keras-applications

keras-applications copied to clipboard

Question about line 74 in inception_resnet_v2.py

1

First of all, thank you for your great work! I found this line a trouble. What is _layers_ in this line? Is it _None_ as in line 33? I got...

mdtjan

Cannot clone object <keras.wrappers.scikit_learn.KerasRegressor object at 0x7fdc9c3ba550>

1

Trying to hypertune ANN but getting an error while using fit..(grid1.fit(X_train, y_train)) Below is the code def create_model(dropout_rate,weight_constraint,optimizer,init,layers,activation): model = Sequential() model.add(Dense(nodes, input_dim=171, kernel_initializer=init, activation='relu', kernel_constraint=maxnorm(weight_constraint))) model.add(Dropout(dropout_rate)) model.add(Dense(1, kernel_initializer=init, activation='relu'))...

ghost

ValueError: Error when checking input: expected input_1 to have shape (3, 224, 224) but got array with shape (3, 3, 224)

2

_________________________________ test_resnet __________________________________ [gw0] linux -- Python 3.6.7 /home/ironman/anaconda3/envs/Tf_Cv_Ker/bin/python3 def test_resnet(): app = random.choice(RESNET_LIST) module = keras_applications.resnet last_dim = 2048 > _test_application_basic(app, module=module) test_check.py:197: _ _ _ _ _ _...

Nagaraj4896

Hi, I am facing the below error, when I try to run the object detection model using Yolo, AttributeError: 'NoneType' object has no attribute 'is_keras_tensor'

suravijayjilla

Add "The One Hundred Layers Tiramisu" model

1

I implemented the ["The One Hundred Layers Tiramisu"](https://arxiv.org/abs/1611.09326) model as a part of Google Code-In. The code can be viewed in [this Google Colab](https://colab.research.google.com/drive/1I2taXqYg6sgxA9vjfRmdp0J_8kE-ryYz). Because there is no image segmentation...

rickwierenga

how i can update the weights inside keras cnn layers i want to update both biases and weight during inferenc

2

### Summary ### Environment - Python version: - Keras version: - Keras-applications version: - Keras backend with version: ### Logs or source codes for reproduction

Uspark-dev

https://github.com/keras-team/keras-applications/blob/976050c468ff949bcbd9b9cf64fe1d5c81db3f3a/keras_applications/efficientnet.py#L175 This code will meet trouble when backend.image_data_format() == "channels_first". It should be change as below: ``` if backend.image_data_format() == 'channels_last': se = layers.Reshape((1, 1, filters), name=name + 'se_reshape')(se) else:...

ZJQbelief

### Summary ### Environment - Python version: - Keras version: - Keras-applications version: - Keras backend with version: ### Logs or source codes for reproduction

thaingiW

vgg16 has no dropout

1

I notice there is no dropout in the vgg16 code whereas dropout was used in the original paper. I wonder if there is a reason for removing it and whether...

don-tpanic

**System information** - TensorFlow version : `TF 2.0.0 stable + Keras 2.4.2 `(A )and `1.13.1 +Keras 2.3.1` (B) - Are you willing to contribute it (Yes/No): Yes **Describe the feature...

shartoo