automl

automl copied to clipboard

Hi, I tried to run `python3 infer.py --mode tf2bm --model_name efficientnetv2-s --model_dir ../../efficientnetv2-s/ --export_dir ../../efficientnetv2-s/saved_model` with pretrained models and got the following errors: ``` Traceback (most recent call last): File...

shuyuelan

How much does it take to train EfficientDet-D0 for one epoch in COCO train 2017? Thanks!

bryanbocao

Training Problem

4

Hi, i try to train EfficientDet-d2 for floorplan object detection here is my configuration :  here is my command :  After the...

refdinal22

Is it possible to convert tflite quantized ?

1

is it possible convert ckpt to tflite quantized by using model_inspect.py ? currently I convert ``` python model_inspect.py --runmode=saved_model --model_name=efficientdet-d0 \ --ckpt_path=$CKPT_PATH --saved_model_dir=$SAVED_MODEL_PATH \ --tflite_path=$TFLITE_PATH \ --hparams=voc_config.yaml ```

yi0109-sec

custom trained model inference issue on single image

2

python3 model_inspect.py --runmode=infer --model_name='efficientdet-d0' --hparams="image_size=600x400" --max_boxes_to_draw=100 --min_score_thresh=0.4 --ckpt_path=/home/angad/puretech/automl/efficientdet/model_weights/efficientdet-d0-train-eval-08/ --input_image=/home/angad/puretech/automl/efficientdet/testdata/men-who-love-dogs.jpg --output_image_dir=/home/angad/puretech/automl/efficientdet/testdata/ 2021-10-25 16:43:20.608362: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file...

ayennam

efficientnet v2| memory leak @ tf2 implementation ?

4

I tried running the efficientnet v2 implementation: `python3 main_tf2.py --mode=train --model_name=efficientnetv2-s --dataset_cfg=imagenet --model_dir=/home/eran/rm-debug/efficientnet/models/automl/efficientnetv2 --use_tpu=False --data_dir=/sda/Eran/imagenet/imagenet-home/tf_records/train`. While training I get a memory leak, the memory of the process keep increasing, even...

exx8

I used this algorithm to train a model containing 200 detection targets. Some of these detection targets are relatively similar, but the similarity in actual recognition is very low. In...

alvinhuai

train custom dataset problem

2

I meet the flowing problem, i don't know how to solve it. 2 root error(s) found. (0) INVALID_ARGUMENT: Input size should match (header_size + row_size * abs_height) but they differ...

bloom1123

efficientnetv2 export issue trained for custom dataset

1

Hi everyone, I trained / fine tuned an efficientnetv2-s from a custom dataset, without a problem. I changed the datasets.py with the necessary changes (my model was for example 278...

bnascimento

Error: Training on ImageNet from scratch

2

I am trying to train efficientnetv2 on ImageNet from scratch using the command from https://github.com/google/automl/tree/master/efficientnetv2 I am using the most recent version of the code (as of May 30th). The...

Basawaraj1