issue: no ./train directory

def check_image(path): try: im = Image.open(path) return True except: return False img_transforms = transforms.Compose([ transforms.Resize((64,64)),
transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225] ) ]) train_data_path = "./train/" train_data = torchvision.datasets.ImageFolder(root=train_data_path,transform=img_transforms, is_valid_file=check_image) val_data_path = "./val/" val_data = torchvision.datasets.ImageFolder(root=val_data_path,transform=img_transforms, is_valid_file=check_image) batch_size=64 train_data_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,shuffle=True) val_data_loader = torch.utils.data.DataLoader(val_data, batch_size=batch_size, shuffle=True) if torch.cuda.is_available(): device = torch.device("cuda") else: device = torch.device("cpu")

FileNotFoundErrorTraceback (most recent call last) in () 12 ]) 13 train_data_path = "./train/" ---> 14 train_data = torchvision.datasets.ImageFolder(root=train_data_path,transform=img_transforms, is_valid_file=check_image) 15 val_data_path = "./val/" 16 val_data = torchvision.datasets.ImageFolder(root=val_data_path,transform=img_transforms, is_valid_file=check_image)

~/anaconda3/lib/python3.6/site-packages/torchvision/datasets/folder.py in init(self, root, transform, target_transform, loader, is_valid_file) 207 transform=transform, 208 target_transform=target_transform, --> 209 is_valid_file=is_valid_file) 210 self.imgs = self.samples

~/anaconda3/lib/python3.6/site-packages/torchvision/datasets/folder.py in init(self, root, loader, extensions, transform, target_transform, is_valid_file) 91 super(DatasetFolder, self).init(root, transform=transform, 92 target_transform=target_transform) ---> 93 classes, class_to_idx = self._find_classes(self.root) 94 samples = make_dataset(self.root, class_to_idx, extensions, is_valid_file) 95 if len(samples) == 0:

~/anaconda3/lib/python3.6/site-packages/torchvision/datasets/folder.py in _find_classes(self, dir) 120 if sys.version_info >= (3, 5): 121 # Faster and available in Python 3.5 and above --> 122 classes = [d.name for d in os.scandir(dir) if d.is_dir()] 123 else: 124 classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]

FileNotFoundError: [Errno 2] No such file or directory: './train/'

py:28: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.

Need dim parameter added to softmax calls.

Replacing the model from Chapter 2 with the one of Chapter 3, results in the following message when the prediction algorithm is called: RuntimeError: mat1 and mat2 shapes cannot be multiplied (256x36 and 9216x4096) EDIT: Found solution, using .unsqueeze(0)

#52

There was missing the line

img = torch.unsqueeze(img, 0)

in order to add an additional dimension as the model expects a DataLoader object with batches.

As title says, how do you evaluate a CNN? I tried use the same approach on chapter 2 but I can't. I get the following.

`--------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in 11 img = img_transforms(img).to(device) 12 cnnet.eval() ---> 13 prediction = F.softmax(cnnet(img), dim=1) 14 prediction = prediction.argmax() 15 cats_pred.append(labels[prediction])

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs) 725 result = self._slow_forward(*input, **kwargs) 726 else: --> 727 result = self.forward(*input, **kwargs) 728 for hook in itertools.chain( 729 _global_forward_hooks.values(),

in forward(self, x) 30 31 def forward(self, x): ---> 32 x = self.features(x) 33 x = self.avgpool(x) 34 x = torch.flatten(x, 1)

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs) 725 result = self._slow_forward(*input, **kwargs) 726 else: --> 727 result = self.forward(*input, **kwargs) 728 for hook in itertools.chain( 729 _global_forward_hooks.values(),

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\container.py in forward(self, input) 115 def forward(self, input): 116 for module in self: --> 117 input = module(input) 118 return input 119

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs) 725 result = self._slow_forward(*input, **kwargs) 726 else: --> 727 result = self.forward(*input, **kwargs) 728 for hook in itertools.chain( 729 _global_forward_hooks.values(),

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\conv.py in forward(self, input) 421 422 def forward(self, input: Tensor) -> Tensor: --> 423 return self._conv_forward(input, self.weight) 424 425 class Conv3d(_ConvNd):

D:\Users\gusta\anaconda3\envs\book-1\lib\site-packages\torch\nn\modules\conv.py in _conv_forward(self, input, weight) 417 weight, self.bias, self.stride, 418 _pair(0), self.dilation, self.groups) --> 419 return F.conv2d(input, weight, self.bias, self.stride, 420 self.padding, self.dilation, self.groups) 421

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [64, 3, 11, 11], but got 3-dimensional input of size [3, 64, 64] instead `

Bumps pillow from 7.0.0 to 8.1.1.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Hi, I do not find the solution, why len(train_loader.dataset) is 0 and leads to this error. Thank you for help. Brds, Patrick

