-
## Fix the model test for `mobilenet_v2_quantized_qat.py`
1. setup env according to [Run a model under torch_xla2](https://github.com/pytorch/xla/blob/master/experimental/torch_xla2/docs/support_a_…
-
Hi,
Previously we have been successfully running our custom YOLOv5 model on the NPU of Rockchip 3588 platform.
Now we want to porting our platform to STM32MP2. From the wiki guide, object detectio…
-
Hi, we encountered an issue when generating the proof. We have converted the resnet50 model types to TFLite. However, after processing about 10 layers, the program crashed with “NotEnoughRowsAvailable…
-
Hello, we encountered the following problems when we replaced Resnet101 with Mobilenet_v2. How can I solve it?
Traceback (most recent call last):
File "train.py", line 185, in
train()
F…
huaxv updated
4 years ago
-
I used mobilenet V2 with CasCade R-CNN network training, but compared to Resnet101, the accuracy rate is reduced by 20%, but the paper of mobilenet V2 will not decrease so much, which is about 2%. The…
huaxv updated
4 years ago
-
I think it is a good idea to add mobilenet v3
It is better than mobilenet v2 and more efficient than most backbones present here.
Are you planning on adding it soon ?
-
### 🚀 The feature
`torch.compile` is a Pytorch feature that compiles the model into static kernels using a JIT. More information on: https://pytorch.org/tutorials/intermediate/torch_compile_tutoria…
-
MobileNet is a new architecture from Google (https://arxiv.org/abs/1704.04861) that is designed to run on mobile devices making it a perfect fit for cnndroid: https://github.com/Zehaos/MobileNet
I …
-
How can I modify the backbone using MobileNet?
-
```
weightsPath = "frozen_inference_graph.pb"
configPath = "ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt"
model = cv2.dnn_DetectionModel(weightsPath,configPath)
```
![image](https://user-im…