hironsan / bosssensor Goto Github PK

Image preprocessing should be divided into a class of function.

My experiment was based on the pictures of those famous movie stars I gathered from the Internet. I could only get an approx 60% accuracy when training the model.

Is there any way to improve the accuracy?

when i run boss_train, it appears, and the prompt message refer to 'validation_data=(dataset.X_valid, dataset.Y_valid)'.

please help me.

It seems you read all the images in to cache. Will it be problem if amount of images is huge. like 100k training images?
I also used keras, but I use flow_from_directory method in keras instead
Thanks you code.
Got some inspiration.

I have following error.

➜  BossSensor git:(master) ✗ python camera_reader.py
Using TensorFlow backend.
Model Loaded.
face detected
Traceback (most recent call last):
  File "camera_reader.py", line 36, in <module>
    result = model.predict(image)
  File "/Users/huseyinmert/Desktop/tmp_code/BossSensor/boss_train.py", line 159, in predict
    result = self.model.predict_proba(image)
  File "/usr/local/lib/python2.7/site-packages/keras/models.py", line 758, in predict_proba
    preds = self.predict(x, batch_size, verbose)
  File "/usr/local/lib/python2.7/site-packages/keras/models.py", line 671, in predict
    return self.model.predict(x, batch_size=batch_size, verbose=verbose)
  File "/usr/local/lib/python2.7/site-packages/keras/engine/training.py", line 1161, in predict
    check_batch_dim=False)
  File "/usr/local/lib/python2.7/site-packages/keras/engine/training.py", line 108, in standardize_input_data
    str(array.shape))
Exception: Error when checking : expected convolution2d_input_1 to have shape (None, 64, 64, 3) but got array with shape (1, 3, 64, 64)

I would like to ask why recognition boss failed

my data
boss Folder has 121 Pictures , image format is .jpg (Only the face part)
other Folder has 227 Pictures , image format is .jpg, 5 different people (Only the face part)

i run boss_train.py get ,the accuracy is 0.89

i backed use TensorFlow

but i run camera_reader.py to start BossSensor

recognition boss failed

I do not know which part is wrong, is image format or something

please help me,thanks

Model Saved.
Traceback (most recent call last):
File "boss_train.py", line 180, in
model.save()
File "boss_train.py", line 147, in save
self.model.save(file_path)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2423, in save
save_model(self, filepath, overwrite)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 48, in save_model
f = h5py.File(filepath, 'w')
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 271, in init
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
File "/usr/local/lib/python2.7/dist-packages/h5py/_hl/files.py", line 107, in make_fid
fid = h5f.create(name, h5f.ACC_TRUNC, fapl=fapl, fcpl=fcpl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (/tmp/pip-nCYoKW-build/h5py/_objects.c:2840)
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (/tmp/pip-nCYoKW-build/h5py/_objects.c:2798)
File "h5py/h5f.pyx", line 98, in h5py.h5f.create (/tmp/pip-nCYoKW-build/h5py/h5f.c:2284)
IOError: Unable to create file (Unable to open file: name = './store/model.h5', errno = 2, error message = 'no such file or directory', flags = 13, o_flags = 242)

全世界无产阶级联合起来摸鱼！
世界のプロレタリアートは団結して仕事でふざけよう！
The proletariat of the world unite to goof off at work!

When I read “boss_train.py”,I found a constant named "FILE_PATH".I can't find its value "./store/model.h5" in any folders.Is it a forein file?

Install OpenCV, PyQt4, Anaconda.

That means I have to install these three separately?

conda install -c https://conda.anaconda.org/menpo opencv3

Install opencv with anaconda again?

有没有大神包装成exe文件，配置环境比较麻烦

Could not open requirements file: [Errno 2] No such file or directory: 'requirements.txt'

how many pictures are used to train? I use your code. Boss picture number: 300 other picture number: 300*10 ; (10 persons , everyone have 300 ). the model give accuracy 0.93. I think it is too low. how to improve the accuracy?

Which MacOSX Version is Optimal for this installation ?

I'm using in Sierra(MacOSX 10.12.x), But There is problems with your manual.

Thanks in advance.

Model Loaded.
OpenCV Error: Assertion failed (!empty()) in detectMultiScale, file /Users/jenkins/miniconda/1/x64/conda-bld/work/opencv-3.1.0/modules/objdetect/src/cascadedetect.cpp, line 1639
Traceback (most recent call last):
File "camera_reader.py", line 25, in
facerect = cascade.detectMultiScale(frame_gray, scaleFactor=1.2, minNeighbors=3, minSize=(10, 10))
cv2.error: /Users/jenkins/miniconda/1/x64/conda-bld/work/opencv-3.1.0/modules/objdetect/src/cascadedetect.cpp:1639: error: (-215) !empty() in function detectMultiScale

Cleaned up camera.

