x = inputs
x = builder.conv2d(x, 32, 3, 2, 'VALID')
x = builder.conv2d(x, 32, 3, 1, 'VALID')
x = builder.conv2d(x, 64, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 3, 2, 'VALID')
x = builder.conv2d(x, 80, 1, 1, 'VALID')
x = builder.conv2d(x, 192, 3, 1, 'VALID')
x = builder.max_pooling2d(x, 3, 2, 'VALID')
x = inception_v3_a(builder, x, 32)
x = inception_v3_a(builder, x, 64)
x = inception_v3_a(builder, x, 64)
x = inception_v3_b(builder, x)
x = inception_v3_c(builder, x, 128)
x = inception_v3_c(builder, x, 160)
x = inception_v3_c(builder, x, 160)
x = inception_v3_c(builder, x, 192)
x = inception_v3_d(builder, x)
x = inception_v3_e(builder, x, 'AVG')
x = inception_v3_e(builder, x, 'MAX')
return builder.spatial_average2d(x)
if args['predict']:
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.predict(inception_v3, args)
else:
nvutils.train(inception_v3, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(inception_v3, args)
[('conv2d', n, 1, 1, 'SAME'), ('conv2d', p, 5, 1, 'SAME')],
[('mpool2d', 3, 1, 'SAME'), ('conv2d', q, 1, 1, 'SAME')]]
return builder.inception_module(x, 'incept_v1', cols)
builder = nvutils.LayerBuilder(tf.nn.relu, args['image_format'], training)
x = inputs
x = builder.conv2d(x, 64, 7, 2, 'SAME')
x = builder.max_pooling2d(x, 3, 2, 'SAME')
x = builder.conv2d(x, 64, 1, 1, 'SAME')
x = builder.conv2d(x, 192, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 3, 2, 'SAME')
x = inception_v1(builder, x, 64, 96, 128, 16, 32, 32)
x = inception_v1(builder, x, 128, 128, 192, 32, 96, 64)
x = builder.max_pooling2d(x, 3, 2, 'SAME')
x = inception_v1(builder, x, 192, 96, 208, 16, 48, 64)
x = inception_v1(builder, x, 160, 112, 224, 24, 64, 64)
x = inception_v1(builder, x, 128, 128, 256, 24, 64, 64)
x = inception_v1(builder, x, 112, 144, 288, 32, 64, 64)
x = inception_v1(builder, x, 256, 160, 320, 32, 128, 128)
x = builder.max_pooling2d(x, 3, 2, 'SAME')
x = inception_v1(builder, x, 256, 160, 320, 32, 128, 128)
x = inception_v1(builder, x, 384, 192, 384, 48, 128, 128)
x = builder.spatial_average2d(x)
return x
nvutils.train(googlenet, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(googlenet, args)
'num_iter': 90,
'checkpoint_secs': None,
'display_every': 10,
'iter_unit': 'epoch'
}
args, _ = nvutils.parse_cmdline(default_args)
def overfeat(inputs, training=False):
builder = nvutils.LayerBuilder(tf.nn.relu, args['image_format'], training)
x = inputs
x = builder.conv2d(x, 96, 11, 4, 'VALID')
x = builder.max_pooling2d(x, 2, 2, 'VALID')
x = builder.conv2d(x, 256, 5, 1, 'VALID')
x = builder.max_pooling2d(x, 2, 2, 'VALID')
x = builder.conv2d(x, 512, 3, 1, 'SAME')
x = builder.conv2d(x, 1024, 3, 1, 'SAME')
x = builder.conv2d(x, 1024, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 2, 2, 'VALID')
x = builder.flatten2d(x)
x = builder.dense(x, 3072)
x = builder.dense(x, 4096)
return x
nvutils.train(overfeat, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(overfeat, args)
return x
residual_scale = 0.2
x = inputs
x = builder.conv2d(x, 32, 3, 2, 'VALID')
x = builder.conv2d(x, 32, 3, 1, 'VALID')
x = builder.conv2d(x, 64, 3, 1, 'SAME')
x = inception_v4_sa(x)
x = inception_v4_sb(x)
x = inception_v4_sc(x)
for _ in range(5):
x = builder.residual2d(x, inception_resnet_v2_a, scale=residual_scale)
x = inception_v4_ra(x, 256, 256, 384, 384)
for _ in range(10):
x = builder.residual2d(x, inception_resnet_v2_b, scale=residual_scale)
x = inception_resnet_v2_rb(x)
for _ in range(5):
x = builder.residual2d(x, inception_resnet_v2_c, scale=residual_scale)
x = builder.spatial_average2d(x)
x = builder.dropout(x, 0.8)
return x
if args['predict']:
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.predict(inception_resnet_v2, args)
else:
nvutils.train(inception_resnet_v2, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(inception_resnet_v2, args)
x = builder.conv2d(x, 512, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 2, 2)
x = builder.flatten2d(x)
x = builder.dense(x, 4096)
x = builder.dense(x, 4096)
return x
def vgg(inputs, training=False):
"""Visual Geometry Group's family of models
https://arxiv.org/abs/1409.1556
"""
builder = nvutils.LayerBuilder(tf.nn.relu, args['image_format'], training)
if flags.layers == 11:
return inference_vgg_impl(builder, inputs, [1, 1, 2, 2, 2]) # A
elif flags.layers == 13:
return inference_vgg_impl(builder, inputs, [2, 2, 2, 2, 2]) # B
