Develop Reference

TypeError: cross_entropy_loss(): argument ‘input’ (position 1) must be Tensor, not Linear

I was following a youtube video and learning to make a chat bot, the teacher explained this step to make the training model, the code compiled perfectly for the teacher but im getting an error. What am i doing wrong?
for epoch in range(num_epochs):
for (words, labels) in train_loader:
words = words.to(device)
labels = labels.to(device, dtype=torch.int64)
outputs= model(words)
loss = criterion(outputs,labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if(epoch +1) % 100 == 0:
print(f'epoch {epoch+1}/{epoch}, loss = {loss.item():.4f}')
print(f'epoch {epoch+1}/{epoch}, loss = {loss.item():.4f}')
NeuralNet:
class NeuralNet(nn.Module):
def __init__(self,input_size, hidden_size,num_classes):
super(NeuralNet,self).__init__()
self.l1 = nn.Linear(input_size,hidden_size)
self.l2 = nn.Linear(hidden_size,hidden_size)
self.l3 = nn.Linear(hidden_size,num_classes)
self.relu = nn.ReLU()
def forward(self,x):
out = self.l1(x)
out = self.relu(out)
out = self.l2(out)
out = self.relu(out)
out = self.l3
return out

The issue is with the NeuralNet code specifically in the line:
out = self.l3
You are setting out to be the Linear layer instead of calling the linear layer on the data. Change it to
out = self.l3(out)
and it will work

