Это некоторая часть кода, который я использую
checkpoint_dir = 'training_checkpoints1'
checkpoint_prefix = os.path.join(checkpoint_dir, "ckpt")
checkpoint = tf.train.Checkpoint(optimizer=optimizer,
encoder=encoder,
decoder=decoder)
Теперь это обучающая часть
EPOCHS = 900
for epoch in range(EPOCHS):
start = time.time()
hidden = encoder.initialize_hidden_state()
total_loss = 0
for (batch, (inp, targ)) in enumerate(dataset):
loss = 0
with tf.GradientTape() as tape:
enc_output, enc_hidden = encoder(inp, hidden)
dec_hidden = enc_hidden
dec_input = tf.expand_dims([targ_lang.word2idx['<start>']] * batch_size, 1)
# Teacher forcing - feeding the target as the next input
for t in range(1, targ.shape[1]):
# passing enc_output to the decoder
predictions, dec_hidden, _ = decoder(dec_input, dec_hidden, enc_output)
loss += loss_function(targ[:, t], predictions)
# using teacher forcing
dec_input = tf.expand_dims(targ[:, t], 1)
batch_loss = (loss / int(targ.shape[1]))
total_loss += batch_loss
variables = encoder.variables + decoder.variables
gradients = tape.gradient(loss, variables)
optimizer.apply_gradients(zip(gradients, variables))
if batch % 100 == 0:
print('Epoch {} Batch {} Loss {:.4f}'.format(epoch + 1,
batch,
batch_loss.numpy()))
# saving (checkpoint) the model every 2 epochs
if (epoch + 1) % 2 == 0:
checkpoint.save(file_prefix = checkpoint_prefix)
print('Epoch {} Loss {:.4f}'.format(epoch + 1,
total_loss / num_batches))
print('Time taken for 1 epoch {} sec\n'.format(time.time() - start))
Теперь я хочу восстановить для опыта эту контрольную точку и начать обучение оттуда, но я не знаю как.
path="/content/drive/My Drive/training_checkpoints1/ckpt-9"
checkpoint.restore(path)
Результат
<tensorflow.python.training.tracking.util.CheckpointLoadStatus at 0x7f6653263048>