This repository has been archived by the owner on Jan 24, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #27 from dayhaha/develop
PR for recognize_digits
- Loading branch information
Showing
19 changed files
with
842 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,6 @@ | ||
data/raw_data | ||
data/train.list | ||
data/test.list | ||
*.log | ||
*.pyc | ||
plot.png |
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
#!/usr/bin/env sh | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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. | ||
# This scripts downloads the mnist data and unzips it. | ||
set -e | ||
DIR="$( cd "$(dirname "$0")" ; pwd -P )" | ||
rm -rf "$DIR/raw_data" | ||
mkdir "$DIR/raw_data" | ||
cd "$DIR/raw_data" | ||
|
||
echo "Downloading..." | ||
|
||
for fname in train-images-idx3-ubyte train-labels-idx1-ubyte t10k-images-idx3-ubyte t10k-labels-idx1-ubyte | ||
do | ||
if [ ! -e $fname ]; then | ||
wget --no-check-certificate http://yann.lecun.com/exdb/mnist/${fname}.gz | ||
gunzip ${fname}.gz | ||
fi | ||
done | ||
|
||
cd $DIR | ||
rm -f *.list | ||
echo "./data/raw_data/train" > "$DIR/train.list" | ||
echo "./data/raw_data/t10k" > "$DIR/test.list" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
#!/usr/bin/python | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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. | ||
import sys | ||
import re | ||
import math | ||
|
||
|
||
def get_best_pass(filename): | ||
with open(filename, 'r') as f: | ||
text = f.read() | ||
pattern = re.compile( | ||
'Test.*? cost=([0-9]+\.[0-9]+).*?classification_error_evaluator=([0-9]+\.[0-9]+).*?pass-([0-9]+)', | ||
re.S) | ||
results = re.findall(pattern, text) | ||
sorted_results = sorted(results, key=lambda result: float(result[0])) | ||
return sorted_results[0] | ||
|
||
|
||
filename = sys.argv[1] | ||
log = get_best_pass(filename) | ||
classification_accuracy = (1 - float(log[1])) * 100 | ||
print 'Best pass is %s, testing Avgcost is %s' % (log[2], log[0]) | ||
print 'The classification accuracy is %.2f%%' % classification_accuracy |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,47 @@ | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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. | ||
import numpy as np | ||
import matplotlib.pyplot as plt | ||
import random | ||
import struct | ||
|
||
|
||
def read_data(path, filename): | ||
with open(path + filename + "-images-idx3-ubyte", | ||
"rb") as f: # open picture file | ||
magic, n, rows, cols = struct.unpack(">IIII", f.read(16)) | ||
images = np.fromfile( | ||
f, 'ubyte', | ||
count=n * rows * cols).reshape(n, rows, cols).astype('float32') | ||
|
||
with open(path + filename + "-labels-idx1-ubyte", | ||
"rb") as l: # open label file | ||
magic, n = struct.unpack(">II", l.read(8)) | ||
labels = np.fromfile(l, 'ubyte', count=n).astype("int") | ||
|
||
return images, labels | ||
|
||
|
||
if __name__ == "__main__": | ||
train_images, train_labels = read_data("./data/raw_data/", "train") | ||
test_images, test_labels = read_data("./data/raw_data/", "t10k") | ||
label_list = [] | ||
for i in range(10): | ||
index = random.randint(0, train_images.shape[0] - 1) | ||
label_list.append(train_labels[index]) | ||
plt.subplot(1, 10, i + 1) | ||
plt.imshow(train_images[index], cmap="Greys_r") | ||
plt.axis('off') | ||
print('label: %s' % (label_list, )) | ||
plt.show() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,95 @@ | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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 paddle.trainer_config_helpers import * | ||
