Python tensorpack.models.regularize_cost() Examples

The following are 11 code examples of tensorpack.models.regularize_cost(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorpack.models , or try the search function .
Example #1
Source File: imagenet_utils.py    From ghostnet with Apache License 2.0 6 votes vote down vote up 
def build_graph(self, image, label):
        image = ImageNetModel.image_preprocess(image, bgr=self.image_bgr)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        print('self.label_smoothing', self.label_smoothing)
        loss = ImageNetModel.compute_loss_and_error(logits, label, self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      tf.contrib.layers.l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #2
Source File: imagenet_utils.py    From benchmarks with The Unlicense 6 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format == 'NCHW'
        image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      tf.contrib.layers.l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #3
Source File: imagenet_utils.py    From webvision-2.0-benchmarks with Apache License 2.0 6 votes vote down vote up 
def _build_graph(self, inputs):
        image, label = inputs
        image = ImageNetModel.image_preprocess(image, bgr=True)
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        loss = ImageNetModel.compute_loss_and_error(logits, label)

        if self.weight_decay > 0:
            wd_loss = regularize_cost('.*/W', tf.contrib.layers.l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            self.cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            self.cost = tf.identity(loss, name='cost')
            add_moving_summary(self.cost)
Example #4
Source File: imagenet_utils.py    From GroupNorm-reproduce with Apache License 2.0 6 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      tf.contrib.layers.l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #5
Source File: utils_tp.py    From imgclsmob with MIT License 5 votes vote down vote up 
def build_graph(self,
                    image,
                    label):

        image = self.image_preprocess(image)
        if is_channels_first(self.data_format):
            image = tf.transpose(image, [0, 3, 1, 2], name="image_transpose")

        # tf.summary.image('input_image_', image)
        # tf.summary.tensor_summary('input_tensor_', image)
        # with tf.name_scope('tmp1_summaries'):
        #     add_tensor_summary(image, ['histogram', 'rms', 'sparsity'], name='tmp1_tensor')

        is_training = get_current_tower_context().is_training
        logits = self.model_lambda(
            x=image,
            training=is_training)
        loss = ImageNetModel.compute_loss_and_error(
            logits=logits,
            label=label,
            label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(
                regex=self.weight_decay_pattern,
                func=tf.contrib.layers.l2_regularizer(self.weight_decay),
                name="l2_regularize_loss")
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name="cost")
        else:
            total_cost = tf.identity(loss, name="cost")
            add_moving_summary(total_cost)

        if self.loss_scale != 1.0:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #6
Source File: imagenet_utils.py    From LQ-Nets with MIT License 5 votes vote down vote up 
def _build_graph(self, inputs):
        image, label = inputs
        image = ImageNetModel.image_preprocess(image, bgr=self.image_bgr)
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        loss = ImageNetModel.compute_loss_and_error(logits, label)
        wd_loss = regularize_cost(self.weight_decay_pattern,
                                  tf.contrib.layers.l2_regularizer(self.weight_decay),
                                  name='l2_regularize_loss')
        add_moving_summary(loss, wd_loss)
        self.cost = tf.add_n([loss, wd_loss], name='cost')
Example #7
Source File: imagenet_utils.py    From tensorpack with Apache License 2.0 5 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        tf.nn.softmax(logits, name='prob')
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #8
Source File: imagenet_utils.py    From tensorpack with Apache License 2.0 5 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        tf.nn.softmax(logits, name='prob')
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #9
Source File: imagenet_utils.py    From tensorpack with Apache License 2.0 5 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        tf.nn.softmax(logits, name='prob')
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #10
Source File: imagenet_utils.py    From tensorpack with Apache License 2.0 5 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        tf.nn.softmax(logits, name='prob')
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost
Example #11
Source File: imagenet_utils.py    From tensorpack with Apache License 2.0 5 votes vote down vote up 
def build_graph(self, image, label):
        image = self.image_preprocess(image)
        assert self.data_format in ['NCHW', 'NHWC']
        if self.data_format == 'NCHW':
            image = tf.transpose(image, [0, 3, 1, 2])

        logits = self.get_logits(image)
        tf.nn.softmax(logits, name='prob')
        loss = ImageNetModel.compute_loss_and_error(
            logits, label, label_smoothing=self.label_smoothing)

        if self.weight_decay > 0:
            wd_loss = regularize_cost(self.weight_decay_pattern,
                                      l2_regularizer(self.weight_decay),
                                      name='l2_regularize_loss')
            add_moving_summary(loss, wd_loss)
            total_cost = tf.add_n([loss, wd_loss], name='cost')
        else:
            total_cost = tf.identity(loss, name='cost')
            add_moving_summary(total_cost)

        if self.loss_scale != 1.:
            logger.info("Scaling the total loss by {} ...".format(self.loss_scale))
            return total_cost * self.loss_scale
        else:
            return total_cost