Develop Reference

Can't print model summary using PyTorch?

Hello I am building a DQN model for reinforcement learning on cartpole and want to print my model summary like keras model.summary() function
Here is my model class.
class DQN():
''' Deep Q Neural Network class. '''
def __init__(self, state_dim, action_dim, hidden_dim=64, lr=0.05):
super(DQN, self).__init__()
self.criterion = torch.nn.MSELoss()
self.model = torch.nn.Sequential(
torch.nn.Linear(state_dim, hidden_dim),
torch.nn.ReLU(),
torch.nn.Linear(hidden_dim, hidden_dim*2),
torch.nn.ReLU(),
torch.nn.Linear(hidden_dim*2, action_dim)
)
self.optimizer = torch.optim.Adam(self.model.parameters(), lr)
def update(self, state, y):
"""Update the weights of the network given a training sample. """
y_pred = self.model(torch.Tensor(state))
loss = self.criterion(y_pred, Variable(torch.Tensor(y)))
self.optimizer.zero_grad()
loss.backward()
self.optimizer.step()
def predict(self, state):
""" Compute Q values for all actions using the DQL. """
with torch.no_grad():
return self.model(torch.Tensor(state))
Here is the model instance with the parameters passed.
# Number of states = 4
n_state = env.observation_space.shape[0]
# Number of actions = 2
n_action = env.action_space.n
# Number of episodes
episodes = 150
# Number of hidden nodes in the DQN
n_hidden = 50
# Learning rate
lr = 0.001
simple_dqn = DQN(n_state, n_action, n_hidden, lr)
I tried using torchinfo summary
from torchinfo import summary
simple_dqn = DQN(n_state, n_action, n_hidden, lr)
summary(simple_dqn, input_size=(4, 2, 50))
But I get the following error
NotImplementedError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/torchinfo/torchinfo.py in forward_pass(model, x, batch_dim, cache_forward_pass, device, mode, **kwargs)
286 if isinstance(x, (list, tuple)):
--> 287 _ = model.to(device)(*x, **kwargs)
288 elif isinstance(x, dict):
4 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1147
-> 1148 result = forward_call(*input, **kwargs)
1149 if _global_forward_hooks or self._forward_hooks:
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _forward_unimplemented(self, *input)
200 """
--> 201 raise NotImplementedError(f"Module [{type(self).__name__}] is missing the required \"forward\" function")
202
NotImplementedError: Module [DQN] is missing the required "forward" function
The above exception was the direct cause of the following exception:
RuntimeError Traceback (most recent call last)
<ipython-input-24-ee921f7e5cb5> in <module>
1 from torchinfo import summary
2 simple_dqn = DQN(n_state, n_action, n_hidden, lr)
----> 3 summary(simple_dqn, input_size=(4, 2, 50))
/usr/local/lib/python3.7/dist-packages/torchinfo/torchinfo.py in summary(model, input_size, input_data, batch_dim, cache_forward_pass, col_names, col_width, depth, device, dtypes, mode, row_settings, verbose, **kwargs)
216 )
217 summary_list = forward_pass(
--> 218 model, x, batch_dim, cache_forward_pass, device, model_mode, **kwargs
219 )
220 formatting = FormattingOptions(depth, verbose, columns, col_width, rows)
/usr/local/lib/python3.7/dist-packages/torchinfo/torchinfo.py in forward_pass(model, x, batch_dim, cache_forward_pass, device, mode, **kwargs)
297 "Failed to run torchinfo. See above stack traces for more details. "
298 f"Executed layers up to: {executed_layers}"
--> 299 ) from e
300 finally:
301 if hooks:
RuntimeError: Failed to run torchinfo. See above stack traces for more details. Executed layers up to: []
Any help is appreciated.

If you look at the stack trace , you can see it throws this error at the beginning.
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _forward_unimplemented(self, *input)
200 """
--> 201 raise NotImplementedError(f"Module [{type(self).__name__}] is missing the required \"forward\" function")
202
NotImplementedError: Module [DQN] is missing the required "forward" function
This is the main error you should be looking at. Which is that you are missing the forward function your model should have. Here is an example of how you would implement it.
def forward(self, x):
x = self.pool(torch.nn.relu(self.conv1(x)))
x = self.pool(torch.nn.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = torch.nn.relu(self.fc1(x))
x = torch.nn.relu(self.fc2(x))
x = self.fc3(x)
return x

summary() takes in a model as its first parameter. simple_dqn is not a model, it's your custom class. Try passing simple_dqn.model (i.e. summary(simple_dqn.model, input_size=(4, 2, 50)))

