Stack Overflow
Stack Overflow

Questions tagged [mobilenet]

205 questions
0
votes
1 answer

Trying to custom train MobilenetV2 with 40x40px images - wrong results after training

I need to classify small images in 4 different categories, +1 "background" for false detection. While training the loss quickly drop to 0.7, but stay there even after 800k steps. In the end, the frozen graph seems to classify most images with the…
Robin D.
  • 48
  • 5
0
votes
1 answer

SSD Mobilenet Input Image Size

I would like to train an Object detector using Mobilenet SSD Model on a custom dataset. Looking at the config file of Mobilenet, there is a block called image_resizer{} which I think the default is 300x300, but my available images is in 224x224. Is…
kjell324
  • 1
  • 2
0
votes
1 answer

TensorFlow transfer learning ValueError

I was trying transfer learning, on an image classification problem, on google colab and when I ran this code: # Setup input shape to the model INPUT_SHAPE = [None, 244, 244, 3] # batch, height, width, colour channels # Setup output shape of the…
Aditeya
  • 303
  • 2
  • 10
0
votes
1 answer

Changing MobileNet Dropout After Loading

I am working a transfer learning problem. When I create a new model from just the Mobilenet, I set a dropout. base_model = MobileNet(weights='imagenet', include_top=False, input_shape=(200,200,3), dropout=.15) x = base_model.output x =…
theastronomist
  • 955
  • 2
  • 13
  • 33
0
votes
1 answer

Face Recognition: High validation accuracy but performs very poor on real time face recognition

I am making a CNN model for face recognition in which I have used Mobilenet. While training I got the val_acc of as high as 90 percent but when I test it on a real video from the webcam or some test video the model performs poorly. What could be the…
Mayank Goel
  • 11
  • 2
0
votes
0 answers

mobilenetv1 trained with custom dataset Quantization Size problem

I am working on an object detection software, basically i am using TensorFlow objet detection API on Python with MobileNetV1, i have trained the model with my own dataset. The frozen_inference_graph.pb file resulting of the training with my dataset…
rfourdinier
  • 1
0
votes
1 answer

what should be the input and output forom of variables for float object detection model

https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_ssd_tflite_v1.zip I am making an android object detection app with gpu delegate support. The above link is for tensorflow lite object detection float model. There is no…
user11375418
0
votes
1 answer

Saving image in a real time object detector

I am currently running a real-time object detector using SSD MobileNetv2 in TensorFlow 1.x and would like to know if there are any ways where I can save an image when one of the class gets detected by the video stream. PATH_TO_FROZEN_GRAPH =…
user8996213
0
votes
1 answer

Aborted Caffe training - no error message

I'd like to train my network with caffe but unfortunately, when I try to run train.sh, the process gets aborted showing no specific error message. I already created my pre-trained weights, my model.prototxt and the LMDB database which I checked to…
Totemi1324
  • 468
  • 1
  • 6
  • 19
0
votes
0 answers

Trouble tracing error "Invalid Metadata Provided"

I followed this tutorial to learn how to use the tensorflow.js model mobilenet in node.js:link Now I am trying to use my own tensorflow.js model trained in teachable machine using the @teachablemachine/image package: link Here is my code: const tf =…
r3vdev
  • 315
  • 3
  • 10
0
votes
2 answers

Tensorflow Object Detection API: Training gets stuck at step=0 for ssd + mobilenetv2 with custom data

I wanted to do transfer learning using a ssd + mobilenetv2 model with my own images. I have only one class. The images were downloaded from OpenImageDataSet. I used tensorflow's object detection API. But the training stuck at step = 0. I verified…
jackyvr
  • 11
  • 1
  • 4
0
votes
1 answer

Some questions about the required 300x300 input of the quantized Mobilenet-SSD V2

I want to retrain quantized Mobilenet-SSD V2 model so i downloaded the unlabeled folder from COCO. This model requires input size of 300x300 but i succeeded retrainig it once on pictures of a different size and it worked (poorly, but worked). Also,…
Gal Elias
  • 11
  • 2
0
votes
0 answers

Convert MobileNet from Keras to Tensorflow Lite

I'm using Keras 2.2.5, Tensorflow 1.15.0 and I want to convert MobileNet to Tensorflow Lite in order to use in flutter app: my code in this link I've tried everything but still got this stuck from keras.layers import DepthwiseConv2D, ReLU from…
Ngô Nhật Trí
  • 1
  • 1
0
votes
1 answer

How to load model back from cpkt, .meta, .index and .pb files for Mobilenet v3?

I have downloaded checkpoints along with model for Mobilenet v3. After extraction of rar file, I get two folders and two other files. Directory looks like following Main Folder ema (folder) checkpoint …
Awais Hussain
  • 392
  • 1
  • 11
  • 25
0
votes
0 answers

Loading mobilenet_v2 from hub conf gives error: cannot import name 'resnext50_32x4d'

model = torch.hub.load('pytorch/vision:v0.5.0', 'mobilenet_v2', pretrained=True) Importing the mobile net gives an error because its dependency 'resnext50_32x4d' cannot be imported. Is this the only way to use the mobile network in torch or how can…
Nidhi Joshi
  • 1
  • 4
1 2 3
…
13 14