Merge pull request #467 from tensorlayer/release-1.8.4rc0

[release] 1.8.4rc1

Author: wagamamaz

README.md

@@ -24,6 +24,7 @@ TensorLayer is a deep learning and reinforcement learning library on top of [Ten
 - Useful links: [Documentation](http://tensorlayer.readthedocs.io), [Examples](http://tensorlayer.readthedocs.io/en/latest/user/example.html), [中文文档](https://tensorlayercn.readthedocs.io), [中文书](http://www.broadview.com.cn/book/5059)
 
 # News
+* [05 Apr] Release [models APIs](http://tensorlayer.readthedocs.io/en/latest/modules/models.html#) for well-known pretained networks.
 * [18 Mar] Release experimental APIs for binary networks.
 * [18 Jan] [《深度学习：一起玩转TensorLayer》](http://www.broadview.com.cn/book/5059) (Deep Learning using TensorLayer)
 * [17 Dec] Release experimental APIs for distributed training (by [TensorPort](https://tensorport.com)). See [tiny example](https://github.com/zsdonghao/tensorlayer/blob/master/example/tutorial_mnist_distributed.py).

docs/conf.py

@@ -67,9 +67,9 @@
 # built documents.
 #
 # The short X.Y version.
-version = '1.8.4rc0'
+version = '1.8.4rc1'
 # The full version, including alpha/beta/rc tags.
-release = '1.8.4rc0'
+release = '1.8.4rc1'
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -143,7 +143,7 @@
 # The name for this set of Sphinx documents.
 # "<project> v<release> documentation" by default.
 #
-# html_title = 'TensorLayer v1.8.4rc0'
+# html_title = 'TensorLayer v1.8.4rc1'
 
 # A shorter title for the navigation bar.  Default is the same as html_title.
 #

example/tutorial_mnist.py

@@ -119,13 +119,13 @@ def main_test_layers(model='relu'):
                 n_batch += 1
             print("   val loss: %f" % (val_loss / n_batch))
             print("   val acc: %f" % (val_acc / n_batch))
-            try:
-                # You can visualize the weight of 1st hidden layer as follow.
-                tl.vis.draw_weights(network.all_params[0].eval(), second=10, saveable=True, shape=[28, 28], name='w1_' + str(epoch + 1), fig_idx=2012)
-                # You can also save the weight of 1st hidden layer to .npz file.
-                # tl.files.save_npz([network.all_params[0]] , name='w1'+str(epoch+1)+'.npz')
-            except:  # pylint: disable=bare-except
-                print("You should change vis.draw_weights(), if you want to save the feature images for different dataset")
+            # try:
+            #     # You can visualize the weight of 1st hidden layer as follow.
+            #     tl.vis.draw_weights(network.all_params[0].eval(), second=10, saveable=True, shape=[28, 28], name='w1_' + str(epoch + 1), fig_idx=2012)
+            #     # You can also save the weight of 1st hidden layer to .npz file.
+            #     # tl.files.save_npz([network.all_params[0]] , name='w1'+str(epoch+1)+'.npz')
+            # except:  # pylint: disable=bare-except
+            #     print("You should change vis.draw_weights(), if you want to save the feature images for different dataset")
 
     print('Evaluation')
     test_loss, test_acc, n_batch = 0, 0, 0
@@ -306,11 +306,11 @@ def main_test_stacked_denoise_AE(model='relu'):
                 n_batch += 1
             print("   val loss: %f" % (val_loss / n_batch))
             print("   val acc: %f" % (val_acc / n_batch))
-            try:
-                # visualize the 1st hidden layer during fine-tune
-                tl.vis.draw_weights(network.all_params[0].eval(), second=10, saveable=True, shape=[28, 28], name='w1_' + str(epoch + 1), fig_idx=2012)
-            except:  # pylint: disable=bare-except
-                print("You should change vis.draw_weights(), if you want to save the feature images for different dataset")
+            # try:
+            #     # visualize the 1st hidden layer during fine-tune
+            #     tl.vis.draw_weights(network.all_params[0].eval(), second=10, saveable=True, shape=[28, 28], name='w1_' + str(epoch + 1), fig_idx=2012)
+            # except:  # pylint: disable=bare-except
+            #     print("You should change vis.draw_weights(), if you want to save the feature images for different dataset")
 
     print('Evaluation')
     test_loss, test_acc, n_batch = 0, 0, 0
@@ -451,10 +451,10 @@ def main_test_cnn_layer():
                 n_batch += 1
             print("   val loss: %f" % (val_loss / n_batch))
             print("   val acc: %f" % (val_acc / n_batch))
-            try:
-                tl.vis.CNN2d(network.all_params[0].eval(), second=10, saveable=True, name='cnn1_' + str(epoch + 1), fig_idx=2012)
-            except:  # pylint: disable=bare-except
-                print("You should change vis.CNN(), if you want to save the feature images for different dataset")
+            # try:
+            #     tl.vis.CNN2d(network.all_params[0].eval(), second=10, saveable=True, name='cnn1_' + str(epoch + 1), fig_idx=2012)
+            # except:  # pylint: disable=bare-except
+            #     print("You should change vis.CNN(), if you want to save the feature images for different dataset")
 
     print('Evaluation')
     test_loss, test_acc, n_batch = 0, 0, 0
@@ -474,7 +474,7 @@ def main_test_cnn_layer():
     sess = tf.InteractiveSession()
 
