-
Hello, I changed to efficiencydet-d0, but it still does n’t work
Th…
-
I ran the coco eval (5000) exactly per the readme:
https://github.com/google/automl/tree/master/efficientdet#5-eval-on-coco-2017-val-or-test-dev
to test out running in colab and hit an issue I di…
-
I am trying to retrain EfficientDet-d0 on **coco** from scratch by following the instructions in the readme file:
- STEP1:
`python3 train.py --snapshot imagenet --phi {0, 1, 2, 3, 4, 5, 6} --gpu 0…
-
@Jupanlee
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.206
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.330
Average Precision (AP)…
-
Hi, I want to detect a image lists in form of 'txt', and I change the code of build_input, but it also error in post process. Because the batch size of inference is 1, when send all images to the mode…
-
Hi Xuannianz,
Thanks for the great work on Keras-EfficientDet.
I followed the readme of training on MSCOCO with one GTX 1080 Ti:
train
STEP1: python3 train.py --snapshot imagenet --phi {0, 1, 2,…
-
Was happy to see the latest checkin addressing the TFLite issue.
However, I tested today under the new requirements of TF 2.2.0-rc4 and still hit the exact same issue as before (issue 341).
Really …
-
Hello, I'm using tf.2.1.0 and I have the following error:
Traceback (most recent call last):
File "main.py", line 383, in
tf.app.run(main)
File "/data01/wens/venv/tf20/lib/python3.6/sit…
-
I used your eval code,"python3 eval/common.py to evaluate by specifying model path there.",but error found,
ValueError: Layer #1 (named "stem_conv"), weight has shape (3, 3, 3, 32), but the saved we…
-
Can you reproduce the results reported in EfficientDet paper?