Then we need to setup the the `train_program`. It takes the prediction from the classifier first. During the training, it will calculate the `avg_loss` from the prediction.
Then we need to setup the the `train_program`. It takes the prediction from the classifier first.
During the training, it will calculate the `avg_loss` from the prediction.
**NOTE:** A train program should return an array and the first return argument has to be `avg_cost`.
The trainer always implicitly use it to calculate the gradient.
Please feel free to modify the code to test different results between `softmax regression`, `mlp`, and `convolutional neural network` classifier.
# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
```
```
Pass 0, Batch 0, Cost 0.125650
Pass 100, Batch 0, Cost 0.161387
Pass 200, Batch 0, Cost 0.040036
Pass 300, Batch 0, Cost 0.023391
Pass 400, Batch 0, Cost 0.005856
Pass 500, Batch 0, Cost 0.003315
Pass 600, Batch 0, Cost 0.009977
Pass 700, Batch 0, Cost 0.020959
Pass 800, Batch 0, Cost 0.105560
Pass 900, Batch 0, Cost 0.239809
Test with Epoch 0, avg_cost: 0.053097883707459624, acc: 0.9822850318471338
```
After the training, we can check the model's prediction accuracy.
```
```python
# find the best pass
best = sorted(lists, key=lambda list: float(list[1]))[0]
print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
print 'The classification accuracy is %.2f%%' % (float(best[2]) * 100)
```
Usually, with MNIST data, the softmax regression model achieves an accuracy around 92.34%, the MLP 97.66%, and the convolution network around 99.20%. Convolution layers have been widely considered a great invention for image processing.
...
...
@@ -323,23 +384,48 @@ Usually, with MNIST data, the softmax regression model achieves an accuracy arou
After training, users can use the trained model to classify images. The following code shows how to inference MNIST images through `fluid.Inferencer`.
### Create Inferencer
The `Inferencer` takes an `infer_func` and `param_path` to setup the network and the trained parameters.
We can simply plug-in the classifier defined earlier here.
```python
inferencer = fluid.Inferencer(
# infer_func=softmax_regression, # uncomment for softmax regression
# infer_func=multilayer_perceptron, # uncomment for MLP
infer_func=convolutional_neural_network, # uncomment for LeNet5
infer_func=convolutional_neural_network, # uncomment for LeNet5
param_path=params_dirname,
place=place)
```
#### Generate input data for inferring
batch_size = 1
import numpy
tensor_img = numpy.random.uniform(-1.0, 1.0,
[batch_size, 1, 28, 28]).astype("float32")
`infer_3.png` is an example image of the digit `3`. Turn it into an numpy array to match the data feeder format.
results = inferencer.infer({'img': tensor_img})
```python
# Prepare the test image
import os
import numpy as np
from PIL import Image
def load_image(file):
im = Image.open(file).convert('L')
im = im.resize((28, 28), Image.ANTIALIAS)
im = np.array(im).reshape(1, 1, 28, 28).astype(np.float32)
im = im / 255.0 * 2.0 - 1.0
return im
cur_dir = cur_dir = os.getcwd()
img = load_image(cur_dir + '/image/infer_3.png')
```
print("infer results: ", results[0])
### Inference
Now we are ready to do inference.
```python
results = inferencer.infer({'img': img})
lab = np.argsort(results) # probs and lab are the results of one batch data
print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
Then we need to setup the the `train_program`. It takes the prediction from the classifier first. During the training, it will calculate the `avg_loss` from the prediction.
Then we need to setup the the `train_program`. It takes the prediction from the classifier first.
During the training, it will calculate the `avg_loss` from the prediction.
**NOTE:** A train program should return an array and the first return argument has to be `avg_cost`.
The trainer always implicitly use it to calculate the gradient.
Please feel free to modify the code to test different results between `softmax regression`, `mlp`, and `convolutional neural network` classifier.
# Test with Pass 0, Cost 0.326659, {'classification_error_evaluator': 0.09470000118017197}
```
```
Pass 0, Batch 0, Cost 0.125650
Pass 100, Batch 0, Cost 0.161387
Pass 200, Batch 0, Cost 0.040036
Pass 300, Batch 0, Cost 0.023391
Pass 400, Batch 0, Cost 0.005856
Pass 500, Batch 0, Cost 0.003315
Pass 600, Batch 0, Cost 0.009977
Pass 700, Batch 0, Cost 0.020959
Pass 800, Batch 0, Cost 0.105560
Pass 900, Batch 0, Cost 0.239809
Test with Epoch 0, avg_cost: 0.053097883707459624, acc: 0.9822850318471338
```
After the training, we can check the model's prediction accuracy.
```
```python
# find the best pass
best = sorted(lists, key=lambda list: float(list[1]))[0]
print 'Best pass is %s, testing Avgcost is %s' % (best[0], best[1])
print 'The classification accuracy is %.2f%%' % (100 - float(best[2]) * 100)
print 'The classification accuracy is %.2f%%' % (float(best[2]) * 100)
```
Usually, with MNIST data, the softmax regression model achieves an accuracy around 92.34%, the MLP 97.66%, and the convolution network around 99.20%. Convolution layers have been widely considered a great invention for image processing.
...
...
@@ -365,23 +426,48 @@ Usually, with MNIST data, the softmax regression model achieves an accuracy arou
After training, users can use the trained model to classify images. The following code shows how to inference MNIST images through `fluid.Inferencer`.
### Create Inferencer
The `Inferencer` takes an `infer_func` and `param_path` to setup the network and the trained parameters.
We can simply plug-in the classifier defined earlier here.
```python
inferencer = fluid.Inferencer(
# infer_func=softmax_regression, # uncomment for softmax regression
# infer_func=multilayer_perceptron, # uncomment for MLP
infer_func=convolutional_neural_network, # uncomment for LeNet5
infer_func=convolutional_neural_network, # uncomment for LeNet5
param_path=params_dirname,
place=place)
```
#### Generate input data for inferring
batch_size = 1
import numpy
tensor_img = numpy.random.uniform(-1.0, 1.0,
[batch_size, 1, 28, 28]).astype("float32")
`infer_3.png` is an example image of the digit `3`. Turn it into an numpy array to match the data feeder format.
results = inferencer.infer({'img': tensor_img})
```python
# Prepare the test image
import os
import numpy as np
from PIL import Image
def load_image(file):
im = Image.open(file).convert('L')
im = im.resize((28, 28), Image.ANTIALIAS)
im = np.array(im).reshape(1, 1, 28, 28).astype(np.float32)
im = im / 255.0 * 2.0 - 1.0
return im
cur_dir = cur_dir = os.getcwd()
img = load_image(cur_dir + '/image/infer_3.png')
```
print("infer results: ", results[0])
### Inference
Now we are ready to do inference.
```python
results = inferencer.infer({'img': img})
lab = np.argsort(results) # probs and lab are the results of one batch data
print "Label of image/infer_3.png is: %d" % lab[0][0][-1]