     # Dropout and Dropconnect
-    main_test_layers(model='relu')  # model = relu, dropconnect
+    # main_test_layers(model='relu')  # model = relu, dropconnect
 
     # Single Denoising Autoencoder
     # main_test_denoise_AE(model='sigmoid')       # model = relu, sigmoid
@@ -483,4 +483,4 @@ def main_test_cnn_layer():
     # main_test_stacked_denoise_AE(model='relu')  # model = relu, sigmoid
 
     # CNN
-    # main_test_cnn_layer()
+    main_test_cnn_layer()

setup.py

@@ -10,7 +10,7 @@
 
 setup(
     name="tensorlayer",
-    version="1.8.4rc0",
+    version="1.8.4rc1",
     include_package_data=True,
     author='TensorLayer Contributors',
     author_email='[email protected]',

tensorlayer/__init__.py

@@ -24,7 +24,7 @@
 act = activation
 vis = visualize
 
-__version__ = "1.8.4rc0"
+__version__ = "1.8.4rc1"
 
 global_flag = {}
 global_dict = {}

tensorlayer/layers/core.py

@@ -1387,8 +1387,6 @@ def __init__(
         # self.all_layers = list(layer.all_layers)
         # self.all_params = list(layer.all_params)
         # self.all_drop = dict(layer.all_drop)
-        # self.all_drop.update({LayersConfig.set_keep[name]: keep})
-        # self.all_layers.append(self.outputs)
-        # self.all_params.extend([W, b])
-
+        self.all_drop.update({LayersConfig.set_keep[name]: keep})
         self.all_layers.append(self.outputs)
+        self.all_params.extend([W, b])

tensorlayer/models/__init__.py

@@ -1,4 +1,4 @@
-"""A collections of pre-defined well known models."""
+# """A collections of pre-defined well known models."""
 
 from .vgg16 import VGG16
 from .squeezenetv1 import SqueezeNetV1

tensorlayer/models/mobilenetv1.py

@@ -32,6 +32,7 @@ class MobileNetV1(Layer):
     Examples
     ---------
     Classify ImageNet classes, see `tutorial_models_mobilenetv1.py <https://github.com/tensorlayer/tensorlayer/blob/master/example/tutorial_models_mobilenetv1.py>__`
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get the whole model
     >>> net = tl.models.MobileNetV1(x)
@@ -42,6 +43,7 @@ class MobileNetV1(Layer):
     >>> probs = tf.nn.softmax(net.outputs)
 
     Extract features and Train a classifier with 100 classes
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get model without the last layer
     >>> cnn = tl.models.MobileNetV1(x, end_with='reshape')
@@ -57,6 +59,7 @@ class MobileNetV1(Layer):
     >>> train_params = tl.layers.get_variables_with_name('output')
 
     Reuse model
+
     >>> x1 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> x2 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get VGG without the last layer

tensorlayer/models/squeezenetv1.py

@@ -32,6 +32,7 @@ class SqueezeNetV1(Layer):
     Examples
     ---------
     Classify ImageNet classes, see `tutorial_models_squeezenetv1.py <https://github.com/tensorlayer/tensorlayer/blob/master/example/tutorial_models_squeezenetv1.py>__`
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get the whole model
     >>> net = tl.models.SqueezeNetV1(x)
@@ -42,6 +43,7 @@ class SqueezeNetV1(Layer):
     >>> probs = tf.nn.softmax(net.outputs)
 
     Extract features and Train a classifier with 100 classes
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get model without the last layer
     >>> cnn = tl.models.SqueezeNetV1(x, end_with='fire9')
@@ -57,6 +59,7 @@ class SqueezeNetV1(Layer):
     >>> train_params = tl.layers.get_variables_with_name('output')
 
     Reuse model
+
     >>> x1 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> x2 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get VGG without the last layer

tensorlayer/models/vgg16.py

@@ -245,6 +245,7 @@ class VGG16(VGG16Base):
     Examples
     ---------
     Classify ImageNet classes with VGG16, see `tutorial_models_vgg16.py <https://github.com/tensorlayer/tensorlayer/blob/master/example/tutorial_models_vgg16.py>__`
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get the whole model
     >>> vgg = tl.models.VGG16(x)
@@ -255,6 +256,7 @@ class VGG16(VGG16Base):
     >>> probs = tf.nn.softmax(vgg.outputs)
 
     Extract features with VGG16 and Train a classifier with 100 classes
+
     >>> x = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get VGG without the last layer
     >>> vgg = tl.models.VGG16(x, end_with='fc2_relu')
@@ -269,6 +271,7 @@ class VGG16(VGG16Base):
     >>> train_params = tl.layers.get_variables_with_name('out')
 
     Reuse model
+
     >>> x1 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> x2 = tf.placeholder(tf.float32, [None, 224, 224, 3])
     >>> # get VGG without the last layer