[9] train(audionet, optimizer, torch.nn.CrossEntropyLoss(), train_loader, valid_loader, epochs=20, device=device)

ZeroDivisionError Traceback (most recent call last) in ----> 1 train(audionet, optimizer, torch.nn.CrossEntropyLoss(), train_loader, valid_loader, epochs=20, device=device)

in train(model, optimizer, loss_fn, train_loader, val_loader, epochs, device) 14 optimizer.step() 15 training_loss += loss.data.item() * inputs.size(0) ---> 16 training_loss /= len(train_loader.dataset) 17 18 model.eval()

ZeroDivisionError: float division by zero

transfer_model.fc = nn.Sequential(nn.Linear(transfer_model.fc.in_features, 500), nn.ReLU(), nn.Dropout(), nn.Linear(500,2))

AttributeError: 'Sequential' object has no attribute 'in_features'

Hi,

after having inserted the missing train_loader argument in the find_lr() function (we should open a PR for this after having solved this error), I get a RuntimeError in the current version of Chapter6.ipynb.

After running

torch.save(audionet.state_dict(), "audionet.pth")
optimizer = optim.Adam(audionet.parameters(), lr=0.001)
### added: , train_loader, device="cuda"
logs,losses = find_lr(audionet, nn.CrossEntropyLoss(), optimizer, train_loader, device="cuda")
plt.plot(logs,losses)

I get this error:

---------------------------------------------------------------------------

RuntimeError                              Traceback (most recent call last)

<ipython-input-47-d21b94029709> in <module>()
      2 optimizer = optim.Adam(audionet.parameters(), lr=0.001)
      3 ### added: , train_loader, device="cuda"
----> 4 logs,losses = find_lr(audionet, nn.CrossEntropyLoss(), optimizer, train_loader, device="cuda")
      5 plt.plot(logs,losses)

4 frames

<ipython-input-41-3824bd6072de> in find_lr(model, loss_fn, optimizer, train_loader, init_value, final_value, device)
     49         targets = targets.to(device)
     50         optimizer.zero_grad()
---> 51         outputs = model(inputs)
     52         loss = loss_fn(outputs, targets)
     53 

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

<ipython-input-44-db3925c72c5e> in forward(self, x)
     31         x = F.relu(self.bn4(x))
     32         x = self.pool4(x)
---> 33         x = self.avgPool(x)
     34         x = x.squeeze(-1)
     35         x = self.fc1(x)

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/usr/local/lib/python3.6/dist-packages/torch/nn/modules/pooling.py in forward(self, input)
    484         return F.avg_pool1d(
    485             input, self.kernel_size, self.stride, self.padding, self.ceil_mode,
--> 486             self.count_include_pad)
    487 
    488 

RuntimeError: Given input size: (512x1x1). Calculated output size: (512x1x0). Output size is too small

The same happens when I run

train(audionet, optimizer, torch.nn.CrossEntropyLoss(),train_loader, valid_loader, epochs=20)

I ran the code in Colab.

the cell with

audionet.save("audionet.pth")

fails with error message AttributeError: 'AudioNet' object has no attribute 'save'

So of course later attempts to load this pth also fail.

Running the code on Ubuntu 19.10 and an Ananconda python setup

Hi, I've been trying to follow the code examples from the class activation mapping workflow (chapter 7) but have a hard time understanding how this code fits with what comes before:

fts = sf[0].features[idx]
        prob = np.exp(to_np(log_prob))
        preds = np.argmax(prob[idx])
        fts_np = to_np(fts)
        f2=np.dot(np.rollaxis(fts_np,0,3), prob[idx])
        f2-=f2.min()
        f2/=f2.max()
        f2
plt.imshow(dx)
plt.imshow(scipy.misc.imresize(f2, dx.shape), alpha=0.5, cmap='jet');

Could you please post the code that is consistent with previous naming, or add a file in the repository to demonstrate this flow ?

Thanks !

Bumps pillow from 7.0.0 to 9.3.0.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Chapter 6: The ESC-50 folder name are different between book and repo code

In the book, tell me to get the wav file from 2 ways, one is to use git clone, the command in the book is below:

git clone https://github.com/karoldvl/ESC-50

The other is to download the zip file directly and unzip it.

Both will create the folder with the default name ESC-50.

but in the repo code, it used another name esc50 in the file Chapter 6.ipynb:

device="cuda"
bs=64
PATH_TO_ESC50 = Path.cwd() / 'esc50'

It confused me for a long while, every times I failed, get 0 result, I checked and checked again, and finally found the reason.

I suggest to update the repo code

Bumps numpy from 1.18.5 to 1.22.0.