Tensorflow 2.0 ValueError while Loading weights from .h5 file

I have a VAE architecture script as follows:
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Input, Conv2D, Flatten, Dense, Conv2DTranspose, Lambda, Reshape, Layer
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras import backend as K
INPUT_DIM = (64,64,3)
CONV_FILTERS = [32,64,64, 128]
CONV_KERNEL_SIZES = [4,4,4,4]
CONV_STRIDES = [2,2,2,2]
CONV_ACTIVATIONS = ['relu','relu','relu','relu']
DENSE_SIZE = 1024
CONV_T_FILTERS = [64,64,32,3]
CONV_T_KERNEL_SIZES = [5,5,6,6]
CONV_T_STRIDES = [2,2,2,2]
CONV_T_ACTIVATIONS = ['relu','relu','relu','sigmoid']
Z_DIM = 32
BATCH_SIZE = 100
LEARNING_RATE = 0.0001
KL_TOLERANCE = 0.5
class Sampling(Layer):
def call(self, inputs):
mu, log_var = inputs
epsilon = K.random_normal(shape=K.shape(mu), mean=0., stddev=1.)
return mu + K.exp(log_var / 2) * epsilon
class VAEModel(Model):
def __init__(self, encoder, decoder, r_loss_factor, **kwargs):
super(VAEModel, self).__init__(**kwargs)
self.encoder = encoder
self.decoder = decoder
self.r_loss_factor = r_loss_factor
def train_step(self, data):
if isinstance(data, tuple):
data = data[0]
def compute_kernel(x, y):
x_size = tf.shape(x)[0]
y_size = tf.shape(y)[0]
dim = tf.shape(x)[1]
tiled_x = tf.tile(tf.reshape(x, tf.stack([x_size, 1, dim])), tf.stack([1, y_size, 1]))
tiled_y = tf.tile(tf.reshape(y, tf.stack([1, y_size, dim])), tf.stack([x_size, 1, 1]))
return tf.exp(-tf.reduce_mean(tf.square(tiled_x - tiled_y), axis=2) / tf.cast(dim, tf.float32))
def compute_mmd(x, y):
x_kernel = compute_kernel(x, x)
y_kernel = compute_kernel(y, y)
xy_kernel = compute_kernel(x, y)
return tf.reduce_mean(x_kernel) + tf.reduce_mean(y_kernel) - 2 * tf.reduce_mean(xy_kernel)
with tf.GradientTape() as tape:
z_mean, z_log_var, z = self.encoder(data)
reconstruction = self.decoder(z)
reconstruction_loss = tf.reduce_mean(
tf.square(data - reconstruction), axis = [1,2,3]
)
reconstruction_loss *= self.r_loss_factor
kl_loss = 1 + z_log_var - tf.square(z_mean) - tf.exp(z_log_var)
kl_loss = tf.reduce_sum(kl_loss, axis = 1)
kl_loss *= -0.5
true_samples = tf.random.normal(tf.stack([BATCH_SIZE, Z_DIM]))
loss_mmd = compute_mmd(true_samples, z)
total_loss = reconstruction_loss + loss_mmd
grads = tape.gradient(total_loss, self.trainable_weights)
self.optimizer.apply_gradients(zip(grads, self.trainable_weights))
return {
"loss": total_loss,
"reconstruction_loss": reconstruction_loss,
"kl_loss": kl_loss,
"mmd_loss": loss_mmd
}
def call(self,inputs):
latent = self.encoder(inputs)
return self.decoder(latent)
class VAE():
def __init__(self):
self.models = self._build()
self.full_model = self.models[0]
self.encoder = self.models[1]
self.decoder = self.models[2]
self.input_dim = INPUT_DIM
self.z_dim = Z_DIM
self.learning_rate = LEARNING_RATE
self.kl_tolerance = KL_TOLERANCE
def _build(self):
vae_x = Input(shape=INPUT_DIM, name='observation_input')
vae_c1 = Conv2D(filters = CONV_FILTERS[0], kernel_size = CONV_KERNEL_SIZES[0], strides = CONV_STRIDES[0], activation=CONV_ACTIVATIONS[0], name='conv_layer_1')(vae_x)
vae_c2 = Conv2D(filters = CONV_FILTERS[1], kernel_size = CONV_KERNEL_SIZES[1], strides = CONV_STRIDES[1], activation=CONV_ACTIVATIONS[0], name='conv_layer_2')(vae_c1)
vae_c3= Conv2D(filters = CONV_FILTERS[2], kernel_size = CONV_KERNEL_SIZES[2], strides = CONV_STRIDES[2], activation=CONV_ACTIVATIONS[0], name='conv_layer_3')(vae_c2)
vae_c4= Conv2D(filters = CONV_FILTERS[3], kernel_size = CONV_KERNEL_SIZES[3], strides = CONV_STRIDES[3], activation=CONV_ACTIVATIONS[0], name='conv_layer_4')(vae_c3)
vae_z_in = Flatten()(vae_c4)
vae_z_mean = Dense(Z_DIM, name='mu')(vae_z_in)
vae_z_log_var = Dense(Z_DIM, name='log_var')(vae_z_in)
vae_z = Sampling(name='z')([vae_z_mean, vae_z_log_var])
#### DECODER:
vae_z_input = Input(shape=(Z_DIM,), name='z_input')
vae_dense = Dense(1024, name='dense_layer')(vae_z_input)
vae_unflatten = Reshape((1,1,DENSE_SIZE), name='unflatten')(vae_dense)
vae_d1 = Conv2DTranspose(filters = CONV_T_FILTERS[0], kernel_size = CONV_T_KERNEL_SIZES[0] , strides = CONV_T_STRIDES[0], activation=CONV_T_ACTIVATIONS[0], name='deconv_layer_1')(vae_unflatten)
vae_d2 = Conv2DTranspose(filters = CONV_T_FILTERS[1], kernel_size = CONV_T_KERNEL_SIZES[1] , strides = CONV_T_STRIDES[1], activation=CONV_T_ACTIVATIONS[1], name='deconv_layer_2')(vae_d1)
vae_d3 = Conv2DTranspose(filters = CONV_T_FILTERS[2], kernel_size = CONV_T_KERNEL_SIZES[2] , strides = CONV_T_STRIDES[2], activation=CONV_T_ACTIVATIONS[2], name='deconv_layer_3')(vae_d2)
vae_d4 = Conv2DTranspose(filters = CONV_T_FILTERS[3], kernel_size = CONV_T_KERNEL_SIZES[3] , strides = CONV_T_STRIDES[3], activation=CONV_T_ACTIVATIONS[3], name='deconv_layer_4')(vae_d3)
#### MODELS
vae_encoder = Model(vae_x, [vae_z_mean, vae_z_log_var, vae_z], name = 'encoder')
vae_decoder = Model(vae_z_input, vae_d4, name = 'decoder')
vae_full = VAEModel(vae_encoder, vae_decoder, 10000)
opti = Adam(lr=LEARNING_RATE)
vae_full.compile(optimizer=opti)
return (vae_full,vae_encoder, vae_decoder)
def set_weights(self, filepath):
self.full_model.load_weights(filepath)
def train(self, data):
self.full_model.fit(data, data,
shuffle=True,
epochs=1,
batch_size=BATCH_SIZE)
def save_weights(self, filepath):
self.full_model.save_weights(filepath)
Problem:
vae = VAE()
vae.set_weights(filepath)
throws:
File
"/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py",
line 2200, in load_weights
'Unable to load weights saved in HDF5 format into a subclassed ' ValueError: Unable to load weights saved in HDF5 format into a
subclassed Model which has not created its variables yet. Call the
Model first, then load the weights.
I am not sure what this means since I am not that proficient in OOP. The surprising bit is that the above code was working until it stopped working. The model is training from scratch and it saves the weights in filepath. But when I am loading the same weights now it is throwing the above error!

