Stack Overflow
Stack Overflow

Questions tagged [tensorflow-model-garden]

TensorFlow Model Garden is a GitHub repository that provides state-of-the-art machine learning models implemented in TensorFlow. Use this tag to ask questions about TensorFlow official model garden.

Resources TensorFlow Model Garden GitHub TensorFlow GitHub

83 questions
7
votes
0 answers

tf-models: official.vision.detection Mask-RCNN Invalid argument: indices[1,63] = [1, -1] does not index into param shape [2,100,112,112]

I am trying to train a Mask RCNN model based on the official MaskRCNN model present here: tensorflow/models. Below are the steps I followed: Created a tfrecord for training and validation. I have checked encoding and decoding of the tfrecords, it…
NVS Abhilash
  • 574
  • 7
  • 24
6
votes
1 answer

Loading checkpoints while training a Faster-RCNN model on a custom dataset

I'm trying to load checkpoints and populate model weights using The Faster-RCNN architecture (Faster R-CNN ResNet50 V1 640x640 to be precise, from here. I'm trying to load the weights for this network similar to how it's done in the example notebook…
Rohan Gautam
  • 146
  • 1
  • 9
4
votes
1 answer

colab_utils.annotate(), annotation format

I am following the Tensorflow notebook for Few shot learning ( https://colab.research.google.com/github/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb#scrollTo=RW1FrT2iNnpy ) In it,…
ahsan mukhtar
  • 423
  • 7
  • 21
4
votes
1 answer

How to save best models in latest Tensorflow Object Detection API V2 with TF2?

Recently I am trying Tensorflow Object Detection API V2 with TF2, and I've sucessfully trained a network. However, I found little information about how to save the best model. I've found some simple tutorials that don't talk much about these…
user10253771
  • 670
  • 5
  • 19
4
votes
1 answer

Normalize input for Tensorflow object detection API

Is preprocessing like input normalization made by default by Tensorflow Object Detection API ? I cannot find anywhere any documentation on it. There is an option called 'NormalizeImage' in the DataAugmentations. In all the configuration files for…
rok
  • 2,574
  • 3
  • 23
  • 44
3
votes
1 answer

Why is 32768 used as a constant to normalize the wav data in VGGish?

I'm trying to follow along with what the code is doing for VGGish and I came across a piece that I don't really understand. In vggish_input.py there is this: def wavfile_to_examples(wav_file): """Convenience wrapper around waveform_to_examples()…
filifunk
  • 543
  • 1
  • 6
  • 18
3
votes
1 answer

Error "indices[0] = 0 not in [0,0)" when training CenterNet MobileNetV2 FPN 512x512 with tensorflow object detection api

I'm running the tensorflow object detection api according to this guide https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html#configuring-a-training-job however with a slightly modified code for making the record…
mattiasnasstrom
  • 31
  • 2
3
votes
1 answer

How to train a custom model for object detection using models/official/vision/detection?

How to train a custom model for object detection using models/official/vision/detection?
user11530462
2
votes
1 answer

protobuf incompatibility when installing tensorflow model garden

I try to test my installation of tensorflow model garden and execute the following command in my PowerShell: python object_detection/builders/model_builder_tf2_test.py Thereby, I get the following error message: Traceback (most recent call last): …
Christian01
  • 307
  • 1
  • 5
  • 19
2
votes
1 answer

How to mask [PAD] and [SEP] tokens to prevent their prediction and loss calculation for NER task on BERT models?

I am trying to fine-tune BERT model for NER tagging task using tensorflow official nlp toolkit. I found there's already a bert token classifier class which i wanted to use. Looking at the code inside, I don't see any masking to prevent tag…
Mani Rai
  • 665
  • 2
  • 9
  • 22
2
votes
1 answer

Visualize proposal regions from RPN head in Faster R-CNN with Tensorflow Object Detection API

I'm trying debug my trained Faster R-CNN model using Tensorflow Object Detection API and I want to visualize the proposal regions of RPN on an image. Can anyone tell me how to do it? I found a post here but it hasn't been answered. I tried to export…
iumyx
  • 21
  • 3
2
votes
1 answer

Deeplabv3 re-train result is skewed for non-square images

I have issues fine-tuning the pretrained model deeplabv3_mnv2_pascal_train_aug in Google Colab. When I do the visualization with vis.py, the results appear to be displaced to the left/upper side of the image if it has a bigger height/width, namely,…
Darkhorrow
  • 37
  • 1
  • 9
2
votes
1 answer

How to increase num_classes in ssd_mobilenet_v1 tensorflow

I am using ssd_mobilenet_v1_coco.config and I changed the value of num_classes to 20 after adding 13 things after planning training python model_main.py --alsologtostderr --model_dir=training/…
임철규
  • 37
  • 5
2
votes
1 answer

Use tensorboard with object detection API in sagemaker

with this I successfully created a training job on sagemaker using the Tensorflow Object Detection API in a docker container. Now I'd like to monitor the training job using sagemaker, but cannot find anything explaining how to do it. I don't use a…
rok
  • 2,574
  • 3
  • 23
  • 44
2
votes
1 answer

How to use ssd_mobilenet_v2_mnasfpn_coco in android app

I downloaded ssd_mobilenet_v2_mnasfpn_coco and untar it, found there is already a tflite file called model.tflite, I want to know how to use it in android app, can I replace original detect.tflite at object_detection android demo app with this…
Wade Wang
  • 536
  • 6
  • 11
1
2 3 4 5 6