-
I was just wondering if someone already tried to convert the model architecture to MobileNet-v2? It seems to be very similar to the used resnet bottleneck structure but inference would prop. way faste…
-
I am training edgetpu_mobilnet on the custom dataset and follow this link for the model selection. https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md
However, I …
-
Thank you for sharing this work. It helps me a lot.
I am trying to use mobilenetv3 backbone but I got some weight size mismatching problems.
I used the below additional script for mobilenetv3. Is …
-
### Feature request
# Feature Request
`transformers` models can be easily loaded across multiple devices using `device_map="auto"`. This will automatically allocate weights across available dev…
-
我在训练时，先使用了mobilenet，成果了，但是改为xcption时，miou一直不变为9.72，acc也不变化，这是什么原因
-
大佬，你使用的mobilenet 是不是修改过的，因为它的输入是192*192而不是224*224，小白提问。
-
I've trained yolov3 on mobilenet backend and get a good MAP(about 90M and 2 times faster than keras yolov3).Is anyone interested in this?I can share some of my code and discuss about it.
my email is …
-
```bash
root@ubuntu1804-lts-base:/scratch/dev/dev/dl-infer-perf# python3 infer_perf/onnx2trt.py mobilenet
[TensorRT] ERROR: Network must have at least one output
Traceback (most recent call last):
…
-
hello, how to change backbone like res18, mobilenet? And how to training without pre-train model
-
在imagenet实验中给出的是MobileNetV2，但是结果中是MobileNetV1。我查看了您这里的V2的结构和DKD工作中的V1结构相同，请问您这里的V2是命名有问题还是别的什么问题呢？