CachCheng

When I train yolov7 instance model on my own datasets , exist error: AMP: checks failed X, disabling Automatic Mixed Precision. ??? but I need AMP

// stride 16 { ncnn::Mat out; ex.extract("288", out); ncnn::Mat anchors(6); anchors[0] = 36.f; anchors[1] = 75.f; anchors[2] = 76.f; anchors[3] = 55.f; anchors[4] = 72.f; anchors[5] = 146.f; std::vector objects16;...

7767517 147 187 Input images 0 1 images MemoryData 285 0 1 285 MemoryData 289 0 1 289 MemoryData 325 0 1 325 MemoryData 329 0 1 329 MemoryData 365...

ex.extract("288", out); ex.extract("302", out); 从上面我的参数文件里面的网络结构，我怎么确认“288”、“302”，这两个层应该是多少呢？

I compiled the file in "(https://github.com/Tencent/ncnn/tree/master/examples/yolov7.cpp", and run ./yolov7 get error: find_blob_index_by_name 288 failed find_blob_index_by_name 302 failed

> I appear to be having the same issue. Have you or anyone else discovered a fix for this? What's your problem？I haven't now

[2024-06-27 16:04:18 internimage_b_1k_224](main.py 354): INFO Max accuracy: 99.56% [2024-06-27 16:04:19 internimage_b_1k_224](main.py 561): INFO Test: [0/25] Time 0.757 (0.757) Loss 8.1779 (8.1779) Acc@1 0.000 (0.000) Acc@5 0.000 (0.000) Mem 20310MB [2024-06-27...

(llm) ahs@ahs-SYS-4029GP-TRTC-ZY001:/meta/cash/llm/InternImage/classification$ python export.py --model_name internimage_b_1k_224 --ckpt_dir output/internimage_b_1k_224 --trt => merge config from ./configs/internimage_b_1k_224.yaml using core type: DCNv3 using activation layer: GELU using main norm layer: LN using dpr: linear,...