|
||
is_predict = get_config_arg("is_predict", bool, False) | ||
|
||
####################Data Configuration ################## | ||
|
||
if not is_predict: | ||
data_dir = './data/' | ||
define_py_data_sources2( | ||
train_list=data_dir + 'train.list', | ||
test_list=data_dir + 'test.list', | ||
module='mnist_provider', | ||
obj='process') | ||
|
||
######################Algorithm Configuration ############# | ||
settings( | ||
batch_size=128, | ||
learning_rate=0.1 / 128.0, | ||
learning_method=MomentumOptimizer(0.9), | ||
regularization=L2Regularization(0.0005 * 128)) | ||
|
||
#######################Network Configuration ############# | ||
|
||
data_size = 1 * 28 * 28 | ||
label_size = 10 | ||
img = data_layer(name='pixel', size=data_size) | ||
|
||
|
||
def softmax_regression(img): | ||
predict = fc_layer(input=img, size=10, act=SoftmaxActivation()) | ||
return predict | ||
|
||
|
||
def multilayer_perceptron(img): | ||
# The first fully-connected layer | ||
hidden1 = fc_layer(input=img, size=128, act=ReluActivation()) | ||
# The second fully-connected layer and the according activation function | ||
hidden2 = fc_layer(input=hidden1, size=64, act=ReluActivation()) | ||
# The thrid fully-connected layer, note that the hidden size should be 10, | ||
# which is the number of unique digits | ||
predict = fc_layer(input=hidden2, size=10, act=SoftmaxActivation()) | ||
return predict | ||
|
||
|
||
def convolutional_neural_network(img): | ||
# first conv layer | ||
conv_pool_1 = simple_img_conv_pool( | ||
input=img, | ||
filter_size=5, | ||
num_filters=20, | ||
num_channel=1, | ||
pool_size=2, | ||
pool_stride=2, | ||
act=TanhActivation()) | ||
# second conv layer | ||
conv_pool_2 = simple_img_conv_pool( | ||
input=conv_pool_1, | ||
filter_size=5, | ||
num_filters=50, | ||
num_channel=20, | ||
pool_size=2, | ||
pool_stride=2, | ||
act=TanhActivation()) | ||
# The first fully-connected layer | ||
fc1 = fc_layer(input=conv_pool_2, size=128, act=TanhActivation()) | ||
# The softmax layer, note that the hidden size should be 10, | ||
# which is the number of unique digits | ||
predict = fc_layer(input=fc1, size=10, act=SoftmaxActivation()) | ||
return predict | ||
|
||
|
||
predict = softmax_regression(img) | ||
#predict = multilayer_perceptron(img) | ||
#predict = convolutional_neural_network(img) | ||
|
||
if not is_predict: | ||
lbl = data_layer(name="label", size=label_size) | ||
inputs(img, lbl) | ||
outputs(classification_cost(input=predict, label=lbl)) | ||
else: | ||
outputs(predict) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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 paddle.trainer.PyDataProvider2 import * | ||
import numpy as np | ||
import struct | ||
|
||
|
||
# Define a py data provider | ||
@provider( | ||
input_types={'pixel': dense_vector(28 * 28), | ||
'label': integer_value(10)}) | ||
def process(settings, filename): # settings is not used currently. | ||
with open(filename + "-images-idx3-ubyte", "rb") as f: # open picture file | ||
magic, n, rows, cols = struct.unpack(">IIII", f.read(16)) | ||
images = np.fromfile( | ||
f, 'ubyte', | ||
count=n * rows * cols).reshape(n, rows, cols).astype('float32') | ||
images = images / 255.0 * 2.0 - 1.0 # normalized to [-1,1] | ||
|
||
with open(filename + "-labels-idx1-ubyte", "rb") as l: # open label file | ||
magic, n = struct.unpack(">II", l.read(8)) | ||
labels = np.fromfile(l, 'ubyte', count=n).astype("int") | ||