If you set model.built = True prior to loading the model weights it works.

i was getting same same error while loading weights via
model.load_weights("Detection_model.h5")
ValueError: Unable to load weights saved in HDF5 format into a subclassed Model which has not created its variables yet. Call the Model first, then load the weights.
solved it by building model before loading weights
model.build(input_shape = <INPUT_SHAPE>)
model.load_weights("Detection_model.h5")
ps, tensorflow Version: 2.5.0

What version of TF are you running? For a while the default saving format was hdf5, but this format cannot support subclassed models as easily, so you get this error. It may be solvable by first training it on a single batch and then loading the weights (to determine how the parts are connected, which is not saved in hdf5).
In the future I would recommend making sure that all saves are done with the TF file format though, it will save you from extra work.

As alwaysmvp45 pointed out "hdf5 does not store how the layers are connected". To make these layers be connected, another way is that you call the model to predict a zeros array with input shape ((1,w,h,c)) before loading weights:
model(np.zeros((1,w,h,c)))

Not sure if this has changed in more recent versions (I'm on 2.4). but I had to go this route:
# Do all the build and training
# ...
# Save the weights
model.save('path/to/location.h5')
# delete any reference to the model
del model
# Now do the load for testing
from tensorflow import keras
model = keras.models.load_model('path/to/location.h5')
If I tried the other suggestions, I got warnings about the layers not being present and I had to build the same model that I did the training on. No big deal, stick it in in a function somewhere, but this works better for me.

Updating specific rows of a tensor matrix during gradient updation?

I have been trying to implement the paper: SeER: An Explainable Deep Learning MIDI-based Hybrid Song Recommender System.
So, what I have been doing is this:
Model Code:
class HybridFactorization(tf.keras.layers.Layer):
# embedding_size is also the number of lstm units
# num_users, num_movies = input_shape
# required_users: (batch_size, embedding_size)
# songs_output: (batch_size, embedding_size)
def __init__(self, embedding_size, num_users, num_tracks):
super(HybridFactorization, self).__init__()
self.embedding_size = embedding_size
self.num_users = num_users
self.num_tracks = num_tracks
self.required_users = None
self.U = self.add_weight("U",
shape=[self.num_users, self.embedding_size],
dtype=tf.float32,
initializer=tf.initializers.GlorotUniform)
self.lstm = tf.keras.layers.LSTM(self.embedding_size)
def call(self, user_index, songs_batch):
output_lstm = self.lstm(songs_batch)
self.required_users = self.U.numpy()
self.required_users = tf.convert_to_tensor(self.required_users[np.array(user_index)],
dtype=tf.float32)
return tf.matmul(self.required_users, output_lstm, transpose_b=True)
class HybridRecommender(tf.keras.Model):
def __init__(self, embedding_size, num_users, num_tracks):
super(HybridRecommender, self).__init__()
self.HybridFactorization = HybridFactorization(embedding_size,
num_users, num_tracks)
def call(self, user_index, songs_batch):
output = self.HybridFactorization(user_index, songs_batch)
return output
Utility Functions and running the model:
def loss_fn(source, target):
mse = tf.keras.losses.MeanSquaredError()
return mse(source, target)
model = HybridRecommender(EMBEDDING_SIZE, num_users, num_tracks)
Xhat = model(user_index, songs_batch)
tf.keras.backend.clear_session()
optimizer = tf.keras.optimizers.Adam()
EPOCHS = 1
for epoch in range(EPOCHS):
start = time.time()
total_loss = 0
for (batch, (input_batch, target_batch)) in enumerate(train_dataset):
songs_batch = create_songs_batch(input_batch)
user_index = input_batch[:, 0].numpy()
X = create_pivot_batch(input_batch, target_batch)
with tf.GradientTape() as tape:
Xhat = model(user_index, songs_batch)
batch_loss = loss_fn(X, Xhat)
variables = model.trainable_variables
gradients = tape.gradient(batch_loss, variables)
optimizer.apply_gradients(zip(gradients, variables))
total_loss += batch_loss
Now, various functions like create_songs_batch(input_batch) and create_pivot_batch(input_batch, target_batch) just provide data in the required format.
My model runs but I get the warning:
WARNING:tensorflow:Gradients do not exist for variables ['U:0'] when minimizing the loss.
Now, I can see why variable U is not being updated as there is no direct path to it.
I want to update some specific rows of U which are mentioned in user_index in every batch call.
Is there a way to do it?

