def train_epoch(model,
optimizer,
dataset,
epoch_index: int,
batch_index: tf.Variable,
log_freq: int = 250,
writer=None):
to_fine_tune = [v for v in model.trainable_variables]
epoch_metrics = make_metric_dict(
["Localization", "Confidence", "WeightedTotal"])
era_metrics = make_metric_dict(
["Localization", "Confidence", "WeightedTotal"])
for (_, met) in era_metrics.items():
met.reset_states()
epoch_samples = 0
era_samples = 0
_log("Started new training epoch")
batch_start = batch_index.numpy()
for batch in dataset:
batch_index.assign_add(1)
epoch_samples += len(batch["image"])
era_samples += len(batch["image"])
keys = [
"cls_targets", "cls_weights", "reg_targets", "reg_weights",
"matched"
]
images, shapes = model.preprocess(batch["image"])
model.provide_groundtruth_direct(**{k: batch[k] for k in keys})
with tf.GradientTape() as tape:
prediction_dict = model.predict(images, shapes)
loss_dict = model.loss(prediction_dict)
gradients = tape.gradient(loss_dict["WeightedTotal"], to_fine_tune)
optimizer.apply_gradients(zip(gradients, to_fine_tune))
update_metric_dict(epoch_metrics, loss_dict)
update_metric_dict(era_metrics, loss_dict)
if (batch_index - batch_start) % log_freq == 0:
_log(f"Completed {batch_index - batch_start} batches")
if writer:
l_dict = metric2scalar_dict(
era_metrics,
prefix=f"Loss/Train/Last_{log_freq}_Batches",
v_func=lambda v: v / era_samples,
reset_states=True)
write_scalars(writer, l_dict, step=batch_index)
if writer:
l_dict = metric2scalar_dict(epoch_metrics,
prefix=f"Loss/Train/Epoch",
v_func=lambda v: v / epoch_samples,
reset_states=True)
write_scalars(writer, l_dict, step=epoch_index)
def _decay_weight_op(self, variable: tf.Variable, learning_rate: float, apply_state: dict):
"""apply the weight operation on variables"""
do_decay = self._do_use_weight_decay(variable.name)
if do_decay:
return variable.assign_add(
learning_rate * apply_state['weight_decay_rate'] * variable,
use_locking=self._use_locking
)
return tf.no_op()
floats = Variable([3.14, 2.72], dtype=tf.float64) ints = tf.Variable([1, 2, 3], tf.int32) complexs = tf.Variable([-1.2j, 1.3 - 4j], tf.complex64) # initialize var with shape print(tf.Variable(tf.constant(4.2, shape=(3, 3)))) # Change vars a = Variable(0.) b = a + 1 print(a) print(b) print(type(b)) a.assign_add(1) print(a) a.assign_sub(4) print(a) # Tensors # Constant tensor c = tf.constant([[1, 1, 1], [2, 3, 3], [4, 4, 4]]) print(c.dtype, c.shape) print(c.numpy()) d = tf.constant([[1, 1, 1], [2, 3, 3], [4, 4, 4]], dtype=tf.float32)