|
||
for i in xrange(n): | ||
yield {"pixel": images[i, :], 'label': labels[i]} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,54 @@ | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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. | ||
|
||
import matplotlib.pyplot as plt | ||
import re | ||
import sys | ||
|
||
|
||
def plot_log(filename): | ||
with open(filename, 'r') as f: | ||
text = f.read() | ||
pattern = re.compile( | ||
'AvgCost=([0-9]+\.[0-9]+).*?Test.*? cost=([0-9]+\.[0-9]+).*?pass-([0-9]+)', | ||
re.S) | ||
results = re.findall(pattern, text) | ||
train_cost, test_cost, pass_ = zip(*results) | ||
train_cost_float = map(float, train_cost) | ||
test_cost_float = map(float, test_cost) | ||
pass_int = map(int, pass_) | ||
plt.plot(pass_int, train_cost_float, 'red', label='Train') | ||
plt.plot(pass_int, test_cost_float, 'g--', label='Test') | ||
plt.ylabel('AvgCost') | ||
plt.xlabel('Epoch') | ||
|
||
# Now add the legend with some customizations. | ||
legend = plt.legend(loc='upper right', shadow=False) | ||
|
||
# The frame is matplotlib.patches.Rectangle instance surrounding the legend. | ||
frame = legend.get_frame() | ||
frame.set_facecolor('0.90') | ||
|
||
# Set the fontsize | ||
for label in legend.get_texts(): | ||
label.set_fontsize('large') | ||
|
||
for label in legend.get_lines(): | ||
label.set_linewidth(1.5) # the legend line width | ||
|
||
plt.show() | ||
|
||
|
||
if __name__ == '__main__': | ||
plot_log(sys.argv[1]) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,79 @@ | ||
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved | ||
# | ||
# 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. | ||
"""Usage: predict.py -c CONF -d ./data/raw_data/ -m MODEL | ||
Arguments: | ||
CONF train conf | ||
DATA MNIST Data | ||
MODEL Model | ||
Options: | ||
-h --help | ||
-c conf | ||
-d data | ||
-m model | ||
""" | ||
|
||
import os | ||
import sys | ||
from docopt import docopt | ||
import matplotlib.pyplot as plt | ||
import numpy as np | ||
|
||
from py_paddle import swig_paddle, DataProviderConverter | ||
from paddle.trainer.PyDataProvider2 import dense_vector | ||
from paddle.trainer.config_parser import parse_config | ||
|
||
from load_data import read_data | ||
|
||
|
||
class Prediction(): | ||
def __init__(self, train_conf, data_dir, model_dir): | ||
|
||
conf = parse_config(train_conf, 'is_predict=1') | ||
self.network = swig_paddle.GradientMachine.createFromConfigProto( | ||
conf.model_config) | ||
self.network.loadParameters(model_dir) | ||
|
||
self.images, self.labels = read_data(data_dir, "t10k") | ||
|
||
slots = [dense_vector(28 * 28)] | ||
self.converter = DataProviderConverter(slots) | ||
|
||
def predict(self, index): | ||
input = self.converter([[self.images[index].flatten().tolist()]]) | ||
output = self.network.forwardTest(input) | ||
prob = output[0]["value"] | ||
predict = np.argsort(-prob) | ||
print "Predicted probability of each digit:" | ||
print prob | ||
print "Predict Number: %d" % predict[0][0] | ||
print "Actual Number: %d" % self.labels[index] | ||
|
||
|
||
def main(): | ||
arguments = docopt(__doc__) | ||
train_conf = arguments['CONF'] | ||
data_dir = arguments['DATA'] | ||
model_dir = arguments['MODEL'] | ||
swig_paddle.initPaddle("--use_gpu=0") | ||
predictor = Prediction(train_conf, data_dir, model_dir) | ||
while True: | ||
index = int(raw_input("Input image_id [0~9999]: ")) | ||
predictor.predict(index) | ||
|
||
|
||
if __name__ == '__main__': | ||
main() |
Oops, something went wrong.