[FIXED] RuntimeError: all elements of input should be between 0 and 1

Issue

I want to use an RNN with bilstm layers using pytorch on protein embeddings. It worked with Linear Layer but when i use Bilstm i have a Runtime error. Sorry if its not clear its my first publication and i will be grateful if someone can help me.

from collections import Counter, OrderedDict
from typing import Optional
import numpy as np
import pytorch_lightning as pl
import torch
import torch.nn.functional as F  # noqa
from deepchain import log
from sklearn.model_selection import train_test_split
from sklearn.utils.class_weight import compute_class_weight
from torch import Tensor, nn
num_layers=2
hidden_size=256
from torch.utils.data import DataLoader, TensorDataset

def classification_dataloader_from_numpy(
    x: np.ndarray, y: np.array, batch_size: int = 32
) -> DataLoader:
    """Build a dataloader from numpy for classification problem

    This dataloader is use only for classification. It detects automatically the class of
    the problem (binary or multiclass classification)
    Args:
        x (np.ndarray): [description]
        y (np.array): [description]
        batch_size (int, optional): [description]. Defaults to None.

    Returns:
        DataLoader: [description]
    """
    n_class: int = len(np.unique(y))
    if n_class > 2:
        log.info("This is a classification problem with %s classes", n_class)
    else:
        log.info("This is a binary classification problem")

    # y is float for binary classification, int for multiclass
    y_tensor = torch.tensor(y).long() if len(np.unique(y)) > 2 else torch.tensor(y).float()
    tensor_set = TensorDataset(torch.tensor(x).float(), y_tensor)
    loader = DataLoader(tensor_set, batch_size=batch_size)
    return loader

class RNN(pl.LightningModule):
     
    """A `pytorch` based deep learning model"""
    def __init__(self, input_shape: int, n_class: int, num_layers,  n_neurons: int = 128, lr: float = 1e-3):
        super(RNN,self).__init__()
        self.lr = lr
        self.n_neurons=n_neurons
        self.num_layers=num_layers
        self.input_shape = input_shape
        self.output_shape = 1 if n_class <= 2 else n_class
        self.activation = nn.Sigmoid() if n_class <= 2 else nn.Softmax(dim=-1)
        self.lstm = nn.LSTM(self.input_shape, self.n_neurons, num_layers, batch_first=True, bidirectional=True)
        self.fc= nn.Linear(self.n_neurons, self.output_shape)
    def forward(self, x):
        h0=torch.zeros(self.num_layers, x_size(0), self.n_neurons).to(device)
        c0=torch.zeros(self.num_layers, x_size(0), self.n_neurons).to(device)
        out, _=self.lstm(x,(h0, c0))
        out=self.fc(out[:, -1, :])
        return self.fc(x)