BiLSTM forward() - RuntimeError: shape '[-1, 38]' is invalid for input of size 1

Goal: implement bidirectionality in LSTM.
I'm new to Deep Learning and chose pytorch-lightening for minimal coding. Progress has been made, thanks to responses from prior posts.
forward() now needs to facilitate nn.LSTM(... bidirectional=True).
I'm basing my latest amendments on this disscuss.pytorch.org response.
Error
Error is based on mismatch of shapes.
Which data needs to be shaped for which layers?
I'm far out of my depths.
RuntimeError: shape '[-1, 38]' is invalid for input of size 1
Code
from argparse import ArgumentParser
import torchmetrics
import pytorch_lightning as pl
import torch
import torch.nn as nn
import torch.nn.functional as F
class LSTMClassifier(nn.Module):
def __init__(self,
num_classes,
batch_size=10,
embedding_dim=100,
hidden_dim=50,
vocab_size=128):
super(LSTMClassifier, self).__init__()
initrange = 0.1
self.num_labels = num_classes
n = len(self.num_labels)
self.hidden_dim = hidden_dim
self.batch_size = batch_size
self.num_layers = 1
self.word_embeddings = nn.Embedding(vocab_size, embedding_dim)
self.word_embeddings.weight.data.uniform_(-initrange, initrange)
self.lstm = nn.LSTM(input_size=embedding_dim, hidden_size=hidden_dim, num_layers=self.num_layers, batch_first=True, bidirectional=True) # !
#self.classifier = nn.Linear(hidden_dim, self.num_labels[0])
self.classifier = nn.Linear(2 * hidden_dim, self.num_labels[0]) # !
def repackage_hidden(h):
"""Wraps hidden states in new Tensors, to detach them from their history."""
if isinstance(h, torch.Tensor):
return h.detach()
else:
return tuple(repackage_hidden(v) for v in h)
def forward(self, sentence, labels=None):
embeds = self.word_embeddings(sentence)
# lstm_out, _ = self.lstm(embeds) # lstm_out - 2 tensors, _ - hidden layer
lstm_out, hidden = self.lstm(embeds)
# Calculate number of directions
self.num_directions = 2 if self.lstm.bidirectional == True else 1
# Extract last hidden state
# final_state = hidden.view(self.num_layers, self.num_directions, self.batch_size, self.hidden_dim)[-1]
final_state = hidden[0].view(self.num_layers, self.num_directions, self.batch_size, self.hidden_dim)[-1]
# Handle directions
final_hidden_state = None
if self.num_directions == 1:
final_hidden_state = final_state.squeeze(0)
elif self.num_directions == 2:
h_1, h_2 = final_state[0], final_state[1]
# final_hidden_state = h_1 + h_2 # Add both states (requires changes to the input size of first linear layer + attention layer)
final_hidden_state = torch.cat((h_1, h_2), 1) # Concatenate both states
print("len(final_hidden_state)", len(final_hidden_state))
print("len(labels)", len(labels))
print("final_hidden_state.shape", final_hidden_state.shape)
print("labels", labels)
self.linear_dims = [0]
# Define set of fully connected layers (Linear Layer + Activation Layer) * #layers
self.linears = nn.ModuleList()
for i in range(0, len(self.linear_dims)-1):
linear_layer = nn.Linear(self.linear_dims[i], self.linear_dims[i+1])
self.init_weights(linear_layer)
self.linears.append(linear_layer)
if i == len(self.linear_dims) - 1:
break # no activation after output layer!!!
self.linears.append(nn.ReLU())
X = final_hidden_state
# Push through linear layers
for l in self.linears:
X = l(X)
# tag_space = self.classifier(hidden[:,0,:] + hidden[:,-1,:]) # ! # torch.flip(lstm_out[:,-1,:], [0, 1]) - 1 tensor
#logits = F.log_softmax(final_hidden_state, dim=1)
logits = F.cross_entropy(final_hidden_state, labels[0].view(-1))
loss = None
if labels:
