Stack Overflow
Stack Overflow

Questions tagged [keras-vggface]

12 questions
2
votes
1 answer

ValueError: Input 0 is incompatible with layer vggface_resnet50: expected shape=(None, 224, 224, 3), found shape=(None, 1, 224, 224, 3)

I want to use the code from https://morioh.com/p/a07857cbc76d to match faces from chokepoint dataset for my face project, I extracted the faces and want to use VGGface and cosine to match them, but got this error, would you please help…
Safoo Ra
  • 21
  • 4
1
vote
3 answers

keras_vggface: No module named 'keras.engine.topology'

There are several tutorials online that import a VGGFace model from keras_vggface like this: from keras_vggface.vggface import VGGFace However, I get the following error: ModuleNotFoundError: No module named 'keras.engine.topology' This problem…
jkortner
  • 549
  • 2
  • 8
  • 23
1
vote
1 answer

How to get embedding vector from an image using Deepface?

I have a face recognition project using features extraction. I want to generate the embedding vector using DeepFace or VGGFace instead of ResNet-34 without changing the whole scripts. Any help will be appreciated I've written a script (encoding.py)…
Adrian
  • 31
  • 3
0
votes
0 answers

No module named 'keras_vggface'

I am trying to install 'keras_vggface' at my Jupyter notebook (running python 3.) but I am getting the following errors : import os, sys, requests, json import pandas as pd # face verification with the VGGFace2 model import cv2 #from matplotlib…
nolan
  • 33
  • 4
0
votes
0 answers

Im using Vgg-Face model and keep getting this error whenever I try to run it

I keep gettin this error; Im implementing the Vgg-Face model but keep getting this error message. ResourceExhaustedError: Exception encountered when calling layer "conv2d_1" " f"(type Conv2D). Full error message InternalError …
rekas
  • 1
  • 2
0
votes
0 answers

get celebrity name in keras-vggface based on index in tensorflowjs

I'm using face-api.js Javascript API to develop a web app that user uploads her/his picture and we want to detect faces in the picture. On the other hand I used VGGface 16 model json formatted to predict that user uploaded image is similar to which…
Ahmad Badpey
  • 6,348
  • 16
  • 93
  • 159
0
votes
0 answers

Get 'No module named 'keras.engine.topology'' when I try to import keras_vggface

When I try to import vggface (after successful install) I get the message: ModuleNotFoundError: No module named 'keras.engine.topology' Does anyone know why this is the case and how I can fix it?
tewerty
  • 367
  • 1
  • 3
  • 9
0
votes
1 answer

In Transfer Learning can we change input size?

I am using VGG16 along with its pre-saved weights. and as this VGG16 was trained on (244 * 244) dimension Images. So can we change the input dimension to like (128 * 128) baseModel = VGG16(weights="imagenet",…
Raj_Ame09
  • 130
  • 1
  • 10
0
votes
1 answer

Tensor Tensor("flatten/Reshape:0", shape=(?, 2622), dtype=float32) is not an element of this graph

Hello StackOverFlow Team: I built a model based on (Vgg_Face_Model) with weights loaded (vgg_face_weights.h5). Note that I use tensorflow-gpu = 2.1.0 , and keras=2.3.1 , with Anaconda 3 create it as interpreter and used with pycharm But the code…
omar abd
  • 443
  • 1
  • 4
  • 7
0
votes
1 answer

Implementing lambda preprocess function for VGGFace

Hi I'm trying to make a network using transfer learning while fine tunning a VGGFace implementation: img_height, img_width = 224,224 module=VGGFace(model = 'resnet50',include_top = False,weights = 'vggface',input_shape = (img_height, img_width,…
lmglm
  • 3
  • 2
0
votes
1 answer

Retraining Custom VGGFace Model Yields Random Results

I am trying to compare a fine-tuned VGGFace model which uses VGGFace weights with a completely retrained model. When I use the fine-tuned model, I get decent accuracy score. However, when I retrain the entire model by unfreezing the weights, the…
Dawei Wang
  • 160
  • 12
0
votes
1 answer

How to correctly concatenate a Flatten layer and a feature vector in Keras

I just need to concatenate a flatten layer and a feature vector in Keras. This is the code: #custom parameters n_features = 38 vgg_model = VGGFace(include_top=False, input_shape=(224, 224, 3)) last_layer = vgg_model.get_layer('pool5').output x =…
shinigami023
  • 63
  • 1
  • 5