So, I was able to solve the problem by rather than copying some rows of U and trying to solve it. Instead, I used a temporary matrix that is one hot encoded form of user_index and multiplied it with U to desired results and it also removed the results.
Part of code that needs to be modified:
def call(self, user_index, songs_batch):
# output_lstm: (batch_size, emb_sz)
# batch_encoding: (batch_size, num_users)
# required_users: (batch_size, emb_sz)
output_lstm = self.lstm(songs_batch)
user_idx = np.array(user_index)
batch_encoding = np.zeros((user_idx.size, self.num_users))
batch_encoding[np.arange(user_idx.size), user_idx] = 1
batch_encoding = tf.convert_to_tensor(batch_encoding, dtype=tf.float32)
self.required_users = tf.matmul(batch_encoding, self.U)
return tf.matmul(self.required_users, output_lstm, transpose_b=True)

Ran out of Ram while training LSTM

I am kind of a beginner in RNNs, so I coded a LSTM architecture using Pytorch, but I always run out of RAM whenever I am in the 3rd epoch. I am already using a DataLoader and I tried to detach the gradient from the input tensor but it doesn't solve the problem out.
This is my training loop
writer = SummaryWriter()
criterion = nn.CrossEntropyLoss(reduction='mean', ignore_index = 0)
optimizer = optim.Adam(lstm.parameters(), lr = 1e-5)
gradient_clip = clip_grad_norm_(lstm.parameters(), max_norm = 5)
num_epochs = 20
epoch_loss = -1.0
loss = - 1
t = trange(num_epochs, desc= "Epoch loss", leave=True)
for epoch in t:
trainLoader = iter(DataLoader(dataset, batch_size = batch_size))
tt = trange(len(trainLoader)-1, desc= "Batch loss", leave=True)
for i in tt:
text, embedding = next(trainLoader)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
y = lstm.forward(embedding.transpose(1,0))
labels = text.transpose(0,1)[1:].transpose(0,1).flatten()
loss = criterion(y.reshape(-1, y.shape[-1]), labels)
tt.set_description("Batch loss : %.4f" % loss)
tt.refresh()
loss.backward(retain_graph=True)
optimizer.step()
epoch_loss += loss
epoch_loss = epoch_loss / (len(trainLoader) - 1)
# Saving model
save_date = datetime.now().strftime("%d%m%Y-%H:%M:%S")
PATH = './save/lstm_model_'+save_date
torch.save(lstm, PATH)
# Updating progression bar
t.set_description("Epoch loss : %.4f" % epoch_loss)
t.refresh()
# Plotting gradients histograms in Tensorboard
writer.add_scalar('Text_generation_Loss/train', epoch_loss, epoch)
for tag, parm in lstm.named_parameters():
with torch.no_grad():
writer.add_histogram(tag, parm.grad.data.cpu().numpy(), epoch)
writer.flush()
print('Finished Training')
writer.close()
And this is the LSTM class that I built:
class LSTM(nn.Module):
def __init__(self, in_size : int, hidden_size : int):
super().__init__()
self.in_size = in_size
self.hidden_size = hidden_size
self.W_fi = nn.Linear(in_size,hidden_size)
self.W_fh = nn.Linear(hidden_size,hidden_size, bias=False)
self.W_ii = nn.Linear(in_size,hidden_size)
self.W_ih = nn.Linear(hidden_size,hidden_size, bias=False)
self.W_Ci = nn.Linear(in_size,hidden_size)
self.W_Ch = nn.Linear(hidden_size,hidden_size, bias=False)
self.W_oi = nn.Linear(in_size,hidden_size)
self.W_oh = nn.Linear(hidden_size,hidden_size, bias=False)
self.sigmoid = nn.Sigmoid()
self.tanh = nn.Tanh()
def one_step(self, x, h, C):
f_t = self.sigmoid(self.W_fi(x) + self.W_fh(h))
i_t = self.sigmoid(self.W_ii(x) + self.W_ih(h))
g_t = self.tanh(self.W_Ci(x) + self.W_Ch(h))
C_t = torch.mul(f_t, C) + torch.mul(i_t, g_t)
o_t = self.sigmoid(self.W_oi(x) + self.W_oh(h))
h_t = torch.mul(o_t, self.tanh(C_t))
return h_t, C_t
def forward(self, X):
h_out = []
h = - torch.ones(X.shape[1], self.hidden_size)
C = - torch.ones(X.shape[1], self.hidden_size)
h_t, C_t = self.one_step(X[0], h, C)
h_out.append(h_t)
for i in range(1, X.shape[0] - 1):
h_t, C_t = self.one_step(X[i], h_t, C_t)
h_out.append(h_t)
h_out = torch.cat(h_out)
return h_out #h_out.reshape(-1,batch_size,num_embeddings)
I already searched for a similar case but I wasn't able to find a solution

