maziyi234

yolox使用L1NormPrune后，模型大小仅仅从3797K降低到3784K

9

img_size = 416 device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model = YoloBody(num_classes, phi) model.load_state_dict(torch.load(weights, map_location=device)) #summary(model, (3, 64, 64), device="cpu") print('\nThe accuracy with masks:') model_train = model.train() yolo_loss =...

量化导入自己pth模型时候出现 KeyError: 'state_dict'

1

(pytorch1) maziyi@kpyf:~/python/yolox5/micronet/micronet/compression/quantization/wqaq/iao$ python main.py --resume "/home/maziyi/python/yolox5/yolox_best.pth" --q_type 0 --q_level 0 --bn_fuse --qaft --lr 0.00001 ==> Options: Namespace(a_bits=8, batch_size=32, bn_fuse=True, bn_fuse_calib=False, cpu=False, data='../../../../data', end_epochs=300, eval_batch_size=32, gpu_id='', lr='0.00001', model_type=1, num_workers=2, percentile=0.999999, pretrained_model=False,...

自己训练的水果分类数据集里，出现了Keyerror

7

File "/home/maziyi/python/yolox4/YOLOX/yolox/evaluators/voc_eval.py", line 139, in voc_eval R = class_recs[image_ids[d]] │ │ └ 0 │ └ ['apple_86', 'apple_86', 'apple_86', 'apple_13', 'apple_13', 'apple_95', 'apple_95', 'orange_67', 'apple_35', 'apple_95', 'ap... └ {'orange_30': {'bbox': array([],...

请问支持maix dock嘛

1

你好 ，这个代码支持maix dock嘛，如过不支持，请问 需要如何修改呢，思路是什么呢

ninja: build stopped: subcommand failed.

1

Build command failed. Error while executing process D:\android with arguments {skd\cmake\3.10.2.4988404\bin\ninja.exe -C F:\ncnn-android-yolox-main\ncnn-android-yolox-main\app\.cxx\cmake\debug\arm64-v8a ncnnyolox} ninja: Entering directory `F:\ncnn-android-yolox-main\ncnn-android-yolox-main\app\.cxx\cmake\debug\arm64-v8a' [1/1] Linking CXX shared library F:\ncnn-android-yolox-main\ncnn-android-yolox-main\app\build\intermediates\cmake\debug\obj\arm64-v8a\libncnnyolox.so FAILED: F:/ncnn-android-yolox-main/ncnn-android-yolox-main/app/build/intermediates/cmake/debug/obj/arm64-v8a/libncnnyolox.so cmd.exe /C "cd ....

请问data.txt的代码你们有嘛，网上找了半天没找到