You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by zh...@apache.org on 2018/01/02 21:48:20 UTC
[incubator-mxnet] branch master updated: Update module.md to
include results of the code snippet (#9123)
This is an automated email from the ASF dual-hosted git repository.
zhasheng pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new dc48eb5 Update module.md to include results of the code snippet (#9123)
dc48eb5 is described below
commit dc48eb563753051019dce280365ddcfdadd97ed3
Author: Haibin Lin <li...@gmail.com>
AuthorDate: Tue Jan 2 13:48:16 2018 -0800
Update module.md to include results of the code snippet (#9123)
* Update module.md
* Update module.md
---
docs/tutorials/basic/module.md | 87 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 87 insertions(+)
diff --git a/docs/tutorials/basic/module.md b/docs/tutorials/basic/module.md
index e0618ca..48f9086 100644
--- a/docs/tutorials/basic/module.md
+++ b/docs/tutorials/basic/module.md
@@ -1,3 +1,4 @@
+
# Module - Neural network training and inference
Training a neural network involves quite a few steps. One need to specify how
@@ -35,6 +36,7 @@ The following code downloads the dataset and creates an 80:20 train:test
split. It also initializes a training data iterator to return a batch of 32
training examples each time. A separate iterator is also created for test data.
+
```python
import logging
logging.getLogger().setLevel(logging.INFO)
@@ -51,8 +53,10 @@ train_iter = mx.io.NDArrayIter(data[:ntrain, :], label[:ntrain], batch_size, shu
val_iter = mx.io.NDArrayIter(data[ntrain:, :], label[ntrain:], batch_size)
```
+
Next, we define the network.
+
```python
net = mx.sym.Variable('data')
net = mx.sym.FullyConnected(net, name='fc1', num_hidden=64)
@@ -62,6 +66,13 @@ net = mx.sym.SoftmaxOutput(net, name='softmax')
mx.viz.plot_network(net)
```
+
+
+
+
+
+
+
## Creating a Module
Now we are ready to introduce module. The commonly used module class is
@@ -75,6 +86,7 @@ Now we are ready to introduce module. The commonly used module class is
For `net`, we have only one data named `data`, and one label named `softmax_label`,
which is automatically named for us following the name `softmax` we specified for the `SoftmaxOutput` operator.
+
```python
mod = mx.mod.Module(symbol=net,
context=mx.cpu(),
@@ -100,6 +112,7 @@ To train a module, we need to perform following steps:
This can be used as follows:
+
```python
# allocate memory given the input data and label shapes
mod.bind(data_shapes=train_iter.provide_data, label_shapes=train_iter.provide_label)
@@ -121,6 +134,13 @@ for epoch in range(5):
print('Epoch %d, Training %s' % (epoch, metric.get()))
```
+ Epoch 0, Training ('accuracy', 0.4554375)
+ Epoch 1, Training ('accuracy', 0.6485625)
+ Epoch 2, Training ('accuracy', 0.7055625)
+ Epoch 3, Training ('accuracy', 0.7396875)
+ Epoch 4, Training ('accuracy', 0.764375)
+
+
To learn more about these APIs, visit [Module API](http://mxnet.io/api/python/module.html).
## High-level Interface
@@ -134,6 +154,7 @@ and it internally executes the same steps.
To fit a module, call the `fit` function as follows:
+
```python
# reset train_iter to the beginning
train_iter.reset()
@@ -153,6 +174,32 @@ mod.fit(train_iter,
num_epoch=8)
```
+ INFO:root:Epoch[0] Train-accuracy=0.364625
+ INFO:root:Epoch[0] Time cost=0.388
+ INFO:root:Epoch[0] Validation-accuracy=0.557250
+ INFO:root:Epoch[1] Train-accuracy=0.633625
+ INFO:root:Epoch[1] Time cost=0.470
+ INFO:root:Epoch[1] Validation-accuracy=0.634750
+ INFO:root:Epoch[2] Train-accuracy=0.697187
+ INFO:root:Epoch[2] Time cost=0.402
+ INFO:root:Epoch[2] Validation-accuracy=0.665500
+ INFO:root:Epoch[3] Train-accuracy=0.735062
+ INFO:root:Epoch[3] Time cost=0.402
+ INFO:root:Epoch[3] Validation-accuracy=0.713000
+ INFO:root:Epoch[4] Train-accuracy=0.762563
+ INFO:root:Epoch[4] Time cost=0.408
+ INFO:root:Epoch[4] Validation-accuracy=0.742000
+ INFO:root:Epoch[5] Train-accuracy=0.782312
+ INFO:root:Epoch[5] Time cost=0.400
+ INFO:root:Epoch[5] Validation-accuracy=0.778500
+ INFO:root:Epoch[6] Train-accuracy=0.797188
+ INFO:root:Epoch[6] Time cost=0.392
+ INFO:root:Epoch[6] Validation-accuracy=0.798250
+ INFO:root:Epoch[7] Train-accuracy=0.807750
+ INFO:root:Epoch[7] Time cost=0.401
+ INFO:root:Epoch[7] Validation-accuracy=0.789250
+
+
By default, `fit` function has `eval_metric` set to `accuracy`, `optimizer` to `sgd`
and optimizer_params to `(('learning_rate', 0.01),)`.
