FileNotFoundError: [Errno 2] No such file or directory: 'out/yolov2.param'

[GramJr]

Hello, after

python train.py -d custom -v slim_yolo_v2 -hr -ms

i've got

Evaluating detections
Custom metric? Yes
AP for killer = -1.0000
AP for robokit = -1.0000
Mean AP = -1.0000
Mean AP: -1.0
Saving state, epoch: 10

and file slim_yolo_v2_10.pth in v831_yolo\weights\custom\slim_yolo_v2
Next i'm trying

python test.py -d custom -v slim_yolo_v2 --trained_model weights/custom/slim_yolo_v2/slim_yolo_v2_10.pth --visual_threshold 0.3 -size 224 --export

and i've got file yolov2.onnx in v831_yolo\out
AND

Traceback (most recent call last):
File "test.py", line 238, in
onnx_to_ncnn(input_shape, onnx=onnx_out, ncnn_param=ncnn_out_param, ncnn_bin=ncnn_out_bin)
File "C:\Users\Robozoom\Documents\MAIX2-releases\v831_yolo\convert.py", line 23, in onnx_to_ncnn
with open(ncnn_param) as f:
FileNotFoundError: [Errno 2] No such file or directory: 'out/yolov2.param'

How i can generate *.param file?

Thanks!

[dianjixz]

You must be run it in linux system environment！

[GramJr]

You must be run it in linux system environment！

I run it at goolge colab, at linux computer, on windows.
This is error at google colab:

use cuda
test on custom ...
/usr/local/lib/python3.7/dist-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2894.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Finished loading model!

    Layer (type)               Output Shape         Param #

================================================================
Conv2d-1 [-1, 32, 224, 224] 896
BatchNorm2d-2 [-1, 32, 224, 224] 64
LeakyReLU-3 [-1, 32, 224, 224] 0
Conv_BN_LeakyReLU-4 [-1, 32, 224, 224] 0
Conv2d-5 [-1, 32, 112, 112] 9,248
BatchNorm2d-6 [-1, 32, 112, 112] 64
LeakyReLU-7 [-1, 32, 112, 112] 0
Conv_BN_LeakyReLU-8 [-1, 32, 112, 112] 0
Conv2d-9 [-1, 64, 112, 112] 18,496
BatchNorm2d-10 [-1, 64, 112, 112] 128
LeakyReLU-11 [-1, 64, 112, 112] 0
Conv_BN_LeakyReLU-12 [-1, 64, 112, 112] 0
Conv2d-13 [-1, 64, 56, 56] 36,928
BatchNorm2d-14 [-1, 64, 56, 56] 128
LeakyReLU-15 [-1, 64, 56, 56] 0
Conv_BN_LeakyReLU-16 [-1, 64, 56, 56] 0
Conv2d-17 [-1, 128, 56, 56] 73,856
BatchNorm2d-18 [-1, 128, 56, 56] 256
LeakyReLU-19 [-1, 128, 56, 56] 0
Conv_BN_LeakyReLU-20 [-1, 128, 56, 56] 0
Conv2d-21 [-1, 128, 28, 28] 147,584
BatchNorm2d-22 [-1, 128, 28, 28] 256
LeakyReLU-23 [-1, 128, 28, 28] 0
Conv_BN_LeakyReLU-24 [-1, 128, 28, 28] 0
Conv2d-25 [-1, 256, 28, 28] 295,168
BatchNorm2d-26 [-1, 256, 28, 28] 512
LeakyReLU-27 [-1, 256, 28, 28] 0
Conv_BN_LeakyReLU-28 [-1, 256, 28, 28] 0
Conv2d-29 [-1, 256, 14, 14] 590,080
BatchNorm2d-30 [-1, 256, 14, 14] 512
LeakyReLU-31 [-1, 256, 14, 14] 0
Conv_BN_LeakyReLU-32 [-1, 256, 14, 14] 0
Conv2d-33 [-1, 512, 14, 14] 1,180,160
BatchNorm2d-34 [-1, 512, 14, 14] 1,024
LeakyReLU-35 [-1, 512, 14, 14] 0
Conv_BN_LeakyReLU-36 [-1, 512, 14, 14] 0
Conv2d-37 [-1, 512, 7, 7] 2,359,808
BatchNorm2d-38 [-1, 512, 7, 7] 1,024
LeakyReLU-39 [-1, 512, 7, 7] 0
Conv_BN_LeakyReLU-40 [-1, 512, 7, 7] 0
DarkNet_Tiny-41 [[-1, 128, 28, 28], [-1, 256, 14, 14], [-1, 512, 7, 7]] 0
Conv2d-42 [-1, 512, 7, 7] 2,359,808
BatchNorm2d-43 [-1, 512, 7, 7] 1,024
LeakyReLU-44 [-1, 512, 7, 7] 0
Conv2d-45 [-1, 512, 7, 7] 0
Conv2d-46 [-1, 512, 7, 7] 2,359,808
BatchNorm2d-47 [-1, 512, 7, 7] 1,024
LeakyReLU-48 [-1, 512, 7, 7] 0
Conv2d-49 [-1, 512, 7, 7] 0
Conv2d-50 [-1, 512, 7, 7] 2,359,808
BatchNorm2d-51 [-1, 512, 7, 7] 1,024
LeakyReLU-52 [-1, 512, 7, 7] 0
Conv2d-53 [-1, 512, 7, 7] 0
Conv2d-54 [-1, 35, 7, 7] 17,955

Total params: 11,816,643
Trainable params: 11,816,643
Non-trainable params: 0

Input size (MB): 0.57
Forward/backward pass size (MB): 963780728.98
Params size (MB): 45.08
Estimated Total Size (MB): 963780774.63

input shape: torch.Size([1, 3, 224, 224])
export onnx ok
sh: 1: onnx2ncnn: not found
Traceback (most recent call last):
File "/content/ncnn/build/v831_yolo/test.py", line 238, in
onnx_to_ncnn(input_shape, onnx=onnx_out, ncnn_param=ncnn_out_param, ncnn_bin=ncnn_out_bin)
File "/content/ncnn/build/v831_yolo/convert.py", line 23, in onnx_to_ncnn
with open(ncnn_param) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/content/ncnn/build/v831_yolo/out/yolov2.param'