-
@orangese @22pilarskil
We're currently using a pretrained model from https://github.com/nyoki-mtl/keras-facenet. This model was trained on MS-CELEB-1M and achieved 99.4% LFW accuracy.
However,…
-
https://github.com/pbaylies/stylegan-encoder/blob/18919c2565e3947eafc152e320ba573b3e61ad08/encoder/perceptual_model.py#L125
Hey, seems like ref_img_features remain uninitialized, features_weight in…
-
When I am trying to simplify onnx model using
`$ python3 -m onnxsim facenet_frozen.pb new_frozen.pb` This is giving me error
> onnx.onnx_cpp2py_export.checker.ValidationError: The model does not hav…
ghost updated
5 years ago
-
Hi Tim,
I would like to use this facenet as a feature extractor, i.e., delete the last few FC layers.
My Code
`model = InceptionResnetV1(pretrained='vggface2', num_classes=8, classify=True).to(devi…
-
Is it possible to convert Facenet/TensorFlow implementation to Caffe Model for running with TensorRT on nvidia JetsonTX1?
-
# Summary of your issue
Hi! I'm trying to use OpenCV face CNN model. However, for the first frame the following code works, i.e., it detects the face and draws the rectangle. But for the next frames …
-
I followed issue #139. Here is my specific step:
Here is my code:
all_vars = tf.trainable_variables()
var_to_restore = [v for v in all_vars if not v.name.startswith('Mixed_8b')] in inception-renet-…
-
In some cases num_positives = 0, how to ensure the num_positives >0
-
##### System information (version)
- OpenCV => 3.4.1
- Operating System / Platform => Windows 64 Bit
- Compiler => Visual Studio 2017
##### Detailed description
So I'm training an **Inc…
-