@@ -161,6 +208,7 @@ and optimizer_params to `(('learning_rate', 0.01),)`.
To predict with module, we can call `predict()`. It will collect and
return all the prediction results.
+
```python
y = mod.predict(val_iter)
assert y.shape == (4000, 26)
@@ -172,11 +220,15 @@ dataset and evaluates the performance according to the given input metric.
It can be used as follows:
+
```python
score = mod.score(val_iter, ['acc'])
print("Accuracy score is %f" % (score[0][1]))
```
+ Accuracy score is 0.789250
+
+
Some of the other metrics which can be used are `top_k_acc`(top-k-accuracy),
`F1`, `RMSE`, `MSE`, `MAE`, `ce`(CrossEntropy). To learn more about the metrics,
visit [Evaluation metric](http://mxnet.io/api/python/metric.html).
@@ -188,6 +240,7 @@ and tune these parameters to get best score.
We can save the module parameters after each training epoch by using a checkpoint callback.
+
```python
# construct a callback function to save checkpoints
model_prefix = 'mx_mlp'
@@ -197,10 +250,28 @@ mod = mx.mod.Module(symbol=net)
mod.fit(train_iter, num_epoch=5, epoch_end_callback=checkpoint)
```
+ INFO:root:Epoch[0] Train-accuracy=0.101062
+ INFO:root:Epoch[0] Time cost=0.422
+ INFO:root:Saved checkpoint to "mx_mlp-0001.params"
+ INFO:root:Epoch[1] Train-accuracy=0.263313
+ INFO:root:Epoch[1] Time cost=0.785
+ INFO:root:Saved checkpoint to "mx_mlp-0002.params"
+ INFO:root:Epoch[2] Train-accuracy=0.452188
+ INFO:root:Epoch[2] Time cost=0.624
+ INFO:root:Saved checkpoint to "mx_mlp-0003.params"
+ INFO:root:Epoch[3] Train-accuracy=0.544125
+ INFO:root:Epoch[3] Time cost=0.427
+ INFO:root:Saved checkpoint to "mx_mlp-0004.params"
+ INFO:root:Epoch[4] Train-accuracy=0.605250
+ INFO:root:Epoch[4] Time cost=0.399
+ INFO:root:Saved checkpoint to "mx_mlp-0005.params"
+
+
To load the saved module parameters, call the `load_checkpoint` function. It
loads the Symbol and the associated parameters. We can then set the loaded
parameters into the module.
+
```python
sym, arg_params, aux_params = mx.model.load_checkpoint(model_prefix, 3)
assert sym.tojson() == net.tojson()
@@ -215,6 +286,7 @@ parameters, so that `fit()` knows to start from those parameters instead of
initializing randomly from scratch. We also set the `begin_epoch` parameter so that
`fit()` knows we are resuming from a previously saved epoch.
+
```python
mod = mx.mod.Module(symbol=sym)
mod.fit(train_iter,
@@ -224,4 +296,19 @@ mod.fit(train_iter,
begin_epoch=3)
```
+ INFO:root:Epoch[3] Train-accuracy=0.544125
+ INFO:root:Epoch[3] Time cost=0.398
+ INFO:root:Epoch[4] Train-accuracy=0.605250
+ INFO:root:Epoch[4] Time cost=0.545
+ INFO:root:Epoch[5] Train-accuracy=0.644312
+ INFO:root:Epoch[5] Time cost=0.592
+ INFO:root:Epoch[6] Train-accuracy=0.675000
+ INFO:root:Epoch[6] Time cost=0.491
+ INFO:root:Epoch[7] Train-accuracy=0.695812
+ INFO:root:Epoch[7] Time cost=0.363
+
+
+
<!-- INSERT SOURCE DOWNLOAD BUTTONS -->
+
+
--
To stop receiving notification emails like this one, please contact
['"commits@mxnet.apache.org" <co...@mxnet.apache.org>'].