keras-arcface

keras-arcface copied to clipboard

If the input is given as `model = Model([input, label], output)` and a generator object is used to call `model.fit` like `model.fit(input_generator, ....)` How will the labels be passed to...

sohamsatyadharma

why I get a 100% acc on the valid data?

11

sosoIrving

**model.save("path")** yield the following error: ` NotImplementedError: Layer ArcFace has arguments in "__init__" and therefore must override "get_config". ` To fix the issue, I implemented the get config function for...

tchaye59

How to predict the class of a new image without sending the label

4

i want to use the trained model to predict the class of a test image without sending the label, is it possible? currently, the implementation required sending the Keras "predict"...

almoghitelman

How to predict each class probability

2

**how to predict the class probability? when I set the output to arcface output (softmax) w.r.t number of class, I got an error when run this model = Model(inputs=model.input[0], outputs=model.layers[-1].output)...

farhantandia

how to predict by trained model?

2

`cosface_model = load_model('models/attention_vgg8_cosface_3d/model.hdf5', custom_objects={'CosFace': CosFace}) cosface_model = Model(inputs=cosface_model.input[0], outputs=cosface_model.layers[-3].output) cosface_features = cosface_model.predict(X_test, verbose=1) cosface_features /= np.linalg.norm(cosface_features, axis=1, keepdims=True)` as far as i know, cosface_features is 3d-coordinate for each cls, how...

chenyanyin

Thanks for great code! but i am just trying to use your model to multi label image dataset.(5 classes and y_train like "01001") please, can you advice the points of...

eksis77

different examples

1

I see different examples in README.md and archs.py ``` x = Dense(args.num_features, kernel_initializer='he_normal', kernel_regularizer=regularizers.l2(weight_decay))(x) x = BatchNormalization()(x) output = ArcFace(10, regularizer=regularizers.l2(weight_decay))([x, y]) ``` ``` x = Dense(512, kernel_initializer='he_normal')(x) x =...

sonfire186

Training is so slow, what's wrong?

3

Hi, I'm doing a 4 classes classification mission. I use pre-trained VGG19 as the base model, and add ArcFace after it. I trained the model for a while, but the...

asjiangh

What is the meaning in ArcFace Loss formula?

2

Hi. Thanks for your great implementation. Im trying to understand the mathematics behind the ArcFace in your implementation. But when I read to this line the **metrics.py** ` logits =...

vmthanh