(),
        nn.Conv2d(hidden_units,hidden_units,3,1,1),
        nn.ReLU(),
        nn.MaxPool2d(2)
    )
    self.layer_2 = nn.Sequential(
        nn.Conv2d(hidden_units,hidden_units,3,1,1),
        nn.ReLU(),
        nn.Conv2d(hidden_units,hidden_units,3,1,1),
        nn.ReLU(),
        nn.MaxPool2d(2)
    )
    self.classifier = nn.Sequential(
        nn.Flatten(),
        nn.Linear(hidden_units,output_shape * 7*7) #There is an trick (Its on the next cell)
    )
  def forward(self,x):
    x = self.layer_1(x)
    x = self.layer_2(x)
    x = self.classifier(x)
    return x

model_final = puttingalltogether(1,10,len(class_names))

#Time for the calculating trick
rand_image_tensor = torch.randn(size=(1,28,28))
rand_image_tensor.shape
# model_final(rand_image_tensor.unsqueeze(0))
10*7*7

#Picking an loss and optimizer functions
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model_final.parameters(),lr=0.01)

#Let us do some analytics on shape so we can clear that its great
for X_test, y_test in test_dataloader:
    print(f"X_test shape: {X_test.shape}, y_test shape: {y_test.shape}")


#Lets write training loop
from tqdm.auto import tqdm
epochs = 4
for epoch in tqdm(range(epochs),desc = f'Training model... with {epoch} left'):
  model_final.train()
  model_final = model_final.to(device)
  for batch,(X,y) in enumerate(train_dataloader):
    X,y = X.to(device),y.to(device)
    y_pred = model_final(X)
    loss = loss_fn(y_pred.argmax(1),y)
    acc = accuracy_fn(y,y_pred.argmax(1))
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
  #Print out what happening
  print(f'train_loss: {loss} | train_acc: {acc} |')

  #Testing loop
  model_final.eval()
  with torch.inference_mode():
    for X_test,y_test in test_dataloader:
      X_test,y_test = X_test.to(device),y_test.to(device)
      test_logits = y_logits = model_final(X_test)
      test_pred = torch.softmax(test_logits,0).argmax(1)
      test_acc = accuracy_fn(test_pred,y_test)
      test_loss = loss_fn(test_pred,y_test)
    #print
    print(f'train_loss: {test_loss} | train_acc: {test_acc} |')

Sir the error is from the training loop (Note: iam using the old accuracy functions from the other cells so no error with the functions)

Error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
[<ipython-input-144-6c0223d56e29>](https://localhost:8080/#) in <cell line: 4>()
      5   model_final.train()
      6   model_final = model_final.to(device)
----> 7   for batch,(X,y) in enumerate(train_dataloader):
      8     X,y = X.to(device),y.to(device)
      9     y_pred = model_final(X)

3 frames
[/usr/local/lib/python3.10/dist-packages/torch/_utils.py](https://localhost:8080/#) in reraise(self)
    692             # instantiate since we don't know how to
    693             raise RuntimeError(msg) from None
--> 694         raise exception
    695 
    696 

TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py", line 54, in fetch
    return self.collate_fn(data)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/collate.py", line 265, in default_collate
    return collate(batch, collate_fn_map=default_collate_fn_map)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/collate.py", line 142, in collate
    return [collate(samples, collate_fn_map=collate_fn_map) for samples in transposed]  # Backwards compatibility.
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/collate.py", line 142, in <listcomp>
    return [collate(samples, collate_fn_map=collate_fn_map) for samples in transposed]  # Backwards compatibility.
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/collate.py", line 150, in collate
    raise TypeError(default_collate_err_msg_format.format(elem_type))
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
Training model... with 0 left: 0%
0/4 [00:00<?, ?it/s]

Sir i saw the error that it's using python PIL image type so it's giving me the error but i tried for several hours finding the solution but i can't find one can anyone help me? i would be glad if anyone helps or even try's to.
#loveFromBangladesh

[shisirkha]

Never mind I got it.