-
I am working on mobilenet-person detection. I can not generate or import DMA IP. I am using `Efinix Efinity 2023.1.150.2.4 ` version. Is it a bug? Thank you for answering.
@yhlee-efx
-
> Also regarding the modification: since you are creating a the first layer (which outputs feature_2) under different variable scope, my bet is it would not be shared with the layer that creates featu…
-
Hi again.
after succesfully trained two models, mobilenet_256 and resnet18_256 where 256 is the image size.
now im starting the process of validating and converting to onnx and trt.
Now i have two …
-
The speed of VGG backbone is 45FPS. When I replaced VGG with MobileNetV2, although the memory becomes small, the speed becomes half slower than that of VGG, only 26fps. Is this normal？
-
**模型压缩的集合**
https://github.com/cedrickchee/awesome-ml-model-compression
**模型压缩四大方向，计算机视觉领域的低功耗深度学习前沿技术综述**
https://www.infoq.cn/article/Y8UuJHRTGvrZVKKPJFh2
**当前深度神经网络模型压缩和加速都有哪些方法？**
https://zhu…
-
When using the ssd_mobilenet_v1_fpn_shared_box_predictor_640x640_coco14_sync.config, google.protobuf.text_format.ParseError: 82:7 : Message type "object_detection.protos.SsdFeatureExtractor" has no fi…
-
can u please explain How can I segment human using mobilenet
-
Hi,
I am able to run SSD MobileNetV2 and CenterNet MobileNetV2 (boxes prediction) on my android device. When I compare inference speed of the models on my android device I get below results:
inf…
-
你好，请问下你移植过MobileNet-SSD吗？
-
Hi, I would like to know if it is possible to use Mobilenet emb256 trained with Emore Dataset for commercial application. You explicit noted that Webface pretrained models cannot be used, but it is st…