elif flags.layers == 16:
return inference_vgg_impl(builder, inputs, [2, 2, 3, 3, 3]) # D
elif flags.layers == 19:
return inference_vgg_impl(builder, inputs, [2, 2, 4, 4, 4]) # E
else:
raise ValueError("Invalid nlayer (%i); must be one of: 11,13,16,19" %
flags.layers)
nvutils.train(vgg, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(vgg, args)
https://arxiv.org/abs/1512.03385
"""
builder = nvutils.LayerBuilder(tf.nn.relu,
args['image_format'],
training,
use_batch_norm=True)
if flags.layers == 18:
return inference_resnet_v1_impl(builder,
inputs, [2, 2, 2, 2],
basic=True)
elif flags.layers == 34:
return inference_resnet_v1_impl(builder,
inputs, [3, 4, 6, 3],
basic=True)
elif flags.layers == 50:
return inference_resnet_v1_impl(builder, inputs, [3, 4, 6, 3])
elif flags.layers == 101:
return inference_resnet_v1_impl(builder, inputs, [3, 4, 23, 3])
elif flags.layers == 152:
return inference_resnet_v1_impl(builder, inputs, [3, 8, 36, 3])
else:
raise ValueError(
"Invalid layer count (%i); must be one of: 18,34,50,101,152" %
flags.layers)
nvutils.train(resnet_v1, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(resnet_v1, args)
default_args = {
'image_width': 224,
'image_height': 224,
'distort_color': False,
'momentum': 0.9,
'loss_scale': 128.0,
# The following params can be changed by cmdline options.
'image_format': 'channels_last',
'data_dir': None,
'data_idx_dir': None,
'batch_size': 256,
'num_iter': 300,
'iter_unit': 'batch',
'log_dir': None,
'export_dir': None,
'tensorboard_dir': None,
'display_every': 10,
'precision': 'fp16',
'dali_mode': None,
'use_xla': False,
'predict': False,
'use_dali': "GPU",
}
args = nvutils.parse_cmdline(default_args)
if args['predict']:
nvutils.predict(args)
else:
nvutils.train(resnet50, args)
'learning_rate_power': 2.0,
'weight_decay': 1e-4,
'loss_scale': None,
'larc_eta': None,
'larc_mode': None,
'num_iter': 500,
'checkpoint_secs': None,
'display_every': 10,
'iter_unit': 'batch'
}
args, _ = nvutils.parse_cmdline(default_args)
def trivial(inputs, training=False):
"""A trivial model for benchmarking input pipeline performance"""
builder = nvutils.LayerBuilder(tf.nn.relu, args['image_format'], training)
x = inputs
x = builder.flatten2d(x)
x = builder.dense_linear(x, 1)
return x
if args['predict']:
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.predict(trivial, args)
else:
nvutils.train(trivial, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(trivial, args)
def alexnet_owt(inputs, training):
"""Alexnet One Weird Trick model
https://arxiv.org/abs/1404.5997
"""
builder = nvutils.LayerBuilder(tf.nn.relu, args['image_format'], training)
# Note: VALID requires padding the images by 3 in width and height
x = inputs
x = builder.conv2d(x, 64, 11, 4, 'VALID')
x = builder.max_pooling2d(x, 3, 2)
x = builder.conv2d(x, 192, 5, 1, 'SAME')
x = builder.max_pooling2d(x, 3, 2)
x = builder.conv2d(x, 384, 3, 1, 'SAME')
x = builder.conv2d(x, 256, 3, 1, 'SAME')
x = builder.conv2d(x, 256, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 3, 2)
x = builder.flatten2d(x)
x = builder.dense(x, 4096)
x = builder.dropout(x)
x = builder.dense(x, 4096)
x = builder.dropout(x)
return x
if args['predict']:
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.predict(alexnet_owt, args)
else:
nvutils.train(alexnet_owt, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(alexnet_owt, args)
def xception_exit(inputs):
x = inputs
x = builder.activate(x)
x = builder.separable_conv2d(x, 728, 3, 1, 'SAME')
x = builder.separable_conv2d_linear(x, 1024, 3, 1, 'SAME')
x = builder.max_pooling2d(x, 3, 2, 'SAME')
return x
x = inputs
x = builder.conv2d(x, 32, 3, 2, 'VALID')
x = builder.conv2d(x, 64, 3, 1, 'VALID')
x = builder.residual2d(x, make_xception_entry(128, False), 128)
x = builder.residual2d(x, make_xception_entry(256), 256)
x = builder.residual2d(x, make_xception_entry(728), 728)
for _ in range(8):
x = builder.residual2d(x, xception_middle)
x = builder.residual2d(x, xception_exit, 1024)
x = builder.separable_conv2d(x, 1536, 3, 1, 'SAME')
x = builder.separable_conv2d(x, 2048, 3, 1, 'SAME')
x = builder.spatial_average2d(x)
# Note: Optional FC layer not included
x = builder.dropout(x, 0.5)
return x
nvutils.train(xception, args)
if args['log_dir'] is not None and args['data_dir'] is not None:
nvutils.validate(xception, args)