The first one is， it is probably version problem, I am newer and I will be very appreicated with your help;
When I run boss_train.py:

AttributeError: module 'tensorflow.python' has no attribute 'control_flow_ops

the second one is : when I run camera_reader.py:
I do not know what is the file of './store/model.h5', thank you!
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper (D:\Build\h5py\h5py-2.6.0\h5py_objects.c:2580)
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper (D:\Build\h5py\h5py-2.6.0\h5py_objects.c:2539)
File "h5py\h5f.pyx", line 76, in h5py.h5f.open (D:\Build\h5py\h5py-2.6.0\h5py\h5f.c:1814)
OSError: Unable to open file (Unable to open file: name = './store/model.h5', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)

I'm a beginner,and i got those issues,what that means?

gine/training.py", line 429, in data_generator_task
generator_output = next(self._generator)
File "/Users/zhangfei/anaconda3/envs/venv/lib/python3.5/site-packages/keras/preprocessing/image.py", line 662, in next
return self.next(*args, **kwargs)
File "/Users/zhangfei/anaconda3/envs/venv/lib/python3.5/site-packages/keras/preprocessing/image.py", line 708, in next
index_array, current_index, current_batch_size = next(self.index_generator)
File "/Users/zhangfei/anaconda3/envs/venv/lib/python3.5/site-packages/keras/preprocessing/image.py", line 645, in _flow_index
current_index = (self.batch_index * batch_size) % n
ZeroDivisionError: integer division or modulo by zero

Traceback (most recent call last):
File "boss_train.py", line 178, in
model.train(dataset, nb_epoch=10)
File "boss_train.py", line 143, in train
validation_data=(dataset.X_valid, dataset.Y_valid))
File "/Users/zhangfei/anaconda3/envs/venv/lib/python3.5/site-packages/keras/models.py", line 935, in fit_generator
initial_epoch=initial_epoch)
File "/Users/zhangfei/anaconda3/envs/venv/lib/python3.5/site-packages/keras/engine/training.py", line 1600, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
UnboundLocalError: local variable 'epoch_logs' referenced before assignment

fuhongwei@fuhongwei-VPCCA48EC:~/BossSensor-master$ python camera_reader.py
Using TensorFlow backend.
Model Loaded.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.

OpenCV Error: Assertion failed (scn == 3 || scn == 4) in cvtColor, file /io/opencv/modules/imgproc/src/color.cpp, line 9748
Traceback (most recent call last):
File "camera_reader.py", line 17, in
frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.error: /io/opencv/modules/imgproc/src/color.cpp:9748: error: (-215) scn == 3 || scn == 4 in function cvtColor

I run the boss_train.py, but there is an error called "AttributeError". It says that, 'ProgbarLogger' object has no attribute 'log_values'.
Does anyone know how this problem happens?
Thanks!

Hi,

do I need to create the model.h5 manually during the training.

python boss_train.py

OSError: Unable to create file (Unable to open file: name = './store/model.h5', errno = 2, error message = 'no such file or directory', flags = 13, o_flags = 602)
Exception ignored in: <bound method BaseSession.del of <tensorflow.python.client.session.Session object at 0x10e0a1e80>>
Traceback (most recent call last):

Hi
could you add your article in the description as a reference to more info?
http://ahogrammer.com/2016/11/15/deep-learning-enables-you-to-hide-screen-when-your-boss-is-approaching/

As the title says, can this project work on Windows10?

I user tensorflow 0.12, and I put some pictures in boss and other directories, but when I run boss_train.py ,it report error:
Traceback (most recent call last):
File "/home/zxx/PycharmProjects/BossSensor/boss_train.py", line 176, in
dataset.read()
File "/home/zxx/PycharmProjects/BossSensor/boss_train.py", line 35, in read
X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100))
File "/usr/lib/python2.7/dist-packages/sklearn/cross_validation.py", line 1556, in train_test_split
arrays = check_arrays(*arrays, **options)
File "/usr/lib/python2.7/dist-packages/sklearn/utils/validation.py", line 287, in check_arrays
array.ndim)
ValueError: Found array with dim 4. Expected <= 2

Could you give me some help, thanks.

OpenCV Error: Assertion failed (scn == 3 || scn == 4) in cvtColor, file /io/opencv/modules/imgproc/src/color.cpp, line 9748
Traceback (most recent call last):
File "camera_reader.py", line 17, in
frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.error: /io/opencv/modules/imgproc/src/color.cpp:9748: error: (-215) scn == 3 || scn == 4 in function cvtColor

boss_train.py errors have occurred.

/Users/icent/Documents/BossSensor/data/boss/dummy.jpg
X_train shape: (0, 64, 64, 3)
0 train samples
0 valid samples
1 test samples
~~
Total params: 6489634

Using real-time data augmentation.
Epoch 1/10
Traceback (most recent call last):
File "/Users/icent/Documents/BossSensor/boss_train.py", line 181, in
model.train(dataset, nb_epoch=10)
File "/Users/icent/Documents/BossSensor/boss_train.py", line 146, in train
validation_data=(dataset.X_valid, dataset.Y_valid))
File "/anaconda/envs/boss/lib/python3.5/site-packages/keras/models.py", line 874, in fit_generator
pickle_safe=pickle_safe)
File "/anaconda/envs/boss/lib/python3.5/site-packages/keras/engine/training.py", line 1485, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)

UnboundLocalError: local variable 'epoch_logs' referenced before assignment

Help me!

X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100))
X_valid, X_test, y_valid, y_test = train_test_split(images, labels, test_size=0.5, random_state=random.randint(0, 100))

I have accomplish the model's train and evaluate,the evaluate result is 93%,but when I predict face on my camera , the process will think of all the faces as me . I should how to the problem。