Merge branch 'master' into Release

Author: Laicheng0830

README.md

@@ -26,6 +26,8 @@ This project can also be found at [iHub](https://code.ihub.org.cn/projects/328)
 
 # News
 
+🔥 **3.0.0 will supports multiple backends, such as TensorFlow, MindSpore and more, allowing users to run the code on different hardware like Nvidia-GPU and Huawei-Ascend. We need more people to join the dev team, if you are interested, please email [email protected]**
+
 🔥 Reinforcement Learning Zoo: [Low-level APIs](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning) for professional usage, [High-level APIs](https://github.com/tensorlayer/RLzoo) for simple usage, and a corresponding [Springer textbook](http://springer.com/gp/book/9789811540943)
 
 🔥 [Sipeed Maxi-EMC](https://github.com/sipeed/Maix-EMC): Run TensorLayer models on the **low-cost AI chip** (e.g., K210) (Alpha Version)

examples/basic_tutorials/tutorial_cifar10_cnn_static.py

@@ -155,24 +155,16 @@ def _map_fn_test(img, target):
 
 for epoch in range(n_epoch):
     start_time = time.time()
-
     train_loss, train_acc, n_iter = 0, 0, 0
     for X_batch, y_batch in train_ds:
         net.train()
-
         with tf.GradientTape() as tape:
             # compute outputs
             _logits = net(X_batch)
             # compute loss and update model
-            _loss_ce = tl.cost.cross_entropy(_logits, y_batch, name='train_loss')
-            _loss_L2 = 0
-            # for p in tl.layers.get_variables_with_name('relu/W', True, True):
-            #      _loss_L2 += tl.cost.lo_regularizer(1.0)(p)
-            _loss = _loss_ce + _loss_L2
-
+            _loss = tl.cost.cross_entropy(_logits, y_batch, name='train_loss')
         grad = tape.gradient(_loss, train_weights)
         optimizer.apply_gradients(zip(grad, train_weights))
-
         train_loss += _loss
         train_acc += np.mean(np.equal(np.argmax(_logits, 1), y_batch))
         n_iter += 1

examples/reinforcement_learning/README.md

@@ -45,7 +45,6 @@ A corresponding [Springer textbook](https://deepreinforcementlearningbook.org) i
 * tensorflow >= 2.0.0 or tensorflow-gpu >= 2.0.0a0
 * tensorlayer >= 2.0.1
 * tensorflow-probability
-* tf-nightly-2.0-preview
 
 *** If you meet the error`AttributeError: module 'tensorflow' has no attribute 'contrib'` when running the code after installing tensorflow-probability, try:
 
@@ -108,7 +107,6 @@ The pretrained models and learning curves for each algorithm are stored [here](h
   See David Silver RL Tutorial Lecture 5 - Q-Learning for more details.
   ```
 
-  ​    
 
 * **Deep Q-Network (DQN)**
 
@@ -157,8 +155,6 @@ The pretrained models and learning curves for each algorithm are stored [here](h
   ```
 
 
-  ```
-
 
 
 

tensorlayer/models/vgg.py

@@ -82,7 +82,7 @@
 
 model_urls = {
     'vgg16': 'http://www.cs.toronto.edu/~frossard/vgg16/',
-    'vgg19': 'https://media.githubusercontent.com/media/tensorlayer/pretrained-models/master/models/'
+    'vgg19': 'https://github.com/tensorlayer/pretrained-models/blob/master/models/vgg19.npy'
 }
 
 model_saved_name = {'vgg16': 'vgg16_weights.npz', 'vgg19': 'vgg19.npy'}