Stack Overflow
Stack Overflow

Questions tagged [mobilenet]

205 questions
0
votes
0 answers

Error while running custom models on Google Coral EdgeTPU, "list index out of range"

I tried running a custom model on the Google Coral EdgeTPU, but it is causing the following error: File "detect.py", line 102, in main() File "detect.py", line 74, in main objs = get_objects(interpreter,…
Ojas Ashwini Ravindra
  • 1
0
votes
0 answers

MobileNet library for React native throws error 'fetch undefined'

I am trying to use the mobile net library to use the trained model in my Tensorflow React Native project. However, I am stuck at a very mysterious problem. When I am trying to load the model, it throws the following error. Cannot read property…
Vijay Kumar Kanta
  • 1,111
  • 1
  • 15
  • 25
0
votes
0 answers

Launch a neural network in a browser

After running the neural network in the browser, an error appears('The dtype of dict['input_tensor'] provided in model.execute(dict) must be int32, but was float32'), but it seems to me that the problem is not in the input_tensor, but in the neural…
Moseich
  • 11
  • 1
0
votes
0 answers

InvalidArgumentError: Graph execution error for MobileNet model

I'm rather new to the world of DL and I'm trying to run a MobileNet model to do a multi-class classification but I keep getting this invalidargumenterror when I run it: code snippet datagen = ImageDataGenerator( rotation_range=0.5, …
bloop
  • 1
  • 1
0
votes
1 answer

How to use mobilnet v2 for binary classification in pytorch?

I'm trying to train a binary classifier using transfer learning in mobilenet v2 but am not sure how to freeze the layers and make it classify between 0 and 1. Any help would be appreciated
anushka agarwal
  • 3
  • 1
  • 3
0
votes
0 answers

Pycharm can't understand modelcaffe file

i was trying to use MobileNet SSD model for Object detection project, and i wanted to use a caffemodel with prototxt file and i downloaded these files from here. After i downloaded files and put them in the same directory of my project, pycharm…
Raed
  • 1
  • 1
0
votes
2 answers

ValueError: Shapes (None, None) and (None, None, None, 3) are incompatible

I am using EfficientNetV2B0, everything works perfectly until when I try to fit the model. On the train_generator I tried the class_mode = 'sparse', and also class_mode = 'categorical', it throws different kinds of error messages. It took me few…
Bet
  • 19
  • 2
0
votes
0 answers

InvalidArgumentError in transfer learning

I am trying to create a Fine Tuned model on Keras using the tf.keras.utils.image_dataset_from_directory method to pass in the training and validation data. This is the code I have written: import tensorflow as tf from tensorflow import keras import…
Antonios
  • 1
  • 2
0
votes
1 answer

Failing During Training MobileNetSSD Object Detection on a Custom Dataset Google Colab

I'm following a Google Colab guide from Roboflow to train the MobileNetSSD Object detection model from Tensorflow on a custom dataset. Here is the link to the colab guide: https://colab.research.google.com/drive/1wTMIrJhYsQdq_u7ROOkf0Lu_fsX5Mu8a The…
Max Claesson
  • 15
  • 3
0
votes
1 answer

Couldn't convert MobileNet V2 PyTorch to mlmodel using CoreML tools

I want to convert PyTorch MobileNet V2 pre-trained model to .mlmodel using coremltools. here is my code: import torchvision import torch import coremltools as ct # Load a pre-trained version of MobileNetV2 torch_model =…
Amine Sehaba
  • 122
  • 6
0
votes
0 answers

SSD MobileNet V2 - Does feeding in a 640x480 image into a 300x300 model reduce accuracy?

Does feeding in a 640x480 image into a 300x300 SSDMobileNetV2 model reduce accuracy? I am starting with a 2560x1440 image, which I then split into 12 distinct images of 640x480. The speed of this setup is great. Only 12 images to run through for…
Isaac Padberg
  • 200
  • 8
0
votes
1 answer

why the classification models use top5 accuracy in evaluation metrics?

I was checking the evaluation metrics in Resnet and Mobilenet and I was wondering why top5 accuracy is used for evaluation metrics? The highest probability will be selected and top1 accuracy is the best for these applications.
Matin Hoseini
  • 1
0
votes
0 answers

Keras Image Classification on specific portion of image

Is it possible to perform image classification on a specific portion of images rather than a whole image? I have an image Keras sequential image classifier where I give an image as input and it gives predictions. Is it possible to pass the location…
Ankit Sachan
  • 7,690
  • 16
  • 63
  • 98
0
votes
0 answers

Uncaught (in promise) Error: Operands could not be broadcast together with shapes 2034 and 2034,2

I trained a mobilenet_v3_small model using Tensorflow version 1.15.2 (object detection API), then converted it to tfjs. I was able to make predictions in python but when I try to run the model using tfjs, I get the above error. I am not sure that…
user15840394
  • 23
  • 2
0
votes
1 answer

Execution of mobilenet v2 for object detection with Tensorflow JS

I trained different types of mobilenet v2 models using Tensorflow object detection API, then converted them to tfjs and ran them in the web. It seems that the execution of these models only supports the executeAsync() method. I feel like being able…
user15840394
  • 23
  • 2
1 2 3
…
13 14