# print("len(logits.view(-1, self.num_labels[0]))", len(logits.view(-1, self.num_labels[0])))
print("len(self.num_labels)", len(self.num_labels))
print("self.num_labels[0]", self.num_labels[0])
print("len(labels[0].view(-1))", len(labels[0].view(-1)))
loss = F.cross_entropy(logits.view(-1, self.num_labels[0]), labels[0].view(-1))
return loss, logits
class LSTMTaggerModel(pl.LightningModule):
def __init__(
self,
num_classes,
class_map,
from_checkpoint=False,
model_name='last.ckpt',
learning_rate=3e-6,
**kwargs,
):
super().__init__()
self.save_hyperparameters()
self.learning_rate = learning_rate
self.model = LSTMClassifier(num_classes=num_classes)
# self.model.load_state_dict(torch.load(model_name), strict=False) # !
self.class_map = class_map
self.num_classes = num_classes
self.valid_acc = torchmetrics.Accuracy()
self.valid_f1 = torchmetrics.F1()
def forward(self, *input, **kwargs):
return self.model(*input, **kwargs)
def training_step(self, batch, batch_idx):
x, y_true = batch
loss, _ = self(x, labels=y_true)
self.log('train_loss', loss)
return loss
def validation_step(self, batch, batch_idx):
x, y_true = batch
_, y_pred = self(x, labels=y_true)
preds = torch.argmax(y_pred, axis=1)
self.valid_acc(preds, y_true[0])
self.log('val_acc', self.valid_acc, prog_bar=True)
self.valid_f1(preds, y_true[0])
self.log('f1', self.valid_f1, prog_bar=True)
def configure_optimizers(self):
'Prepare optimizer and schedule (linear warmup and decay)'
opt = torch.optim.Adam(params=self.parameters(), lr=self.learning_rate)
sch = torch.optim.lr_scheduler.CosineAnnealingLR(opt, T_max=10)
return [opt], [sch]
def training_epoch_end(self, training_step_outputs):
avg_loss = torch.tensor([x['loss']
for x in training_step_outputs]).mean()
self.log('train_loss', avg_loss)
print(f'###score: train_loss### {avg_loss}')
def validation_epoch_end(self, val_step_outputs):
acc = self.valid_acc.compute()
f1 = self.valid_f1.compute()
self.log('val_score', acc)
self.log('f1', f1)
print(f'###score: val_score### {acc}')
def add_model_specific_args(parent_parser):
parser = parent_parser.add_argument_group("OntologyTaggerModel")
parser = ArgumentParser(parents=[parent_parser], add_help=False)
parser.add_argument("--learning_rate", default=2e-3, type=float)
return parent_parser
Traceback:
Global seed set to 42
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
| Name | Type | Params
---------------------------------------------
0 | model | LSTMClassifier | 77.4 K
1 | valid_acc | Accuracy | 0
2 | valid_f1 | F1 | 0
---------------------------------------------
77.4 K Trainable params
0 Non-trainable params
77.4 K Total params
0.310 Total estimated model params size (MB)
Validation sanity check: 0it [00:00, ?it/s]
len(final_hidden_state) 10
len(labels) 1
final_hidden_state.shape torch.Size([10, 100])
labels [tensor([ 2, 31, 26, 37, 22, 5, 31, 36, 5, 10])]
len(self.num_labels) 1
self.num_labels[0] 38
len(labels[0].view(-1)) 10
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-16-3f817f701f20> in <module>
11 """.split()
12
---> 13 run_training(args)
<ipython-input-5-bb0d8b014e32> in run_training(input)
66 shutil.copyfile(labels_file_orig, labels_file_cp)
67 trainer = pl.Trainer.from_argparse_args(args, callbacks=[checkpoint_callback], logger=loggers)
---> 68 trainer.fit(model, dm)
69 model_file = os.path.join(args.modeldir, 'last.ckpt')
70 trainer.save_checkpoint(model_file, weights_only=True)
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py in fit(self, model, train_dataloader, val_dataloaders, datamodule)
497
498 # dispath `start_training` or `start_testing` or `start_predicting`