    def training_step(self, batch, batch_idx):
        """training_step defined the train loop. It is independent of forward"""
        x, y = batch
        y_hat = self.fc(x).squeeze()
        y = y.squeeze()
        if self.output_shape > 1:
            y_hat = torch.log(y_hat)
        loss = self.loss(y_hat, y)
        self.log("train_loss", loss, on_epoch=True, on_step=False)
        return {"loss": loss}
    def validation_step(self, batch, batch_idx):
        """training_step defined the train loop. It is independent of forward"""
        x, y = batch
        y_hat = self.fc(x).squeeze()
        y = y.squeeze()
        if self.output_shape > 1:
            y_hat = torch.log(y_hat)
        loss = self.loss(y_hat, y)
        self.log("val_loss", loss, on_epoch=True, on_step=False)
        return {"val_loss": loss}
    def configure_optimizers(self):
        """(Optional) Configure training optimizers."""
        return torch.optim.Adam(self.parameters(),lr=self.lr)
    def compute_class_weight(self, y: np.array, n_class: int):
        """Compute class weight for binary/multiple classification
        If n_class=2, only compute weights for the positve class.
        If n>2, compute for all classes.
        Args:
            y ([np.array]):vector of int represented the class
            n_class (int) : number fo class to use
        """
        if n_class == 2:
            class_count: typing.Counter = Counter(y)
            cond_binary = (0 in class_count) and (1 in class_count)
            assert cond_binary, "Must have O and 1 class for binary classification"
            weight = class_count[0] / class_count[1]
        else:
            weight = compute_class_weight(class_weight="balanced", classes=np.unique(y), y=y)
        return torch.tensor(weight).float()
    def fit(
        self,
        x: np.ndarray,
        y: np.array,
        epochs: int = 10,
        batch_size: int = 32,
        class_weight: Optional[str] = None,
        validation_data: bool = True, 
        **kwargs
    ):
        assert isinstance(x, np.ndarray), "X should be a numpy array"
        assert isinstance(y, np.ndarray), "y should be a numpy array"
        assert class_weight in (
            None,
            "balanced",
        ), "the only choice available for class_weight is 'balanced'"
        n_class = len(np.unique(y))
        weight = None
        self.input_shape = x.shape[1]
        self.output_shape = 1 if n_class <= 2 else n_class
        self.activation = nn.Sigmoid() if n_class <= 2 else nn.Softmax(dim=-1)
        if class_weight == "balanced":
            weight = self.compute_class_weight(y, n_class)
        self.loss = nn.NLLLoss(weight) if self.output_shape > 1 else nn.BCELoss(weight)
        if validation_data:
            x_train, x_val, y_train, y_val = train_test_split(x, y, test_size=0.2)
            train_loader = classification_dataloader_from_numpy(
                x_train, y_train, batch_size=batch_size
            )
            val_loader = classification_dataloader_from_numpy(x_val, y_val, batch_size=batch_size)
        else:
            train_loader = classification_dataloader_from_numpy(x, y, batch_size=batch_size)
            val_loader = None
        self.trainer = pl.Trainer(max_epochs=epochs, **kwargs)
        self.trainer.fit(self, train_loader, val_loader)
    def predict(self, x):
        """Run inference on data."""
        if self.output_shape is None:
            log.warning("Model is not fitted. Can't do predict")
            return
        return self.forward(x).detach().numpy()
    def save(self, path: str):
        """Save the state dict model with torch"""
        torch.save(self.fc.state_dict(), path)
        log.info("Save state_dict parameters in model.pt")
    def load_state_dict(self, state_dict: "OrderedDict[str, Tensor]", strict: bool = False):
        """Load state_dict saved parameters
        Args:
            state_dict (OrderedDict[str, Tensor]): state_dict tensor
            strict (bool, optional): [description]. Defaults to False.
        """
        self.fc.load_state_dict(state_dict, strict=strict)
        self.fc.eval()

    mlp = RNN(input_shape=1024, n_neurons=1024, num_layers=2, n_class=2)
mlp.fit(embeddings_train, np.array(y_train),validation_data=(embeddings_test, np.array(y_test)), epochs=30)
mlp.save("model.pt")

These are the errors that are occured. I really need help and i remain at your disposal for further informations.

Error 1

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-154-e5fde11a675c> in <module>
      1 # init MLP model, train it on the data, then save model
      2 mlp = RNN(input_shape=1024, n_neurons=1024, num_layers=2, n_class=2)
----> 3 mlp.fit(embeddings_train, np.array(y_train),validation_data=(embeddings_test, np.array(y_test)), epochs=30)
      4 mlp.save("model.pt")

<ipython-input-153-a8d51af53bb5> in fit(self, x, y, epochs, batch_size, class_weight, validation_data, **kwargs)
    134             val_loader = None
    135         self.trainer = pl.Trainer(max_epochs=epochs, **kwargs)
--> 136         self.trainer.fit(self, train_loader, val_loader)
    137     def predict(self, x):
    138         """Run inference on data."""

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in fit(self, model, train_dataloader, val_dataloaders, datamodule)
    456         )
    457 
--> 458         self._run(model)
    459 
    460         assert self.state.stopped

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in _run(self, model)
    754 
    755         # dispatch `start_training` or `start_evaluating` or `start_predicting`
--> 756         self.dispatch()
    757 
    758         # plugin will finalized fitting (e.g. ddp_spawn will load trained model)

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in dispatch(self)
    795             self.accelerator.start_predicting(self)
    796         else:
--> 797             self.accelerator.start_training(self)
    798 
    799     def run_stage(self):

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/accelerators/accelerator.py in start_training(self, trainer)
     94 
     95     def start_training(self, trainer: 'pl.Trainer') -> None:
---> 96         self.training_type_plugin.start_training(trainer)
     97 
     98     def start_evaluating(self, trainer: 'pl.Trainer') -> None:

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py in start_training(self, trainer)
    142     def start_training(self, trainer: 'pl.Trainer') -> None:
    143         # double dispatch to initiate the training loop
--> 144         self._results = trainer.run_stage()
    145 
    146     def start_evaluating(self, trainer: 'pl.Trainer') -> None:

