Hi, I am using Resnet50 to do transfer learning. The backend is tensorflow. I tried to stack three more layers on top of the Resnet but fail with following error:

Exception: The shape of the input to "Flatten" is not fully defined (got (None, None, 2048). 
Make sure to pass a complete "input_shape" or "batch_input_shape" argument to the first layer in your model.

The code for stacking two models are as following:

    model = ResNet50(include_top=False, weights='imagenet')

    top_model = Sequential()
    top_model.add(Flatten(input_shape=model.output_shape[1:]))
    top_model.add(Dense(256, activation='relu'))
    top_model.add(Dropout(0.5))
    top_model.add(Dense(1, activation='sigmoid'))
    top_model.load_weights(top_model_weights_path)

    model = Model(input=model.input, output=top_model(model.output))

I am slowly converting the caffe autocolorize model to keras in the PR.

Some references:

• caffe model viz
• Project page and weights
• Caffe model and code
• Paper

>>> from resnet50 import ResNet50
Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.8.0 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.8.0 locally
>>> model = ResNet50(weights='imagenet')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "resnet50.py", line 192, in ResNet50
    data_format=K.image_data_format(),
AttributeError: 'module' object has no attribute 'image_data_format'
>>> from keras.preprocessing import image
>>> from imagenet_utils import preprocess_input, decode_predictions
>>> model = ResNet50(weights='imagenet')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "resnet50.py", line 192, in ResNet50
    data_format=K.image_data_format(),
AttributeError: 'module' object has no attribute 'image_data_format'

My System

• Tensorflow 1.0.0
• Keras 1.2.2

when calling predict:

Traceback (most recent call last):
  File "/home/omar/Pycharm_ubuntu_v2/Spatial_v2_Aug-2016/features_from_keras_tool_RGB_final.py", line 72, in <module>
    model = InceptionV3(weights='imagenet', include_top=False)
  File "/home/omar/Pycharm_ubuntu_v2/Spatial_v2_Aug-2016/inception_v3.py", line 272, in InceptionV3
    model.load_weights(weights_path)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2446, in load_weights
    self.load_weights_from_hdf5_group(f)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 2518, in load_weights_from_hdf5_group
    ' elements.')
Exception: Layer #162 (named "batchnormalization_79" in the current model) was found to correspond to layer convolution2d_77 in the save file. However the new layer batchnormalization_79 expects 4 weights, but the saved weights have 2 elements.

Process finished with exit code 1

Hi, Is it possible to use provided weights for fine-tuning inception-v3 model? Writing a simple manual for this, really helps. Something like Fine-tuning CaffeNet for Style Recognition.

I tried to run this code

from vgg16 import VGG16
from keras.preprocessing import image
from imagenet_utils import preprocess_input

model = VGG16(weights='imagenet', include_top=False)

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

features = model.predict(x)

but i got KeyError: “Can’t open attribute (Can’t locate attribute: ‘layer_names’) what should i do?

I've already converted the caffe vgg_face model to keras,but it's only compatible with Theano. I've also tried many times to use the convert_kernel function in keras.utils.np_utils to make it compatible with Tensorflow,but I can't get the right result.

Would it be reasonable to add an optional batch normalization mode argument to ResNet50? Allowing for mode = 2 would enable ResNet50 to be used in a shared fashion. I think the same BN initializations could be used in mode = 2. Happy to do a PR if folks think it's worthwhile.

Are the weight files here as same as the original VGG-16 net? There is a mean image file with VGG-16's Caffe Model. Should I still apply it for the best result?

I have used the resnet and vgg models successfully but cannot use the freshly released inception weights.

Keras is on the latest master commit from github and i'm using anaconda python 3.5. -- Edit it was not on the 'latest' commit. It was on a commit from several days ago when I first cloned this repo; didn't realize it needed to be updated again.

Thoughts?

from inception_v3 import InceptionV3
from keras.preprocessing import image
from imagenet_utils import preprocess_input

model = InceptionV3(weights='imagenet', include_top=False)

Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.2/inception_v3_weights_th_dim_ordering_th_kernels_notop.h5
86679552/86916664 [============================>.] - ETA: 0s
---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-5-881bb296c35e> in <module>()
      3 from imagenet_utils import preprocess_input
      4 
----> 5 model = InceptionV3(weights='imagenet', include_top=False)

/home/agonzales/git/image_classifier/src/inception_v3.py in InceptionV3(include_top, weights, input_tensor)
    279                                         cache_subdir='models',
    280                                         md5_hash='79aaa90ab4372b4593ba3df64e142f05')
--> 281             model.load_weights(weights_path)
    282             if K.backend() == 'tensorflow':
    283                 warnings.warn('You are using the TensorFlow backend, yet you '