--> 499 self.dispatch()
500
501 # plugin will finalized fitting (e.g. ddp_spawn will load trained model)
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py in dispatch(self)
544
545 else:
--> 546 self.accelerator.start_training(self)
547
548 def train_or_test_or_predict(self):
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py in start_training(self, trainer)
71
72 def start_training(self, trainer):
---> 73 self.training_type_plugin.start_training(trainer)
74
75 def start_testing(self, trainer):
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py in start_training(self, trainer)
112 def start_training(self, trainer: 'Trainer') -> None:
113 # double dispatch to initiate the training loop
--> 114 self._results = trainer.run_train()
115
116 def start_testing(self, trainer: 'Trainer') -> None:
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py in run_train(self)
605 self.progress_bar_callback.disable()
606
--> 607 self.run_sanity_check(self.lightning_module)
608
609 # set stage for logging
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py in run_sanity_check(self, ref_model)
858
859 # run eval step
--> 860 _, eval_results = self.run_evaluation(max_batches=self.num_sanity_val_batches)
861
862 self.on_sanity_check_end()
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py in run_evaluation(self, max_batches, on_epoch)
723 # lightning module methods
724 with self.profiler.profile("evaluation_step_and_end"):
--> 725 output = self.evaluation_loop.evaluation_step(batch, batch_idx, dataloader_idx)
726 output = self.evaluation_loop.evaluation_step_end(output)
727
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/trainer/evaluation_loop.py in evaluation_step(self, batch, batch_idx, dataloader_idx)
164 model_ref._current_fx_name = "validation_step"
165 with self.trainer.profiler.profile("validation_step"):
--> 166 output = self.trainer.accelerator.validation_step(args)
167
168 # capture any logged information
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py in validation_step(self, args)
175
176 with self.precision_plugin.val_step_context(), self.training_type_plugin.val_step_context():
--> 177 return self.training_type_plugin.validation_step(*args)
178
179 def test_step(self, args):
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py in validation_step(self, *args, **kwargs)
129
130 def validation_step(self, *args, **kwargs):
--> 131 return self.lightning_module.validation_step(*args, **kwargs)
132
133 def test_step(self, *args, **kwargs):
<ipython-input-15-6ef4e0993417> in validation_step(self, batch, batch_idx)
130 def validation_step(self, batch, batch_idx):
131 x, y_true = batch
--> 132 _, y_pred = self(x, labels=y_true)
133 preds = torch.argmax(y_pred, axis=1)
134 self.valid_acc(preds, y_true[0])
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/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(),
<ipython-input-15-6ef4e0993417> in forward(self, *input, **kwargs)
120
121 def forward(self, *input, **kwargs):
--> 122 return self.model(*input, **kwargs)
123
124 def training_step(self, batch, batch_idx):
~/anaconda3/envs/pytorch_latest_p36/lib/python3.6/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(),
<ipython-input-15-6ef4e0993417> in forward(self, sentence, labels)
93 print("self.num_labels[0]", self.num_labels[0])
94 print("len(labels[0].view(-1))", len(labels[0].view(-1)))
---> 95 loss = F.cross_entropy(logits.view(-1, self.num_labels[0]), labels[0].view(-1))
96 return loss, logits
97
RuntimeError: shape '[-1, 38]' is invalid for input of size 1

