-
I am running into issues at the line:
`model.build_train_functions(loss_weights=loss_weights, **loss_config)`
I am getting the following error
```
-------------------------------------------…
-
I would like to know how did you train model whose weights are loaded into chosen model (Resnet, Senet).
Did you train the model in keras, how you implemented triplet loss, what training parameter…
-
## This is the code as shown in the documentation: https://pypi.org/project/celeb-detector/
```python
import celeb_detector # on running for the first time, this will download vggface model
# img…
-
This is a tracking issue for different face embeddings. The main criteria what the cropping procedure is (is it compatible with dlib?) are how well it performs on different benchmarks and the size. LF…
-
```
tensorflow v1.4
keras : v2.1.1
keras_vggface : v0.5
```
**Bug reports:**
Senet50 architecture is not working as intended. The weights or architecture implementation should be checked aga…
-
您好，请问您可以给一下checkpoint_[1, 1]_33_0.002_89.162.pth.tar 的网络结构代码吗？想加载这个vggface的预训练模型，但是不确定网络结构如何？里面好像有drop7.weight和drop7.bias，不确定是什么结构？
-
The loss of age does not decrease, about equal 3.6
-
filename = "/usr/local/lib/python3.7/dist-packages/keras_vggface/models.py"
text = open(filename).read()
open(filename, "w+").write(text.replace('keras.engine.topology', 'tensorflow.keras.utils'))
…
-
Assuming the embedding vectors for faces are clustered somewhat according to gender (to account for male and female differences in facial features), I am guessing it's possible to train a classifier t…
-
Your codes works amazingly well. However, use Spectral Normalization will converge VERY fast and nice !
That is all. I changed 2 things: (1) Added Spectral Normalization to Conv2D layers of Discrim…