训练问题2：

[liuwei3612]

2021-07-30 16:27:00 | INFO | yolox.core.trainer:132 - Model Summary: Params: 5.04M, Gflops: 6.41 2021-07-30 16:27:03 | INFO | apex.amp.frontend:328 - Selected optimization level O1: Insert automatic casts around Pytorch functions and Tensor methods. 2021-07-30 16:27:03 | INFO | apex.amp.frontend:329 - Defaults for this optimization level are: 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - enabled : True 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - opt_level : O1 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - cast_model_type : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - patch_torch_functions : True 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - keep_batchnorm_fp32 : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - master_weights : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:331 - loss_scale : dynamic 2021-07-30 16:27:03 | INFO | apex.amp.frontend:336 - Processing user overrides (additional kwargs that are not None)... 2021-07-30 16:27:03 | INFO | apex.amp.frontend:354 - After processing overrides, optimization options are: 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - enabled : True 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - opt_level : O1 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - cast_model_type : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - patch_torch_functions : True 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - keep_batchnorm_fp32 : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - master_weights : None 2021-07-30 16:27:03 | INFO | apex.amp.frontend:356 - loss_scale : dynamic 2021-07-30 16:27:03 | INFO | apex.amp.scaler:69 - Warning: multi_tensor_applier fused unscale kernel is unavailable, possibly because apex was installed without --cuda_ext --cpp_ext. Using Python fallback. Original ImportError was: ModuleNotFoundError("No module named 'amp_C'") 2021-07-30 16:27:03 | INFO | yolox.core.trainer:296 - loading checkpoint for fine tuning 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.0.weight in checkpoint is torch.Size([80, 96, 1, 1]), while shape of head.cls_preds.0.weight in model is torch.Size([15, 96, 1, 1]). 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.0.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.0.bias in model is torch.Size([15]). 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.1.weight in checkpoint is torch.Size([80, 96, 1, 1]), while shape of head.cls_preds.1.weight in model is torch.Size([15, 96, 1, 1]). 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.1.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.1.bias in model is torch.Size([15]). 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.2.weight in checkpoint is torch.Size([80, 96, 1, 1]), while shape of head.cls_preds.2.weight in model is torch.Size([15, 96, 1, 1]). 2021-07-30 16:27:03 | WARNING | yolox.utils.checkpoint:27 - Shape of head.cls_preds.2.bias in checkpoint is torch.Size([80]), while shape of head.cls_preds.2.bias in model is torch.Size([15]). 2021-07-30 16:27:03 | INFO | yolox.core.trainer:152 - init prefetcher, this might take one minute or less... 2021-07-30 16:27:15 | ERROR | yolox.core.launch:90 - An error has been caught in function 'launch', process 'MainProcess' (27263), thread 'MainThread' (140593167947520): Traceback (most recent call last):

File "tools/train.py", line 125, in args=(exp, args), │ └ Namespace(batch_size=64, ckpt='pth/yolox_tiny.pth.tar', devices=1, dist_backend='nccl', dist_url=None, exp_file='exps/yolox_t... └ ╒══════════════════╤═════════════════════════════════════════════════════════════════════════════════════════════════════════...

File "/home/lw/work/YOLOX/yolox/core/launch.py", line 90, in launch main_func(*args) │ └ (╒══════════════════╤════════════════════════════════════════════════════════════════════════════════════════════════════════... └ <function main at 0x7fde649d2a70>

File "tools/train.py", line 104, in main trainer.train() │ └ <function Trainer.train at 0x7fdddb054a70> └ <yolox.core.trainer.Trainer object at 0x7fddd87c7f50>

File "/home/lw/work/YOLOX/yolox/core/trainer.py", line 69, in train self.before_train() │ └ <function Trainer.before_train at 0x7fddd8832560> └ <yolox.core.trainer.Trainer object at 0x7fddd87c7f50>

File "/home/lw/work/YOLOX/yolox/core/trainer.py", line 176, in before_train batch_size=self.args.batch_size, is_distributed=self.is_distributed │ │ │ │ └ False │ │ │ └ <yolox.core.trainer.Trainer object at 0x7fddd87c7f50> │ │ └ 64 │ └ Namespace(batch_size=64, ckpt='pth/yolox_tiny.pth.tar', devices=1, dist_backend='nccl', dist_url=None, exp_file='exps/yolox_t... └ <yolox.core.trainer.Trainer object at 0x7fddd87c7f50>

File "exps/yolox_tiny/yolox_tiny.py", line 117, in get_evaluator val_loader = self.get_eval_loader(batch_size, is_distributed, testdev=testdev) │ │ │ │ └ False │ │ │ └ False │ │ └ 64 │ └ <function Exp.get_eval_loader at 0x7fddd87c5cb0> └ ╒══════════════════╤═════════════════════════════════════════════════════════════════════════════════════════════════════════...