My problem was 2 things.
One, I had to run classifier() before calculating cross_entropy().
Secondly, I had to pass X, final_hidden_layer.flatten().
X = final_hidden_state
# Push through linear layers
for l in self.linears:
X = l(X)
logits = self.classifier(X)
This achieves a working model. However, the first epoch's validation score is 0%.
This will require further work.

Pytorch Embedding Error Index out of Range in self

As written in the title above it is the Pytroch Error: "IndexError: index out of range in self". This error occurs as soon as a dataset of more than 500 rows is used. Also when I reload the model and try to run a second data set, I get this error. I have tried everything possible to manually set the embedding size, so everything I have found on the net has not worked. Attached the model, optimizer and runtime, would be very grateful for your help.
class Model(nn.Module):
def __init__(self, embedding_size, num_numerical_cols, output_size, layers, p=0.4):
super().__init__()
self.all_embeddings = nn.ModuleList([nn.Embedding(ni, nf) for ni, nf in embedding_size])
self.embedding_dropout = nn.Dropout(p)
self.batch_norm_num = nn.BatchNorm1d(num_numerical_cols)
all_layers = []
num_categorical_cols = sum((nf for ni, nf in embedding_size))
input_size = num_categorical_cols + num_numerical_cols
for i in layers:
all_layers.append(nn.Linear(input_size, i))
all_layers.append(nn.ReLU(inplace=True))
all_layers.append(nn.BatchNorm1d(i))
all_layers.append(nn.Dropout(p))
input_size = i
all_layers.append(nn.Linear(layers[-1], output_size))
self.layers = nn.Sequential(*all_layers)
def forward(self, x_categorical, x_numerical):
embeddings = []
for i,e in enumerate(self.all_embeddings):
embeddings.append(e(x_categorical[:,i]))
x = torch.cat(embeddings, 1)
x = self.embedding_dropout(x)
x_numerical = self.batch_norm_num(x_numerical)
x = torch.cat([x, x_numerical], 1)
x = self.layers(x)
return x
model = Model(categorical_embedding_sizes, numerical_data.shape[1], 5, [400,100,50], p=0.4)
loss_function = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
epochs = 100
aggregated_losses = []
for i in range(epochs):
i += 1
y_pred = model(categorical_train_data, numerical_train_data)
single_loss = loss_function(y_pred, train_outputs)
aggregated_losses.append(single_loss)
print(f'epoch: {i:3} loss: {single_loss.item():10.8f}')
optimizer.zero_grad()
single_loss.backward()
optimizer.step()
print(f'epoch: {i:3} loss: {single_loss.item():10.10f}')
Here is the error as described:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-157-202810d3193a> in <module>
4 for i in range(epochs):
5 i += 1
----> 6 y_pred = model(categorical_train_data, numerical_train_data)
7 single_loss = loss_function(y_pred, train_outputs)
8 aggregated_losses.append(single_loss)
C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
<ipython-input-117-fd6404aba4b5> in forward(self, x_categorical, x_numerical)
25 embeddings = []
26 for i,e in enumerate(self.all_embeddings):
---> 27 embeddings.append(e(x_categorical[:,i]))
28 x = torch.cat(embeddings, 1)
29 x = self.embedding_dropout(x)
C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\module.py in __call__(self, *input, **kwargs)
548 result = self._slow_forward(*input, **kwargs)
549 else:
--> 550 result = self.forward(*input, **kwargs)
551 for hook in self._forward_hooks.values():
552 hook_result = hook(self, input, result)
C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\sparse.py in forward(self, input)
112 return F.embedding(
113 input, self.weight, self.padding_idx, self.max_norm,
--> 114 self.norm_type, self.scale_grad_by_freq, self.sparse)
115
116 def extra_repr(self):
C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
1722 # remove once script supports set_grad_enabled
1723 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 1724 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
1725
1726
IndexError: index out of range in self

Input tensors to a Functional must come from `tf.keras.Input`. Received: 0 (missing previous layer metadata) and cant find the cause

