Merge pull request #133 from PaddlePaddle/develop_alexnet

add AlexNet

paddlex/__init__.py

@@ -53,4 +53,4 @@ log_level = 2
 
 from . import interpret
 
-__version__ = '1.0.5'
+__version__ = '1.0.6'

paddlex/cls.py

@@ -37,5 +37,6 @@ DenseNet161 = cv.models.DenseNet161
 DenseNet201 = cv.models.DenseNet201
 ShuffleNetV2 = cv.models.ShuffleNetV2
 HRNet_W18 = cv.models.HRNet_W18
+AlexNet = cv.models.AlexNet
 
 transforms = cv.transforms.cls_transforms

paddlex/cv/models/__init__.py

@@ -35,6 +35,7 @@ from .classifier import DenseNet161
 from .classifier import DenseNet201
 from .classifier import ShuffleNetV2
 from .classifier import HRNet_W18
+from .classifier import AlexNet
 from .base import BaseAPI
 from .yolo_v3 import YOLOv3
 from .faster_rcnn import FasterRCNN

paddlex/cv/models/base.py

@@ -221,8 +221,8 @@ class BaseAPI:
             logging.info(
                 "Load pretrain weights from {}.".format(pretrain_weights),
                 use_color=True)
-            paddlex.utils.utils.load_pretrain_weights(
-                self.exe, self.train_prog, pretrain_weights, fuse_bn)
+            paddlex.utils.utils.load_pretrain_weights(self.exe, self.train_prog,
+                                                      pretrain_weights, fuse_bn)
         # 进行裁剪
         if sensitivities_file is not None:
             import paddleslim
@@ -262,6 +262,7 @@ class BaseAPI:
 
         info['_Attributes']['num_classes'] = self.num_classes
         info['_Attributes']['labels'] = self.labels
+        info['_Attributes']['fixed_input_shape'] = self.fixed_input_shape
         try:
             primary_metric_key = list(self.eval_metrics.keys())[0]
             primary_metric_value = float(self.eval_metrics[primary_metric_key])
@@ -325,9 +326,7 @@ class BaseAPI:
         logging.info("Model saved in {}.".format(save_dir))
 
     def export_inference_model(self, save_dir):
-        test_input_names = [
-            var.name for var in list(self.test_inputs.values())
-        ]
+        test_input_names = [var.name for var in list(self.test_inputs.values())]
         test_outputs = list(self.test_outputs.values())
         if self.__class__.__name__ == 'MaskRCNN':
             from paddlex.utils.save import save_mask_inference_model
@@ -364,8 +363,7 @@ class BaseAPI:
 
         # 模型保存成功的标志
         open(osp.join(save_dir, '.success'), 'w').close()
-        logging.info("Model for inference deploy saved in {}.".format(
-            save_dir))
+        logging.info("Model for inference deploy saved in {}.".format(save_dir))
 
     def train_loop(self,
                    num_epochs,
@@ -489,13 +487,11 @@ class BaseAPI:
                         eta = ((num_epochs - i) * total_num_steps - step - 1
                                ) * avg_step_time
                     if time_eval_one_epoch is not None:
-                        eval_eta = (
-                            total_eval_times - i // save_interval_epochs
-                        ) * time_eval_one_epoch
+                        eval_eta = (total_eval_times - i // save_interval_epochs
+                                    ) * time_eval_one_epoch
                     else:
-                        eval_eta = (
-                            total_eval_times - i // save_interval_epochs
-                        ) * total_num_steps_eval * avg_step_time
+                        eval_eta = (total_eval_times - i // save_interval_epochs
+                                    ) * total_num_steps_eval * avg_step_time
                     eta_str = seconds_to_hms(eta + eval_eta)
 
                     logging.info(

paddlex/cv/models/classifier.py

@@ -48,6 +48,8 @@ class BaseClassifier(BaseAPI):
         self.fixed_input_shape = None
 
