-
Training mobilenetv3-ssd model with coco datasets, and convert it to ncnn, then i changed the .param file manually. When I use ncnn to inference the image, i got the "detection_out" error, like this
…
yy2yy updated
4 years ago
-
我修改了mobilenetv3中的Width multiplier 参数，默认为1.0，结果训练不了，网络shape对不上，请问还需要修改哪些部分。
-
Code:
```python
import torch
from torch import nn, Tensor
from torch.nn import functional as F
def _make_divisible(v, divisor, min_value=None):
"""
This function is taken from the o…
-
I appreciate your effort of making these experiment results and sharing code. I am quite interesting in the experiment on ImageNet. I try but cannot produce your result.
My training strategy is ba…
-
I got the error when i use the model of mobilenetv3_small to train,and i used my own dataset like as VOC. Would you give me some advice?
And,would you tell me the torch version and torchvision versio…
-
paddleclas2.5使用MobileNetV3_large_x1_25训练multilabel数据集NUS-SCENE-dataset之后，导出成onnx格式后，onnx推断的结果和原始模型结果对不上，图片传不上来，我把文本结果直接粘贴出来了：
1、原始模型的推断结果：
[{'class_ids': [23], 'scores': [0.58354], 'file_name': '/Vi…
-
hi, all,
has anyone succeed to convert mobilenetv3 onnx to coreml yet? I found it will get `Error while converting op of type: Conv. Error message: provided number axes -1 not supported` error.
…
-
Dear author,thanks for watching my issue.Due to the limitation of computer computing resources，I can't pre-train the mobilenetv3+CA model.Do you have any pre-trained model for me to keep the reaserch?…
-
What are these levels? https://github.com/lufficc/SSD/blob/68dc0a20efaf3997e58b616afaaaa21bf8ca3c05/ssd/modeling/backbone/mobilenetv3.py#L177-L182
and these
https://github.com/lufficc/SSD/blob/68d…
ksv87 updated
3 months ago
-
deeplab/ckpt/deeplab_mnv3_small_cityscapes_trainfine/model.ckpt
Traceback (most recent call last):
File "/Users//DeepLearning/ml/hand/deeplab/fingertip_seg_train/deeplab/train.py", line 464, in
…