I got an error of ValueError: Input tensors to a Functional must come from tf.keras.Input. Received: 0 (missing previous layer metadata) and i cant find the cause
this is my error trace and my code
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-15-8058f3a2fd50> in <module>()
6 test_loss, test_accuracy = eg.test(dg.user_test)
7 print('Test set: Loss=%.4f ; Accuracy=%.1f%%' % (test_loss, test_accuracy * 100))
----> 8 eg.save_embeddings('embeddings.csv')
7 frames
<ipython-input-5-54ff9897b1c3> in save_embeddings(self, file_name)
66 inp = self.m.input # input placeholder
67 outputs = [layer.output for layer in self.m.layers] # all layer outputs
---> 68 functor = K.function([inp, K.learning_phase()], outputs ) # evaluation function
69
70 #append embeddings to vectors
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py in function(inputs, outputs, updates, name, **kwargs)
3934 from tensorflow.python.keras import models # pylint: disable=g-import-not-at-top
3935 from tensorflow.python.keras.utils import tf_utils # pylint: disable=g-import-not-at-top
-> 3936 model = models.Model(inputs=inputs, outputs=outputs)
3937
3938 wrap_outputs = isinstance(outputs, list) and len(outputs) == 1
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in __new__(cls, *args, **kwargs)
240 # Functional model
241 from tensorflow.python.keras.engine import functional # pylint: disable=g-import-not-at-top
--> 242 return functional.Functional(*args, **kwargs)
243 else:
244 return super(Model, cls).__new__(cls, *args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
--> 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in __init__(self, inputs, outputs, name, trainable)
113 # 'arguments during initialization. Got an unexpected argument:')
114 super(Functional, self).__init__(name=name, trainable=trainable)
--> 115 self._init_graph_network(inputs, outputs)
116
117 #trackable.no_automatic_dependency_tracking
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
--> 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in _init_graph_network(self, inputs, outputs)
142 base_layer_utils.create_keras_history(self._nested_outputs)
143
--> 144 self._validate_graph_inputs_and_outputs()
145
146 # A Network does not create weights of its own, thus it is already
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in _validate_graph_inputs_and_outputs(self)
637 'must come from `tf.keras.Input`. '
638 'Received: ' + str(x) +
--> 639 ' (missing previous layer metadata).')
640 # Check that x is an input tensor.
641 # pylint: disable=protected-access
ValueError: Input tensors to a Functional must come from `tf.keras.Input`. Received: 0 (missing previous layer metadata).
and this is my snipped code:
class EmbeddingsGenerator:
def __init__(self, train_users, data):
self.train_users = train_users
#preprocess
self.data = data.sort_values(by=['timestamp'])
#make them start at 0
self.data['userId'] = self.data['userId'] - 1
self.data['itemId'] = self.data['itemId'] - 1
self.user_count = self.data['userId'].max() + 1
self.movie_count = self.data['itemId'].max() + 1
self.user_movies = {} #list of rated movies by each user
for userId in range(self.user_count):
self.user_movies[userId] = self.data[self.data.userId == userId]['itemId'].tolist()
self.m = self.model()
def model(self, hidden_layer_size=100):
m = Sequential()
m.add(Dense(hidden_layer_size, input_shape=(1, self.movie_count)))
m.add(Dropout(0.2))
m.add(Dense(self.movie_count, activation='softmax'))
m.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
return m
def generate_input(self, user_id):
'''
Returns a context and a target for the user_id
context: user's history with one random movie removed
target: id of random removed movie
'''
user_movies_count = len(self.user_movies[user_id])
#picking random movie
random_index = np.random.randint(0, user_movies_count-1) # -1 avoids taking the last movie
#setting target
target = np.zeros((1, self.movie_count))
target[0][self.user_movies[user_id][random_index]] = 1
#setting context
context = np.zeros((1, self.movie_count))
context[0][self.user_movies[user_id][:random_index] + self.user_movies[user_id][random_index+1:]] = 1
return context, target
def train(self, nb_epochs = 300, batch_size = 10000):
'''
Trains the model from train_users's history
'''
for i in range(nb_epochs):
print('%d/%d' % (i+1, nb_epochs))
batch = [self.generate_input(user_id=np.random.choice(self.train_users) - 1) for _ in range(batch_size)]
X_train = np.array([b[0] for b in batch])
y_train = np.array([b[1] for b in batch])
self.m.fit(X_train, y_train, epochs=1, validation_split=0.5)
def test(self, test_users, batch_size = 100000):
'''
Returns [loss, accuracy] on the test set
'''
batch_test = [self.generate_input(user_id=np.random.choice(test_users) - 1) for _ in range(batch_size)]
X_test = np.array([b[0] for b in batch_test])
y_test = np.array([b[1] for b in batch_test])
return self.m.evaluate(X_test, y_test)
def save_embeddings(self, file_name):
'''
Generates a csv file containg the vector embedding for each movie.
'''
inp = self.m.input # input placeholder
outputs = [layer.output for layer in self.m.layers] # all layer outputs
functor = K.function([inp, K.learning_phase()], outputs ) # evaluation function
#append embeddings to vectors
vectors = []
for movie_id in range(self.movie_count):
movie = np.zeros((1, 1, self.movie_count))
movie[0][0][movie_id] = 1
layer_outs = functor([movie])
vector = [str(v) for v in layer_outs[0][0][0]]
vector = '|'.join(vector)
vectors.append([movie_id, vector])
#saves as a csv file
embeddings = pd.DataFrame(vectors, columns=['item_id', 'vectors']).astype({'item_id': 'int32'})
embeddings.to_csv(file_name, sep=';', index=False)
files.download(file_name)
this is the part of code which call the save_embeddings method
if True: # Generate embeddings?
eg = EmbeddingsGenerator(dg.user_train, pd.read_csv('ml-100k/u.data', sep='\t', names=['userId', 'itemId', 'rating', 'timestamp']))
eg.train(nb_epochs=300)
train_loss, train_accuracy = eg.test(dg.user_train)
print('Train set: Loss=%.4f ; Accuracy=%.1f%%' % (train_loss, train_accuracy * 100))
test_loss, test_accuracy = eg.test(dg.user_test)
print('Test set: Loss=%.4f ; Accuracy=%.1f%%' % (test_loss, test_accuracy * 100))
eg.save_embeddings('embeddings.csv')