     def build_net(self, mode='train'):
+        if self.__class__.__name__ == "AlexNet":
+            assert self.fixed_input_shape is not None, "In AlexNet, input_shape should be defined, e.g. model = paddlex.cls.AlexNet(num_classes=1000, input_shape=[224, 224])"
         if self.fixed_input_shape is not None:
             input_shape = [
                 None, 3, self.fixed_input_shape[1], self.fixed_input_shape[0]
@@ -427,3 +429,10 @@ class HRNet_W18(BaseClassifier):
     def __init__(self, num_classes=1000):
         super(HRNet_W18, self).__init__(
             model_name='HRNet_W18', num_classes=num_classes)
+
+
+class AlexNet(BaseClassifier):
+    def __init__(self, num_classes=1000, input_shape=None):
+        super(AlexNet, self).__init__(
+            model_name='AlexNet', num_classes=num_classes)
+        self.fixed_input_shape = input_shape

paddlex/cv/models/load_model.py

@@ -41,7 +41,16 @@ def load_model(model_dir, fixed_input_shape=None):
     if 'model_name' in info['_init_params']:
         del info['_init_params']['model_name']
     model = getattr(paddlex.cv.models, info['Model'])(**info['_init_params'])
+
     model.fixed_input_shape = fixed_input_shape
+    if '_Attributes' in info:
+        if 'fixed_input_shape' in info['_Attributes']:
+            fixed_input_shape = info['_Attributes']['fixed_input_shape']
+            if fixed_input_shape is not None:
+                logging.info("Model already has fixed_input_shape with {}".
+                             format(fixed_input_shape))
+                model.fixed_input_shape = fixed_input_shape
+
     if status == "Normal" or \
             status == "Prune" or status == "fluid.save":
         startup_prog = fluid.Program()
@@ -88,8 +97,8 @@ def load_model(model_dir, fixed_input_shape=None):
                 model.model_type, info['Transforms'], info['BatchTransforms'])
             model.eval_transforms = copy.deepcopy(model.test_transforms)
         else:
-            model.test_transforms = build_transforms(
-                model.model_type, info['Transforms'], to_rgb)
+            model.test_transforms = build_transforms(model.model_type,
+                                                     info['Transforms'], to_rgb)
             model.eval_transforms = copy.deepcopy(model.test_transforms)
 
     if '_Attributes' in info:

paddlex/cv/models/utils/pretrain_weights.py

@@ -70,6 +70,8 @@ image_pretrain = {
     'https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W60_C_pretrained.tar',
     'HRNet_W64':
     'https://paddle-imagenet-models-name.bj.bcebos.com/HRNet_W64_C_pretrained.tar',
+    'AlexNet':
+    'http://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar'
 }
 
 coco_pretrain = {
@@ -99,10 +101,12 @@ def get_pretrain_weights(flag, model_type, backbone, save_dir):
                 backbone = 'DetResNet50'
         assert backbone in image_pretrain, "There is not ImageNet pretrain weights for {}, you may try COCO.".format(
             backbone)
-        #        url = image_pretrain[backbone]
-        #        fname = osp.split(url)[-1].split('.')[0]
-        #        paddlex.utils.download_and_decompress(url, path=new_save_dir)
-        #        return osp.join(new_save_dir, fname)
+
+        if backbone == 'AlexNet':
+            url = image_pretrain[backbone]
+            fname = osp.split(url)[-1].split('.')[0]
+            paddlex.utils.download_and_decompress(url, path=new_save_dir)
+            return osp.join(new_save_dir, fname)
         try:
             hub.download(backbone, save_path=new_save_dir)
         except Exception as e:

paddlex/cv/nets/__init__.py

@@ -24,6 +24,7 @@ from .xception import Xception
 from .densenet import DenseNet
 from .shufflenet_v2 import ShuffleNetV2
 from .hrnet import HRNet
+from .alexnet import AlexNet
 
 
 def resnet18(input, num_classes=1000):
@@ -153,3 +154,8 @@ def shufflenetv2(input, num_classes=1000):
 def hrnet_w18(input, num_classes=1000):
     model = HRNet(width=18, num_classes=num_classes)
     return model(input)
+
+
+def alexnet(input, num_classes=1000):
+    model = AlexNet(num_classes=num_classes)
+    return model(input)