I don't know if it may help somebody, but I solved the problem. I wasn't perhaps clear about the task, but the goal was to make text generation. The first thing I was doing is embed the sentences using torch.nn.embedding that was defined outside my LSTM. The solution was to include it as a layer of my network, since the embedding is not a pretrained one and should be learned too.

Add training data(text, melspectrogram, spectrogram, label(.wav) files) to Tensorflow 2.0

How to add training data(text, melspectrogram, label(.wav)) in Tensorflow 2.0 like tutorials on Tensorflow website?
How to train that model with gradient tape in tf 2.0? I don't know what is the next step to do? I have built the model with layers with tf.keras.layers and tf.sequence_mask. I am replicating deep voice 3 model to do TTS.
def model():
def __init__(self):
with tf.GradientTape() as tape:
self.char2idx, self.idx2char = load_vocab()
self.x, self.y1, self.y2, self.z, self.num_batch = get_batch()
self.prev_max_attentions_li = tf.ones(shape=(hp.dec_layers, hp.batch_size), dtype=tf.int32)
self.decoder_input = tf.concat((tf.zeros_like(self.y1[:, :1, -hp.n_mels:]), self.y1[:, :-1, -hp.n_mels:]), 1)
self.keys, self.vals = Encoder(self.x)
self.mel_logits, self.done_output, self.decoder_output, self.alignments_li, self.max_attentions_li = Decoder(self.decoder_input, self.keys, self.vals, self.prev_max_attentions_li)
self.mel_output = tf.nn.sigmoid(self.mel_logits)
self.converter_input = tf.reshape(self.decoder_output, (-1, hp.Ty, hp.char_embed//hp.r))
self.converter_input = tf.keras.layers.Dense(hp.cchannel, activation = 'relu')(self.converter_input)
self.mag_logits = Converter(self.converter_input)
self.mag_output = tf.nn.sigmoid(self.mag_logits)
self.global_step = tf.Variable(0, name='global_step', trainable=False)
self.loss_mels = tf.reduce_mean(input_tensor=tf.abs(self.mel_output - self.y1))
self.loss_dones = tf.reduce_mean(input_tensor=tf.nn.sparse_softmax_cross_entropy_with_logits(logits=self.done_output, labels=self.y2))
self.loss_mags = tf.reduce_mean(input_tensor=tf.abs(self.mag_output - self.z))
self.loss = self.loss_mels + self.loss_dones + self.loss_mags
# Training Scheme
self.optimizer = tf.keras.optimizer.Adam(lr=hp.lr)
## gradient clipping
self.gvs = self.optimizer.compute_gradients(self.loss)
self.clipped = []
for grad, var in self.gvs:
grad = tf.clip_by_value(grad, -1. * hp.max_grad_val, hp.max_grad_val)
grad = tf.clip_by_norm(grad, hp.max_grad_norm)
self.clipped.append((grad, var))
self.train_op = self.optimizer.apply_gradients(self.clipped, global_step=self.global_step)
# Summary
tf.summary.scalar('Train_Loss/LOSS', self.loss)
tf.summary.scalar('Train_Loss/mels', self.loss_mels)
tf.summary.scalar('Train_Loss/dones', self.loss_dones)
tf.summary.scalar('Train_Loss/mags', self.loss_mags)
self.merged = tf.summary.merge_all()