MG_Chen

pretrained model about EfficientNet

1

Where to download pretrained model about EfficientNet？ Thanks！

PPTSM转onnx模型时，temporal_shift算子不支持。

4

请问paddle官方有替代的算子吗？ 另外我自己参考github上其他人的操作，修改一个op，麻烦帮忙看看这种方式对不对，我想用到移动端效率可以吗？ def shift_paddle(x, seg_num, shift_ratio): nt, c, h, w = x.size() shape = x.shape # [N*T, C, H, W] reshape_x = x.reshape((-1, seg_num, shape[1], shape[2], shape[3])) #[N, T, C,...

您好，在您的refinedet_mobilenetv2中,最后的P6、P5网络层中为什么num_output=6*class_num？而在标准的refinedet中num_output=3*class_num.

Unknown layer type: DepthwiseConvolution

1

Hello, which version of your caffe version is used, the original version of refinedet does not support depthwise.

Hi，Why the tensorrt model is only 7.6kb and can't detected any face？ and the results of the caffe model are normal。

PPTSM视频分类模型onnx转rknn报错！

3

D Using CPPUTILS: True I Start importing onnx... I Current ONNX Model use ir_version 6 opset_version 10 I Call RKNN onnx optimize fail, skip optimize D Calc tensor Initializer_fill_constant_191.tmp_0 (1,...

Thank you!

运行测试脚本时报错！

2

RuntimeError: max_pool2d_with_indices_out_cuda_frame failed with error code 0 File "/data_1/software/yes/envs/pytorch/lib/python3.6/site-packages/torch/nn/functional.py", line 488, in _max_pool2d input, kernel_size, stride, padding, dilation, ceil_mode) RuntimeError: **max_pool2d_with_indices_out_cuda_frame failed with error code 0** 请问，这是什么原因导致呢？测试图像需要提前resize到320*320尺寸才能用吗？

[Feature] 如何加载预训练模型进行finetune？

4

### Describe the feature train.py文件中只有--resume，没有--checkpoint，如何加载预训练模型进行finetune操作呢？ ### Will you implement it? - [x] I would like to implement this feature and create a PR!