-
I have trained mobilenet from scratch with my custom dataset. Can you guide me how to evaluate my model using the validation set(tfrecord files) and eval_image_classifier.py and save the results to a …
-
https://github.com/liangfu/mxnet-mobilenet-v2/blob/b3e26ca3ce1aff6e190d6e148b6fe778e11bc38f/symbols/mobilenetv2.py#L114
please fix this code， according to 1801.04381 v3.
misunderstood you code (…
dwSun updated
6 years ago
-
Hi, Thanks for your contribution.
I'm working training mobileNet v3 on ImageNet.
Have you finished trained the model? If so, could you share the model on ImageNet?
RYYAI updated
5 years ago
-
A well-trained raccoon model only recognizes raccoons.
How do you identify more objects with ssd_mobilenet_v1_coco?
Load two models at the same time?
Is there a better way
-
Is 69.49% top1 normal with reactnet with mobilenet backbone with full-precision weights and binary activations? I use ```python3 train.py --data=/datasets/imagenet --batch_size=256 --learning_rate=1.2…
-
### 🐛 Describe the bug
Following the [tutorial](https://pytorch.org/tutorials/intermediate/realtime_rpi.html) the program stops with
`[1] 182488 illegal hardware instruction (core dumped)`
…
-
Thank you for your excellent implementation of mobilenet-v3. However, it has been puzzling me that I cannot reach the same top-1 and top-5 precision and recall scores as the same in original paper. It…
-
Hi!
The model trained with Pytorch just finished training :)
![screenshot from 2018-03-16 22-54-42](https://user-images.githubusercontent.com/18093625/37548019-0b79e448-296d-11e8-91c7-32f6dec873a…
-
Thanks for your great work.
There are 2 differences between this mobilenet_v2 and original paper:
1. no expand layer in the first bottleneck block
2. stride=2 at conv4_3/dwise other than conv4_7/d…
-
楼主你好！请问下如何要修改backbone为其他网络，例如mobilenet，我都需要在train.py中修改哪些代码？期待楼主的回答：）