/home/agonzales/anaconda3/envs/keras_extract/lib/python3.5/site-packages/Keras-1.0.6-py3.5.egg/keras/engine/topology.py in load_weights(self, filepath)
   2444         if 'layer_names' not in f.attrs and 'model_weights' in f:
   2445             f = f['model_weights']
-> 2446         self.load_weights_from_hdf5_group(f)
   2447         if hasattr(f, 'close'):
   2448             f.close()

/home/agonzales/anaconda3/envs/keras_extract/lib/python3.5/site-packages/Keras-1.0.6-py3.5.egg/keras/engine/topology.py in load_weights_from_hdf5_group(self, f)
   2516                                     ' weights, but the saved weights have ' +
   2517                                     str(len(weight_values)) +
-> 2518                                     ' elements.')
   2519                 weight_value_tuples += zip(symbolic_weights, weight_values)
   2520             K.batch_set_value(weight_value_tuples)

Exception: Layer #162 (named "batchnormalization_267" in the current model) was found to correspond to layer convolution2d_77 in the save file. However the new layer batchnormalization_267 expects 4 weights, but the saved weights have 2 elements.

Hello,

We cannot fetch the file from the following URL.

https://github.com/fchollet/deep-learning-models/releases/download/v0.7/inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5

The response is as followed

<Code>SignatureDoesNotMatch</Code>
<Message>The request signature we calculated does not match the signature you provided. Check your key and signing method.</Message>

Hello I have written the following code:

validate on val set predictions = model.predict(X_val_prep) predictions = [1 if x>0.5 else 0 for x in predictions]

accuracy = accuracy_score(y_val, predictions) print('Val Accuracy = %.2f' % accuracy)

confusion_mtx = confusion_matrix(y_val, predictions) cm = plot_confusion_matrix(confusion_mtx, classes = list(labels.items()), normalize=False)

ValueError: Error when checking input: expected vgg16_input to have shape (244, 244, 3) but got array with shape (224, 224, 3)

Could you help me how I should tackle it? thank u very much.

Hello I have written the following code:

validate on val set predictions = model.predict(X_val_prep) predictions = [1 if x>0.5 else 0 for x in predictions]

accuracy = accuracy_score(y_val, predictions) print('Val Accuracy = %.2f' % accuracy)

confusion_mtx = confusion_matrix(y_val, predictions) cm = plot_confusion_matrix(confusion_mtx, classes = list(labels.items()), normalize=False)

NameError: name 'X_val_prep' is not defined

Could you help me how I should tackle it? thank u very much.

Hi, I want to load a keras model in parent process and access by child process but i got many issue.what is correct way to do this.is it possible or not?

Sorry to trouble you， I have a problem about training the keras model.Recently，I used the existing models from keras applications like VGG16,VGG19. The applications provide the existing models which are converted from caffe model. I reproduced the result for inference. But when I want to use the VGG16 model with weights retrain imagenet data,the acc was rised from 0,not a higher acc. First,I think the reason is that tfrecords convert the raw image to (-1.1) but caffe used the raw image which substract mean and convert RGB. Soon, I convert the data in tfrecords look like the data in caffe, but the acc is low too... Second I replace the categorical_crossentropy with sparse_categorical_crossentropy and cancell the one-hot coding. But it doen't work. I'm sorry for my English is elementary level.

In the file imagenet_utils.py, the prepocess_input function doesn't contain a normalization procedure, so if I am about to use pretrained VGG19, is it necessary to add this normalization procedure. What's more, why should RGB be changed to BGR. In other websites, the mean value of an image is [123.68, 116.779, 103.939] for RGB, but in this file, it is reversed. which mean value is suitable for the VGG19 in the data format RGB? Do I need to change the image format from RGB to BGR if I want to transfer VGG19 to other tasks? `def preprocess_input(x, dim_ordering='default'): if dim_ordering == 'default': dim_ordering = K.image_dim_ordering() assert dim_ordering in {'tf', 'th'}

if dim_ordering == 'th':
    x[:, 0, :, :] -= 103.939
    x[:, 1, :, :] -= 116.779
    x[:, 2, :, :] -= 123.68
    # 'RGB'->'BGR'
    x = x[:, ::-1, :, :]
else:
    x[:, :, :, 0] -= 103.939
    x[:, :, :, 1] -= 116.779
    x[:, :, :, 2] -= 123.68
    # 'RGB'->'BGR'
    x = x[:, :, :, ::-1]
return x`