add v2 API for imagenet models

image_classification/alexnet.py

+import paddle.v2 as paddle
+
+__all__ = ['alexnet']
+
+
+def alexnet(input):
+    conv1 = paddle.layer.img_conv(
+        input=input,
+        filter_size=11,
+        num_channels=3,
+        num_filters=96,
+        stride=4,
+        padding=1)
+    cmrnorm1 = paddle.layer.img_cmrnorm(
+        input=conv1, size=5, scale=0.0001, power=0.75)
+    pool1 = paddle.layer.img_pool(input=cmrnorm1, pool_size=3, stride=2)
+
+    conv2 = paddle.layer.img_conv(
+        input=pool1,
+        filter_size=5,
+        num_filters=256,
+        stride=1,
+        padding=2,
+        groups=1)
+    cmrnorm2 = paddle.layer.img_cmrnorm(
+        input=conv2, size=5, scale=0.0001, power=0.75)
+    pool2 = paddle.layer.img_pool(input=cmrnorm2, pool_size=3, stride=2)
+
+    pool3 = paddle.networks.img_conv_group(
+        input=pool2,
+        pool_size=3,
+        pool_stride=2,
+        conv_num_filter=[384, 384, 256],
+        conv_filter_size=3,
+        pool_type=paddle.pooling.Max())
+
+    fc1 = paddle.layer.fc(
+        input=pool3,
+        size=4096,
+        act=paddle.activation.Relu(),
+        layer_attr=paddle.attr.Extra(drop_rate=0.5))
+    fc2 = paddle.layer.fc(
+        input=fc1,
+        size=4096,
+        act=paddle.activation.Relu(),
+        layer_attr=paddle.attr.Extra(drop_rate=0.5))
+
+    return fc2

image_classification/googlenet.py

+import paddle.v2 as paddle
+
+__all__ = ['googlenet']
+
+
+def inception(name, input, channels, filter1, filter3R, filter3, filter5R,
+              filter5, proj):
+    cov1 = paddle.layer.conv_projection(
+        input=input,
+        filter_size=1,
+        num_channels=channels,
+        num_filters=filter1,
+        stride=1,
+        padding=0)
+
+    cov3r = paddle.layer.img_conv(
+        name=name + '_3r',
+        input=input,
+        filter_size=1,
+        num_channels=channels,
+        num_filters=filter3R,
+        stride=1,
+        padding=0)
+    cov3 = paddle.layer.conv_projection(
+        input=cov3r, filter_size=3, num_filters=filter3, stride=1, padding=1)
+
+    cov5r = paddle.layer.img_conv(
+        name=name + '_5r',
+        input=input,
+        filter_size=1,
+        num_channels=channels,
+        num_filters=filter5R,
+        stride=1,
+        padding=0)
+    cov5 = paddle.layer.conv_projection(
+        input=cov5r, filter_size=5, num_filters=filter5, stride=1, padding=2)
+
+    pool1 = paddle.layer.img_pool(
+        name=name + '_max',
+        input=input,
+        pool_size=3,
+        num_channels=channels,
+        stride=1,
+        padding=1)
+    covprj = paddle.layer.conv_projection(
+        input=pool1, filter_size=1, num_filters=proj, stride=1, padding=0)
+
+    cat = paddle.layer.concat(
+        name=name,
+        input=[cov1, cov3, cov5, covprj],
+        bias_attr=True,
+        act=paddle.activation.Relu())
+    return cat
+
+
+def googlenet(input):
+    # stage 1
+    conv1 = paddle.layer.img_conv(
+        name="conv1",
+        input=input,
+        filter_size=7,
+        num_channels=3,
+        num_filters=64,
+        stride=2,
+        padding=3)
+    pool1 = paddle.layer.img_pool(
+        name="pool1", input=conv1, pool_size=3, num_channels=64, stride=2)
+
+    # stage 2
+    conv2_1 = paddle.layer.img_conv(
+        name="conv2_1",
+        input=pool1,
+        filter_size=1,
+        num_filters=64,
+        stride=1,
+        padding=0)
+    conv2_2 = paddle.layer.img_conv(
+        name="conv2_2",
+        input=conv2_1,
+        filter_size=3,
+        num_filters=192,
+        stride=1,
+        padding=1)
+    pool2 = paddle.layer.img_pool(
+        name="pool2", input=conv2_2, pool_size=3, num_channels=192, stride=2)
+
+    # stage 3
+    ince3a = inception("ince3a", pool2, 192, 64, 96, 128, 16, 32, 32)
+    ince3b = inception("ince3b", ince3a, 256, 128, 128, 192, 32, 96, 64)
+    pool3 = paddle.layer.img_pool(
+        name="pool3", input=ince3b, num_channels=480, pool_size=3, stride=2)
+
+    # stage 4
+    ince4a = inception("ince4a", pool3, 480, 192, 96, 208, 16, 48, 64)
+    ince4b = inception("ince4b", ince4a, 512, 160, 112, 224, 24, 64, 64)
+    ince4c = inception("ince4c", ince4b, 512, 128, 128, 256, 24, 64, 64)
+    ince4d = inception("ince4d", ince4c, 512, 112, 144, 288, 32, 64, 64)
+    ince4e = inception("ince4e", ince4d, 528, 256, 160, 320, 32, 128, 128)
+    pool4 = paddle.layer.img_pool(
+        name="pool4", input=ince4e, num_channels=832, pool_size=3, stride=2)
+
+    # stage 5
+    ince5a = inception("ince5a", pool4, 832, 256, 160, 320, 32, 128, 128)
+    ince5b = inception("ince5b", ince5a, 832, 384, 192, 384, 48, 128, 128)
+    pool5 = paddle.layer.img_pool(
+        name="pool5",
+        input=ince5b,
+        num_channels=1024,
+        pool_size=7,
+        stride=7,
+        pool_type=paddle.pooling.Avg())
+    dropout = paddle.layer.addto(
+        input=pool5,
+        layer_attr=paddle.attr.Extra(drop_rate=0.4),
+        act=paddle.activation.Linear())
+
+    # fc for output 1
+    pool_o1 = paddle.layer.img_pool(
+        name="pool_o1",
+        input=ince4a,
+        num_channels=512,
+        pool_size=5,
+        stride=3,
+        pool_type=paddle.pooling.Avg())
+    conv_o1 = paddle.layer.img_conv(
+        name="conv_o1",
+        input=pool_o1,
+        filter_size=1,
+        num_filters=128,
+        stride=1,
+        padding=0)
+    fc_o1 = paddle.layer.fc(
+        name="fc_o1",
+        input=conv_o1,
+        size=1024,
+        layer_attr=paddle.attr.Extra(drop_rate=0.7),
+        act=paddle.activation.Relu())
+
+    # fc for output 2
+    pool_o2 = paddle.layer.img_pool(
+        name="pool_o2",
+        input=ince4d,
+        num_channels=528,
+        pool_size=5,
+        stride=3,
+        pool_type=paddle.pooling.Avg())
+    conv_o2 = paddle.layer.img_conv(
+        name="conv_o2",
+        input=pool_o2,
+        filter_size=1,
+        num_filters=128,
+        stride=1,
+        padding=0)
+    fc_o2 = paddle.layer.fc(
+        name="fc_o2",
+        input=conv_o2,
+        size=1024,
+        layer_attr=paddle.attr.Extra(drop_rate=0.7),
+        act=paddle.activation.Relu())
+
+    return dropout, fc_o1, fc_o2