paddlex/cv/nets/alexnet.py

+#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
+#
+#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.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import math
+
+import paddle
+import paddle.fluid as fluid
+
+
+class AlexNet():
+    def __init__(self, num_classes=1000):
+        assert num_classes is not None, "In AlextNet, num_classes cannot be None"
+        self.num_classes = num_classes
+
+    def __call__(self, input):
+        stdv = 1.0 / math.sqrt(input.shape[1] * 11 * 11)
+        layer_name = [
+            "conv1", "conv2", "conv3", "conv4", "conv5", "fc6", "fc7", "fc8"
+        ]
+        conv1 = fluid.layers.conv2d(
+            input=input,
+            num_filters=64,
+            filter_size=11,
+            stride=4,
+            padding=2,
+            groups=1,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[0] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[0] + "_weights"))
+        pool1 = fluid.layers.pool2d(
+            input=conv1,
+            pool_size=3,
+            pool_stride=2,
+            pool_padding=0,
+            pool_type='max')
+
+        stdv = 1.0 / math.sqrt(pool1.shape[1] * 5 * 5)
+        conv2 = fluid.layers.conv2d(
+            input=pool1,
+            num_filters=192,
+            filter_size=5,
+            stride=1,
+            padding=2,
+            groups=1,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[1] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[1] + "_weights"))
+        pool2 = fluid.layers.pool2d(
+            input=conv2,
+            pool_size=3,
+            pool_stride=2,
+            pool_padding=0,
+            pool_type='max')
+
+        stdv = 1.0 / math.sqrt(pool2.shape[1] * 3 * 3)
+        conv3 = fluid.layers.conv2d(
+            input=pool2,
+            num_filters=384,
+            filter_size=3,
+            stride=1,
+            padding=1,
+            groups=1,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[2] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[2] + "_weights"))
+
+        stdv = 1.0 / math.sqrt(conv3.shape[1] * 3 * 3)
+        conv4 = fluid.layers.conv2d(
+            input=conv3,
+            num_filters=256,
+            filter_size=3,
+            stride=1,
+            padding=1,
+            groups=1,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[3] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[3] + "_weights"))
+
+        stdv = 1.0 / math.sqrt(conv4.shape[1] * 3 * 3)
+        conv5 = fluid.layers.conv2d(
+            input=conv4,
+            num_filters=256,
+            filter_size=3,
+            stride=1,
+            padding=1,
+            groups=1,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[4] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[4] + "_weights"))
+        pool5 = fluid.layers.pool2d(
+            input=conv5,
+            pool_size=3,
+            pool_stride=2,
+            pool_padding=0,
+            pool_type='max')
+
+        drop6 = fluid.layers.dropout(x=pool5, dropout_prob=0.5)
+        stdv = 1.0 / math.sqrt(drop6.shape[1] * drop6.shape[2] *
+                               drop6.shape[3] * 1.0)
+
+        fc6 = fluid.layers.fc(
+            input=drop6,
+            size=4096,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[5] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[5] + "_weights"))
+        drop7 = fluid.layers.dropout(x=fc6, dropout_prob=0.5)
+        stdv = 1.0 / math.sqrt(drop7.shape[1] * 1.0)
+
+        fc7 = fluid.layers.fc(
+            input=drop7,
+            size=4096,
+            act='relu',
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[6] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[6] + "_weights"))
+
+        stdv = 1.0 / math.sqrt(fc7.shape[1] * 1.0)
+        out = fluid.layers.fc(
+            input=fc7,
+            size=self.num_classes,
+            bias_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[7] + "_offset"),
+            param_attr=fluid.param_attr.ParamAttr(
+                initializer=fluid.initializer.Uniform(-stdv, stdv),
+                name=layer_name[7] + "_weights"))
+        return out

setup.py

@@ -19,7 +19,7 @@ long_description = "PaddleX. A end-to-end deeplearning model development toolkit
 
 setuptools.setup(
     name="paddlex",
-    version='1.0.5',
+    version='1.0.6',
     author="paddlex",
     author_email="paddlex@baidu.com",
     description=long_description,