Training a new model - Githubissues

t109368507 commented 1 year ago

Issue Type

Support

OS

Ubuntu

OS architecture

aarch64

Programming Language

Python

Framework

TensorFlowLite

Model name and Weights/Checkpoints URL

New training:MobileNetV3+DeeplabV3+PascalVOC Pretraining model: deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz

Description

env: Tensorflow:1.15.3

Using the pre-trained model in the website "deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz", adding metadata can run on the android platform, but using the following command to train a new model can not be inferred to the object normally, it is always inferred to the background, is there any need to modify ?

$ python3 deeplab/train.py \
    --logtostderr \
    --training_number_of_steps=500000 \
    --train_split="train" \
    --model_variant="mobilenet_v3_small_seg" \
    --decoder_output_stride=16 \
    --train_crop_size="513,513" \
    --train_batch_size=8 \
    --dataset="pascal_voc_seg" \
    --save_interval_secs=300 \
    --save_summaries_secs=300 \
    --save_summaries_images=True \
    --log_steps=100 \
    --train_logdir=${PATH_TO_TRAIN_DIR} \
    --dataset_dir=${PATH_TO_DATASET}

Thanks!

Relevant Log Output

No response

URL or source code for simple inference testing code

No response

PINTO0309 commented 1 year ago

If you have questions that are not related to the content of this repository, you can ask them here in the community. https://discuss.tensorflow.org/