File "exps/yolox_tiny/yolox_tiny.py", line 102, in get_eval_loader sampler = torch.utils.data.SequentialSampler(valdataset) └ <yolox.data.datasets.voc.VOCDetection object at 0x7fddb5fe0c50>

NameError: name 'torch' is not defined

[liuwei3612]

明明安装好了torch，怎么还报这个错误

[GOATmessi8]

import torch in your exp file: "exps/yolox_tiny/yolox_tiny.py"

[liuwei3612]

import torch in your exp file: "exps/yolox_tiny/yolox_tiny.py"

!/usr/bin/env python3

-- coding:utf-8 --

Copyright (c) Megvii, Inc. and its affiliates.

import os

from yolox.exp import Exp as MyExp from yolox.data import get_yolox_datadir

class Exp(MyExp): def init(self): super(Exp, self).init() self.depth = 0.33 self.width = 0.375 self.scale = (0.5, 1.5) self.random_size = (10, 20) self.test_size = (416, 416) self.num_classes = 15 self.exp_name = os.path.split(os.path.realpath(file))[1].split(".")[0] self.enable_mixup = False

def get_data_loader(self, batch_size, is_distributed, no_aug=False):
    from yolox.data import (
        VOCDetection,
        TrainTransform,
        YoloBatchSampler,
        DataLoader,
        InfiniteSampler,
        MosaicDetection,
    )

    dataset = VOCDetection(
        data_dir=os.path.join(get_yolox_datadir(), "VOCdevkit"),
        image_sets=[('TIAN', 'trainval')],
        img_size=self.input_size,
        preproc=TrainTransform(
            rgb_means=(0.485, 0.456, 0.406),
            std=(0.229, 0.224, 0.225),
            max_labels=50,
        ),
    )

    dataset = MosaicDetection(
        dataset,
        mosaic=not no_aug,
        img_size=self.input_size,
        preproc=TrainTransform(
            rgb_means=(0.485, 0.456, 0.406),
            std=(0.229, 0.224, 0.225),
            max_labels=120,
        ),
        degrees=self.degrees,
        translate=self.translate,
        scale=self.scale,
        shear=self.shear,
        perspective=self.perspective,
        enable_mixup=self.enable_mixup,
    )

    self.dataset = dataset

    if is_distributed:
        batch_size = batch_size // dist.get_world_size()

    sampler = InfiniteSampler(
        len(self.dataset), seed=self.seed if self.seed else 0
    )

    batch_sampler = YoloBatchSampler(
        sampler=sampler,
        batch_size=batch_size,
        drop_last=False,
        input_dimension=self.input_size,
        mosaic=not no_aug,
    )

    dataloader_kwargs = {"num_workers": self.data_num_workers, "pin_memory": True}
    dataloader_kwargs["batch_sampler"] = batch_sampler
    train_loader = DataLoader(self.dataset, **dataloader_kwargs)

    return train_loader

def get_eval_loader(self, batch_size, is_distributed, testdev=False):
    from yolox.data import VOCDetection, ValTransform

    valdataset = VOCDetection(
        data_dir=os.path.join(get_yolox_datadir(), "VOCdevkit"),
        image_sets=[('TIAN', 'test')],
        img_size=self.test_size,
        preproc=ValTransform(
            rgb_means=(0.485, 0.456, 0.406),
            std=(0.229, 0.224, 0.225),
        ),
    )

    if is_distributed:
        batch_size = batch_size // dist.get_world_size()
        sampler = torch.utils.data.distributed.DistributedSampler(
            valdataset, shuffle=False
        )
    else:
        sampler = torch.utils.data.SequentialSampler(valdataset)

    dataloader_kwargs = {
        "num_workers": self.data_num_workers,
        "pin_memory": True,
        "sampler": sampler,
    }
    dataloader_kwargs["batch_size"] = batch_size
    val_loader = torch.utils.data.DataLoader(valdataset, **dataloader_kwargs)

    return val_loader

def get_evaluator(self, batch_size, is_distributed, testdev=False):
    from yolox.evaluators import VOCEvaluator

    val_loader = self.get_eval_loader(batch_size, is_distributed, testdev=testdev)
    evaluator = VOCEvaluator(
        dataloader=val_loader,
        img_size=self.test_size,
        confthre=self.test_conf,
        nmsthre=self.nmsthre,
        num_classes=self.num_classes,
    )
    return evaluator