image_classification/resnet.py

+import paddle.v2 as paddle
+
+__all__ = ['resnet_imagenet', 'resnet_cifar10']
+
+
+def conv_bn_layer(input,
+                  ch_out,
+                  filter_size,
+                  stride,
+                  padding,
+                  active_type=paddle.activation.Relu(),
+                  ch_in=None):
+    tmp = paddle.layer.img_conv(
+        input=input,
+        filter_size=filter_size,
+        num_channels=ch_in,
+        num_filters=ch_out,
+        stride=stride,
+        padding=padding,
+        act=paddle.activation.Linear(),
+        bias_attr=False)
+    return paddle.layer.batch_norm(input=tmp, act=active_type)
+
+
+def shortcut(input, n_out, stride, b_projection):
+    if b_projection:
+        return conv_bn_layer(input, n_out, 1, stride, 0,
+                             paddle.activation.Linear())
+    else:
+        return input
+
+
+def basicblock(input, ch_out, stride, b_projection):
+    # TODO: bug fix for ch_in = input.num_filters
+    conv1 = conv_bn_layer(input, ch_out, 3, stride, 1)
+    conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1, paddle.activation.Linear())
+    short = shortcut(input, ch_out, stride, b_projection)
+    return paddle.layer.addto(
+        input=[conv2, short], act=paddle.activation.Relu())
+
+
+def bottleneck(input, ch_out, stride, b_projection):
+    # TODO: bug fix for ch_in = input.num_filters
+    conv1 = conv_bn_layer(input, ch_out, 1, stride, 0)
+    conv2 = conv_bn_layer(conv1, ch_out, 3, 1, 1)
+    conv3 = conv_bn_layer(conv2, ch_out * 4, 1, 1, 0,
+                          paddle.activation.Linear())
+    short = shortcut(input, ch_out * 4, stride, b_projection)
+    return paddle.layer.addto(
+        input=[conv3, short], act=paddle.activation.Relu())
+
+
+def layer_warp(block_func, input, features, count, stride):
+    conv = block_func(input, features, stride, True)
+    for i in range(1, count):
+        conv = block_func(conv, features, 1, False)
+    return conv
+
+
+def resnet_imagenet(input, depth=50):
+    cfg = {
+        18: ([2, 2, 2, 1], basicblock),
+        34: ([3, 4, 6, 3], basicblock),
+        50: ([3, 4, 6, 3], bottleneck),
+        101: ([3, 4, 23, 3], bottleneck),
+        152: ([3, 8, 36, 3], bottleneck)
+    }
+    stages, block_func = cfg[depth]
+    conv1 = conv_bn_layer(
+        input, ch_in=3, ch_out=64, filter_size=7, stride=2, padding=3)
+    pool1 = paddle.layer.img_pool(input=conv1, pool_size=3, stride=2)
+    res1 = layer_warp(block_func, pool1, 64, stages[0], 1)
+    res2 = layer_warp(block_func, res1, 128, stages[1], 2)
+    res3 = layer_warp(block_func, res2, 256, stages[2], 2)
+    res4 = layer_warp(block_func, res3, 512, stages[3], 2)
+    pool2 = paddle.layer.img_pool(
+        input=res4, pool_size=7, stride=1, pool_type=paddle.pooling.Avg())
+    return pool2
+
+
+def resnet_cifar10(input, depth=32):
+    # depth should be one of 20, 32, 44, 56, 110, 1202
+    assert (depth - 2) % 6 == 0
+    n = (depth - 2) / 6
+    nStages = {16, 64, 128}
+    conv1 = conv_bn_layer(
+        input, ch_in=3, ch_out=16, filter_size=3, stride=1, padding=1)
+    res1 = layer_warp(basicblock, conv1, 16, n, 1)
+    res2 = layer_warp(basicblock, res1, 32, n, 2)
+    res3 = layer_warp(basicblock, res2, 64, n, 2)
+    pool = paddle.layer.img_pool(
+        input=res3, pool_size=8, stride=1, pool_type=paddle.pooling.Avg())
+    return pool

