keras-team/keras-applications
Reference implementations of popular deep learning models.
PythonNOASSERTION
Issues
- 0
Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (6, 64)
#144 opened by Sanbot-okk - 15
Trouble loading new ResNet models
#100 opened by mazatov - 7
AttributeError: 'Model' object has no attribute 'metrics_tensors' running mask r-cnn
#145 opened by jiangjiangjianggx - 4
ValueError: If your data is in the form of symbolic tensors, you should specify the `steps` argument (instead of the `batch_size` argument, because symbolic tensors are expected to produce batches of input data)
#123 opened by abhisheksrivastava2397 - 4
When to update MobileNetv3?
#135 opened by Stealers - 3
Error while fetching URL in VGG16
#107 opened by Shwetago - 17
For what reason I need to use a specific input shape when loading imagenet weights, even though any shape works fine when transferring?
#122 opened by DableUTeeF - 2
NameError: name 'keras_applications' is not defined
#109 opened by denka0711 - 0
- 0
- 4
Error coming when creating the Object of Class ImageDataGenerator from keras.preprocessing.image
#139 opened by manojrustagi79 - 0
glove embeddings with keras
#143 opened by csharma - 0
Pretrained VGG has multi input sizes?
#142 opened by cuongth95 - 0
glove embeddings for keras layer
#141 opened by csharma - 0
Regarding the model weight licenses
#140 opened by ssrp - 2
How to identify both cats and dogs
#126 opened by seraphD - 2
Keras decoder.predict won't work
#137 opened by Elesa - 2
Parameter 'depth_multiplier' has been deprecated in MobileNetV2 API, docs don't mention this
#108 opened by SJCaldwell - 3
- 2
- 2
Pretrained model: ResNet50_v1
#138 opened by wlt-cortex - 2
Input 0 is incompatible with layer k_max_pooling_12: expected ndim=3, found ndim=2
#111 opened by aviknayakusa - 1
Difficulty in finding the name of category and respective probabilities of an image
#112 opened by csitaula - 1
Keras plot_model error
#104 opened by yaoxunji - 1
Trained Depthwise mobilenet, but size is h5 file is 24 MB, need to reduce the h5 file size.
#127 opened by vasanthhr - 4
No module named 'resnet_152'
#133 opened by DarkDetectiv - 7
I'm having same issue, i've install pip install -U git+https://github.com/keras-team/keras git+https://github.com/keras-team/keras-applications but found error.
#132 opened by DarkDetectiv - 0
- 3
Data augmentation with noise resulted in unreasonable performance improvement on ResNet50
#134 opened by szlge - 3
- 4
Inconsistent imagenet preprocessing function
#128 opened by lagejoao - 0
ImageNet Weights being reset - only able to achieve 53% accuracy, whereas 69.5% was achieved in the paper
#124 opened by s36srini - 2
Supporting ResNet 1by2 variants
#115 opened by avitex - 1
- 2
MobileNetV1: Adding Regularizers
#117 opened by fzyzcjy - 2
Why are there applications missing? (AttributeError: module 'keras.applications' has no attribute 'ResNet101/ResNeXt50/ResNeXt101')
#118 opened by EmielBoss - 1
How to do transfer learning on a custom trained ResNet50 with different image size
#97 opened by aezco - 0
MobileNetV1: Adding
#116 opened by fzyzcjy - 1
Reshape error when making ResNext model with input shape (None, None, 3).
#110 opened by YuanYunshuang - 1
no module named music tagger crnn
#106 opened by SibtainRazaJamali - 7
Self-train These Models on ImageNet
#103 opened by fzyzcjy - 0
- 2
- 0
Why MSE calculated by Keras Compile is different from MSE calculated by Scikit-Learn?
#105 opened by nxthuan512 - 2
High CPU utilization upon model.predict()
#102 opened by Terizian - 1
- 1
- 6
Unnecessary ValueError in MobileNetV2
#92 opened by see-- - 3
VGG16/19 models do not train
#93 opened by htrenquier - 2
Is a bug in NasNet ?
#95 opened by K0BigYang