-
How do I train on a custom dataset?
-
TensorFlow : 2.0
TensorRT : 7.0
CUDA : 10.0
Cudnn : 7.3
GPU : 1050 ti
Python : 3.7.6
`export MODEL=efficientdet-d0`
`python model_inspect.py --runmode=bm --model_name=$MODEL --ckpt_path=ckpt/…
-
my custom dataset have two classes, i convert the dataset to coco format; The training process is normal, but predict some images, I looked at the picture results, to my surprise, only one category c…
HK017 updated
4 years ago
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu18.04 x86_64, CUDA10
- TensorFlow installed from (source or binary): binary
- TensorFlow version (or github S…
-
when I use `freeze_model` to save a frozen.pb file, the weights in frozen.pb are not equal weights in ckpt file.
how to get the correct frozen.pb, and the pb does not contain preprocess and postproc…
-
Thanks for the good work!
Just wanted to mention that I have tried the two currently most stared EfficientDet PyTorch repos on Github, and neither reproduce the paper results on COCO, not even clos…
-
Hi, thank you for your hard work and open sourcing the code!
I tried training, but the following error occurred.
Command:
python main.py --training_file_pattern=tmp/train/train* --model_name=effi…
-
I have converted my dataset to tfrecord format.
When i trying to eval my dataset,i used this command
```
python efficientdet/main.py --mode=eval \
--model_name=efficientdet-d4 --model_dir=/t…
-
Hi,
You need to update https://github.com/toandaominh1997/EfficientDet.Pytorch#training-efficientdet
**Change :**
- To train EfficientDet using the train script simply specify the parameter…
-
When using frozen pb file to do infernece, have erros like
```
(0) Failed precondition: Error while reading resource variable efficientnet-b0/blocks_4/depthwise_conv2d/depthwise_kernel from Contai…