image_classification/train.py

-# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License
-
 import gzip
-
 import paddle.v2 as paddle
 import reader
 import vgg
+import resnet
+import alexnet
+import googlenet
+import argparse
+import os
 
 DATA_DIM = 3 * 224 * 224
-CLASS_DIM = 1000
+CLASS_DIM = 100
 BATCH_SIZE = 128
 
 
 def main():
+    # parse the argument
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        'data_dir',
+        help='The data directory which contains train.list and val.list')
+    parser.add_argument(
+        'model',
+        help='The model for image classification',
+        choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
+    args = parser.parse_args()
 
     # PaddlePaddle init
-    paddle.init(use_gpu=True, trainer_count=4)
+    paddle.init(use_gpu=True, trainer_count=1)
 
     image = paddle.layer.data(
         name="image", type=paddle.data_type.dense_vector(DATA_DIM))
     lbl = paddle.layer.data(
         name="label", type=paddle.data_type.integer_value(CLASS_DIM))
+
+    extra_layers = None
+    if args.model == 'alexnet':
+        net = alexnet.alexnet(image)
+    elif args.model == 'vgg13':
         net = vgg.vgg13(image)
+    elif args.model == 'vgg16':
+        net = vgg.vgg16(image)
+    elif args.model == 'vgg19':
+        net = vgg.vgg19(image)
+    elif args.model == 'resnet':
+        net = resnet.resnet_imagenet(image)
+    elif args.model == 'googlenet':
+        net, fc_o1, fc_o2 = googlenet.googlenet(image)
+        out1 = paddle.layer.fc(
+            input=fc_o1, size=CLASS_DIM, act=paddle.activation.Softmax())
+        loss1 = paddle.layer.cross_entropy_cost(
+            input=out1, label=lbl, coeff=0.3)
+        paddle.evaluator.classification_error(input=out1, label=lbl)
+        out2 = paddle.layer.fc(
+            input=fc_o2, size=CLASS_DIM, act=paddle.activation.Softmax())
+        loss2 = paddle.layer.cross_entropy_cost(
+            input=out2, label=lbl, coeff=0.3)
+        paddle.evaluator.classification_error(input=out2, label=lbl)
+        extra_layers = [loss1, loss2]
+
     out = paddle.layer.fc(
         input=net, size=CLASS_DIM, act=paddle.activation.Softmax())
     cost = paddle.layer.classification_cost(input=out, label=lbl)
@@ -45,16 +70,19 @@ def main():
         momentum=0.9,
         regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
                                                          BATCH_SIZE),
-        learning_rate=0.01 / BATCH_SIZE,
+        learning_rate=0.001 / BATCH_SIZE,
         learning_rate_decay_a=0.1,
         learning_rate_decay_b=128000 * 35,
         learning_rate_schedule="discexp", )
 
     train_reader = paddle.batch(
-        paddle.reader.shuffle(reader.test_reader("train.list"), buf_size=1000),
+        paddle.reader.shuffle(
+            reader.test_reader(os.path.join(args.data_dir, 'train.list')),
+            buf_size=1000),
         batch_size=BATCH_SIZE)
     test_reader = paddle.batch(
-        reader.train_reader("test.list"), batch_size=BATCH_SIZE)
+        reader.train_reader(os.path.join(args.data_dir, 'val.list')),
+        batch_size=BATCH_SIZE)
 
     # End batch and end pass event handler
     def event_handler(event):
@@ -71,7 +99,10 @@ def main():
 
     # Create trainer
     trainer = paddle.trainer.SGD(
-        cost=cost, parameters=parameters, update_equation=optimizer)
+        cost=cost,
+        parameters=parameters,
+        update_equation=optimizer,
+        extra_layers=extra_layers)
 
     trainer.train(
         reader=train_reader, num_passes=200, event_handler=event_handler)