RuntimeError: input.size(-1) must be equal to input_size. Expected 200, got 0 ---- PySyft / PyTorch / Federated Learning

does anyone know a solution for this Error? I am trying to switch my PyTorch network to an Federated Learning network but i always get this Error.
I'm using Google Colab an train on GPU. When I print the size of embeds I get 0, but I don't understand why the data is not used there.
RuntimeError Traceback (most recent call last)
<ipython-input-42-fd4a5223524b> in <module>()
----> 1 model, history = train_model(net, dataloaders_dict, criterion, optimizer, num_epochs=10)
2 #model = train_model(net, dataloaders_dict, criterion, optimizer, num_epochs=10)
6 frames
<ipython-input-41-a386f044d41f> in train_model(model, dataloaders, criterion, optimizer, num_epochs, batch_size)
68 # detaching it from its history on the last instance.
69
---> 70 outputs = model(inputs)
71
72 loss = criterion(outputs, labels)
/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-36-64e9a7d68b11> in forward(self, sentence)
11 def forward(self, sentence):
12 embeds = self.word_embeddings(sentence)
---> 13 lstm_out, (h,t) = self.lstm(embeds)
14 lstm_out = self.dropout(lstm_out)
15 tag_space = self.output(lstm_out[:,-1,:])
/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/rnn.py in forward(self, input, hx)
554 hx = self.permute_hidden(hx, sorted_indices)
555
--> 556 self.check_forward_args(input, hx, batch_sizes)
557 if batch_sizes is None:
558 result = _VF.lstm(input, hx, self._flat_weights, self.bias, self.num_layers,
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in check_forward_args(self, input, hidden, batch_sizes)
506 def check_forward_args(self, input, hidden, batch_sizes):
507 # type: (Tensor, Tuple[Tensor, Tensor], Optional[Tensor]) -> None
--> 508 self.check_input(input, batch_sizes)
509 expected_hidden_size = self.get_expected_hidden_size(input, batch_sizes)
510
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py in check_input(self, input, batch_sizes)
157 raise RuntimeError(
158 'input.size(-1) must be equal to input_size. Expected {}, got {}'.format(
--> 159 self.input_size, input.size(-1)))
160
161 def get_expected_hidden_size(self, input, batch_sizes):
RuntimeError: input.size(-1) must be equal to input_size. Expected 200, got 0
class LSTM(nn.Module):
def __init__(self, embedding_dim, hidden_layers,vocab_size,num_layers,pretrained_weights):
super(LSTM, self).__init__()
self.word_embeddings = nn.Embedding(vocab_size, embedding_dim,_weight=pretrained_weights, padding_idx=0)
self.lstm = nn.LSTM(embedding_dim, hidden_size=hidden_layers,num_layers=num_layers, batch_first=True)
self.output = nn.Linear(hidden_layers, vocab_size, bias=False)
self.dropout = nn.Dropout(0.1)
def forward(self, sentence):
embeds = self.word_embeddings(sentence)
lstm_out, (h,t) = self.lstm(embeds)
lstm_out = self.dropout(lstm_out)
tag_space = self.output(lstm_out[:,-1,:])
return tag_space
The Error throws in this line: lstm_out, (h,t) = self.lstm(embeds)
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
train_loss = 0
acc_score = 0
valid_loss = 0
acc_valid_score = 0
#Variables to store the losses temporary
train_loss_result = 0
acc_score_result = 0
valid_loss_result = 0
acc_valid_score_result = 0
valid_loss_not_decreased = 0
if valid_loss_not_decreased == 5:
break
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
for inputs,labels in dataloaders[phase]:
# Location of current batch
worker = inputs.location # <---- Where will send the model to
#model.to(device)
model = model.send(worker) # <---- for Federated Learning
inputs, labels = inputs.to(device), labels.to(device)
print("--------> INPUT: ",inputs)
print("--------> LABEL: ",labels)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# backward + optimize only if in training phase
if phase == 'train':
# we need to clear out the hidden state of the LSTM,
# detaching it from its history on the last instance.
outputs = model(inputs)
loss = criterion(outputs, labels)
acc = binary_accuracy(outputs,labels)
acc_score = acc_score + acc
train_loss = train_loss + loss.item()
loss.backward()
optimizer.step()

I also have this error when I run LSTM model by using Pysyft.Besides this,the model of LSTM can run without using Pysyft. Actually,the model of CNN can run successfully by using Pysyft.So,I think there maybe some bugs in the Pysyft.