My training set is a set of images (either 3 channel or 1 ofc i use only one type of channel). And the labels are a sequence of points in a specific order that i want to predict from the images.
I am using a model inspired by the image captioning example on the tensorflow website. This is the also the approach that this paper takes https://arxiv.org/pdf/1901.03781.pdf
class CNN_Encoder(tf.keras.Model):
# Since you have already extracted the features and dumped it using pickle
# This encoder passes those features through a Fully connected layer
def __init__(self, embedding_dim):
super(CNN_Encoder, self).__init__()
self.fc = tf.keras.layers.Dense(embedding_dim)
def call(self, x):
x = self.fc(x)
x = tf.nn.relu(x)
return x
class RNN_Decoder(tf.keras.Model):
def __init__(self, embedding_dim, units, output_dim):
super(RNN_Decoder, self).__init__()
self.units = units
self.gru = tf.keras.layers.GRU(self.units,
return_sequences=True,
return_state=True,
recurrent_initializer='glorot_uniform')
self.fc1 = tf.keras.layers.Dense(self.units)
self.fc2 = tf.keras.layers.Dense(output_dim)
def call(self, x, features, hidden):
x = tf.concat((features, x), axis=-1)
output, state = self.gru(x)
x = self.fc1(state)
x = self.fc2(x)
return x
def reset_state(self, batch_size):
return tf.zeros((batch_size, self.units))
@tf.function
def train_step(img_tensor, target):
loss = 0
hidden = decoder.reset_state(batch_size=target.shape[0])
dec_input = tf.expand_dims([[0., 0.]] * target.shape[0], 1)
with tf.GradientTape() as tape:
features = encoder(img_tensor)
for i in (range(1, target.shape[1])):
predictions = decoder(dec_input, features, hidden)
loss += loss_function(target[:, i], predictions)
# using teacher forcing
dec_input = tf.expand_dims(target[:, i], 1)
total_loss = (loss / int(target.shape[1]))
trainable_variables = encoder.trainable_variables + decoder.trainable_variables
gradients = tape.gradient(loss, trainable_variables)
optimizer.apply_gradients(zip(gradients, trainable_variables))
return loss, total_loss
EPOCHS = 20
batch_size = 8
for epoch in tqdm(range(start_epoch, EPOCHS)):
start = time.time()
total_loss = 0
for (batch, (img_tensor, target)) in enumerate((data_generator(preds_t, labels_t))):
img_tensor = img_tensor.reshape((-1, 1, 128*128))
batch_loss, t_loss = train_step(img_tensor, target)
total_loss += t_loss
if batch % 100 == 0:
print ('Epoch {} Batch {} Loss {:.4f}'.format(
epoch + 1, batch, batch_loss.numpy() / int(target.shape[1])))
if batch == 10000:
break
# storing the epoch end loss value to plot later
#loss_plot.append(total_loss / num_steps)
if epoch % 5 == 0:
ckpt_manager.save()
print ('Epoch {} Loss {:.6f}'.format(epoch + 1,
total_loss/num_steps))
print ('Time taken for 1 epoch {} sec\n'.format(time.time() - start))
For the features vector. I am extracting the last layer of a unet. So each image has a size 1x128x128. I reshape it to be 1x1x128*128. Which i then pass through a fully connected layer. The shape then becomes 1x1x256
My labels i want to predict are image coordinates so (x, y). The input to the gru layer is the concatenated 1x1x256 , 1x1x2 (t-1 coordinates). Which i then further pass through a 2 layer fc layer with output dimension 2 for the 2 coordinates. I have removed attention for now to get a simpler model. I normalize my images. I pad the coordinate sequences with 0,0 for the start -1, -1 for the end and -2,-2 for the regular padding to get uniform sequence length of 350x2.
The network doesnt seem to learn much. I just get a few points scattered diagonally across the image. The biggest difference i see with the image captioning model is that the words can be converted to embeddings and then you have a 128 image features 128 word features being concatenated and fed into the lstm. In my case the sequence information is just 1 entry. Could that be the reason that the network is not learning much.
If someone has any insights into what i should change that would be great
