Error when checking : expected convolution2d_input_1 about bosssensor HOT 4 CLOSED

if use tensorflow,change model.predict to "
def predict(self, image):
if image.shape != (1, 3, IMAGE_SIZE, IMAGE_SIZE):
image = resize_with_pad(image)
if K.image_dim_ordering() == 'th':
image = image.reshape((1, 3, IMAGE_SIZE, IMAGE_SIZE))
else:
image = image.reshape((1, IMAGE_SIZE, IMAGE_SIZE ,3))
image = image.astype('float32')
image /= 255
result = self.model.predict_proba(image)
print(result)
result = self.model.predict_classes(image)

    return result[0]

"

then the "Exception: Error when checking : expected convolution2d_input_1 to have shape (None, 64, 64, 3) but got array with shape (1, 3, 64, 64)" disappear.

from bosssensor.

what is your image_dim_ordering? th or tf?

https://keras.io/backend/

from bosssensor.

/Users/Jason/ML/BossSensor/camera_reader.py
Using TensorFlow backend.
Model Loaded.
Traceback (most recent call last):
face detected
File "/Users/Jason/ML/BossSensor/camera_reader.py", line 36, in
result = model.predict(image)
File "/Users/Jason/ML/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)
Cleaned up camera.

I also have this error, how to resolve.

from bosssensor.

I also got this error. my image_dim_ordering is "tf". could it be the reason that I have different sized images in the training folders?

from bosssensor.