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

I copyed the code to pycharm, but it can not run, here are the code:

import torch import torch.nn as nn import torch.optim as optim import torch.utils.data import torch.nn.functional as F import torchvision from torchvision import transforms from PIL import Image, ImageFile

ImageFile.LOAD_TRUNCATED_IMAGES = True

def check_image(path):

try:

im = Image.open(path)

return True

except:

return False

check_image = True

img_transforms = transforms.Compose([ transforms.Resize((64, 64)), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ])

train_data_path = "./train/" train_data = torchvision.datasets.ImageFolder(root=train_data_path, transform=img_transforms) val_data_path = "./val/" val_data = torchvision.datasets.ImageFolder(root=val_data_path, transform=img_transforms) test_data_path = "./test/" test_data = torchvision.datasets.ImageFolder(root=test_data_path, transform=img_transforms)

batch_size = 64

train_data_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size) val_data_loader = torch.utils.data.DataLoader(val_data, batch_size=batch_size) test_data_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size)

class SimpleNet(nn.Module):

def __init__(self):
    super(SimpleNet, self).__init__()
    self.fc1 = nn.Linear(12288, 84)
    self.fc2 = nn.Linear(84, 50)
    self.fc3 = nn.Linear(50, 2)

def forward(self, x):
    x = x.view(-1, 12288)
    x = F.relu(self.fc1(x))
    x = F.relu(self.fc2(x))
    x = self.fc3(x)
    return x

simplenet = SimpleNet()

optimizer = optim.Adam(simplenet.parameters(), lr=0.001)

if torch.cuda.is_available(): device = torch.device("cuda") else: device = torch.device("cpu")

simplenet.to(device)

def train(model, optimizer, loss_fn, train_loader, val_loader, epochs, device): for epoch in range(1, epochs + 1): training_loss = 0.0 valid_loss = 0.0 model.train() for batch in train_loader: optimizer.zero_grad() inputs, targets = batch inputs = inputs.to(device) targets = targets.to(device) output = model(inputs) loss = loss_fn(output, targets) loss.backward() optimizer.step() training_loss += loss.data.item() * inputs.size(0) training_loss /= len(train_loader.dataset)

    model.eval()
    num_correct = 0
    num_examples = 0
    for batch in val_loader:
        inputs, targets = batch
        inputs = inputs.to(device)
        output = model(inputs)
        targets = targets.to(device)
        loss = loss_fn(output, targets)
        valid_loss += loss.data.item() * inputs.size(0)
        correct = torch.eq(torch.max(F.softmax(output, dim=1), dim=1)[1], targets)
        num_correct += torch.sum(correct).item()
        num_examples += correct.shape[0]
    valid_loss /= len(val_loader.dataset)

    print(
        'Epoch: {}, Training Loss: {:.2f}, Validation Loss: {:.2f}, accuracy = {:.2f}'.format(epoch, training_loss,
                                                                                              valid_loss,
                                                                                              num_correct / num_examples))

epoch = 5

train(simplenet, optimizer, torch.nn.CrossEntropyLoss(), train_data_loader, val_data_loader, epoch, device)

mistake information:

Traceback (most recent call last): File "C:\Users\Administrator\Desktop\disk_file\DL\1\5.py", line 110, in train(simplenet, optimizer, torch.nn.CrossEntropyLoss(), train_data_loader, val_data_loader, epoch, device) File "C:\Users\Administrator\Desktop\disk_file\DL\1\5.py", line 75, in train for batch in train_loader: File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torch\utils\data\dataloader.py", line 521, in next data = self._next_data() File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torch\utils\data\dataloader.py", line 561, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torch\utils\data_utils\fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torch\utils\data_utils\fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torchvision\datasets\folder.py", line 232, in getitem sample = self.loader(path) File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torchvision\datasets\folder.py", line 269, in default_loader return pil_loader(path) File "C:\Users\Administrator\AppData\Roaming\Python\Python39\site-packages\torchvision\datasets\folder.py", line 250, in pil_loader img = Image.open(f) File "C:\Program Files\1\lib\site-packages\PIL\Image.py", line 3030, in open raise UnidentifiedImageError( PIL.UnidentifiedImageError: cannot identify image file <_io.BufferedReader name='./train/cat\1004525_cba96ba3c3.jpg'>

At the top of page 21, we have

batch_size=64
train_data_loader = data.DataLoader(train_data, batch_size=batch_size)  ## line 19, 'data' not defined
val_data_loader = data.DataLoader(val_data, batch_size=batch_size)
test_data_loader = data.DataLoader(test_data, batch_size=batch_size)

which python will complain about, because there has been no 'data' package import.

$ python ./prep.py
Traceback (most recent call last):
  File "./prep.py", line 19, in <module>
    train_data_loader = data.DataLoader(train_data, batch_size=batch_size)
NameError: name 'data' is not defined

where is the data package with the DataLoader definition supposed to come from?