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in run_stage(self)
    805         if self.predicting:
    806             return self.run_predict()
--> 807         return self.run_train()
    808 
    809     def _pre_training_routine(self):

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in run_train(self)
    840             self.progress_bar_callback.disable()
    841 
--> 842         self.run_sanity_check(self.lightning_module)
    843 
    844         self.checkpoint_connector.has_trained = False

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in run_sanity_check(self, ref_model)
   1105 
   1106             # run eval step
-> 1107             self.run_evaluation()
   1108 
   1109             self.on_sanity_check_end()

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py in run_evaluation(self, on_epoch)
    960                 # lightning module methods
    961                 with self.profiler.profile("evaluation_step_and_end"):
--> 962                     output = self.evaluation_loop.evaluation_step(batch, batch_idx, dataloader_idx)
    963                     output = self.evaluation_loop.evaluation_step_end(output)
    964 

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/trainer/evaluation_loop.py in evaluation_step(self, batch, batch_idx, dataloader_idx)
    172             model_ref._current_fx_name = "validation_step"
    173             with self.trainer.profiler.profile("validation_step"):
--> 174                 output = self.trainer.accelerator.validation_step(args)
    175 
    176         # capture any logged information

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/accelerators/accelerator.py in validation_step(self, args)
    224 
    225         with self.precision_plugin.val_step_context(), self.training_type_plugin.val_step_context():
--> 226             return self.training_type_plugin.validation_step(*args)
    227 
    228     def test_step(self, args: List[Union[Any, int]]) -> Optional[STEP_OUTPUT]:

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py in validation_step(self, *args, **kwargs)
    159 
    160     def validation_step(self, *args, **kwargs):
--> 161         return self.lightning_module.validation_step(*args, **kwargs)
    162 
    163     def test_step(self, *args, **kwargs):

<ipython-input-153-a8d51af53bb5> in validation_step(self, batch, batch_idx)
     78         if self.output_shape > 1:
     79             y_hat = torch.log(y_hat)
---> 80         loss = self.loss(y_hat, y)
     81         self.log("val_loss", loss, on_epoch=True, on_step=False)
     82         return {"val_loss": loss}

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    887             result = self._slow_forward(*input, **kwargs)
    888         else:
--> 889             result = self.forward(*input, **kwargs)
    890         for hook in itertools.chain(
    891                 _global_forward_hooks.values(),

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
    611     def forward(self, input: Tensor, target: Tensor) -> Tensor:
    612         assert self.weight is None or isinstance(self.weight, Tensor)
--> 613         return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
    614 
    615 

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/torch/nn/functional.py in binary_cross_entropy(input, target, weight, size_average, reduce, reduction)
   2760         weight = weight.expand(new_size)
   2761 
-> 2762     return torch._C._nn.binary_cross_entropy(input, target, weight, reduction_enum)
   2763 
   2764 

RuntimeError: all elements of input should be between 0 and 1

Error 2

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-139-b7e8b13763ef> in <module>
      1 # Model evaluation
----> 2 y_pred = mlp(embeddings_val).squeeze().detach().numpy()
      3 model_evaluation_accuracy(np.array(y_val), y_pred)

/opt/conda/envs/bio-transformers/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    887             result = self._slow_forward(*input, **kwargs)
    888         else:
--> 889             result = self.forward(*input, **kwargs)
    890         for hook in itertools.chain(
    891                 _global_forward_hooks.values(),

<ipython-input-136-e2fc535640ab> in forward(self, x)
     55         self.fc= nn.Linear(self.hidden_size, self.output_shape)
     56     def forward(self, x):
---> 57         h0=torch.zeros(self.num_layers, x_size(0), self.hidden_size).to(device)
     58         c0=torch.zeros(self.num_layers, x_size(0), self.hidden_size).to(device)
     59         out, _=self.lstm(x,(h0, c0))

NameError: name 'x_size' is not defined

Solution

I am adding this as an answer because it would be too hard to put in comment.

The main problem that you have is about BCE loss. IIRC BCE loss expects p(y=1), so your output should be between 0 and 1. If you want to use logits (which is also more numerically stable), you should use BinaryCrossEntropyWithLogits.

As you mention in one of the comments, you are using the sigmoid activation but something about your forward function looks off to me. Mainly the last line of your forward function is

        return self.fc(x)

This does not use sigmoid activation. Moreover you are only using input, x for producing the output. The LSTM outputs are just being discarded? I think, it would be a good idea to add some prints statements or breakpoints to make sure that the intermediate outputs are as you expect them to be.

Answered By - Umang Gupta