在paddle上用yolov3训练自己数据集时出现的问题

基于paddle学习目标检测算法yolov3的基础上用yolov3训练自己的数据集时,发现paddle有报错:

2021-07-18 17:20:02[TRAIN]epoch 0, iter 8, output loss: [898.1042]

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/PIL/Image.py:2800: DecompressionBombWarning: Image size (168416415 pixels) exceeds limit of 89478485 pixels, could be decompression bomb DOS attack.
  DecompressionBombWarning,

2021-07-18 17:20:08[TRAIN]epoch 0, iter 9, output loss: [1166.028]
2021-07-18 17:20:10[TRAIN]epoch 0, iter 10, output loss: [326.97525]

---------------------------------------------------------------------------KeyboardInterrupt                         Traceback (most recent call last)<ipython-input-67-024cd613b6b1> in <module>
     39         MAX_EPOCH = 200
     40         for epoch in range(MAX_EPOCH):
---> 41             for i, data in enumerate(train_loader()):
     42                 img, gt_boxes, gt_labels, img_scale = data
     43                 gt_scores = np.ones(gt_labels.shape).astype('float32')
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/reader/decorator.py in xreader()
    446         finish = 1
    447         while finish < process_num:
--> 448             sample = out_queue.get()
    449             if isinstance(sample, XmapEndSignal):
    450                 finish += 1
/opt/conda/envs/python35-paddle120-env/lib/python3.7/queue.py in get(self, block, timeout)
    168             elif timeout is None:
    169                 while not self._qsize():
--> 170                     self.not_empty.wait()
    171             elif timeout < 0:
    172                 raise ValueError("'timeout' must be a non-negative number")
/opt/conda/envs/python35-paddle120-env/lib/python3.7/threading.py in wait(self, timeout)
    294         try:    # restore state no matter what (e.g., KeyboardInterrupt)
    295             if timeout is None:
--> 296                 waiter.acquire()
    297                 gotit = True
    298             else:
KeyboardInterrupt: 

坑有点大,继续改:

---------------------------------------------------------------------------EnforceNotMet                             Traceback (most recent call last)<ipython-input-162-c16e7c3f4792> in <module>
      2 import numpy as np
      3 with fluid.dygraph.guard():
----> 4     backbone = DarkNet53_conv_body(is_test=False)
      5     x = np.random.randn(1, 3, 640, 640).astype('float32')
      6     x = to_variable(x)
<ipython-input-161-76715bce0d06> in __init__(self, is_test)
    149             stride=1,
    150             padding=1,
--> 151             is_test=is_test)
    152 
    153         # 下采样,使用stride=2的卷积来实现
<ipython-input-161-76715bce0d06> in __init__(self, ch_in, ch_out, filter_size, stride, groups, padding, act, is_test)
     33                 initializer=fluid.initializer.Normal(0., 0.02)),
     34             bias_attr=False,
---> 35             act=None)
     36 
     37         self.batch_norm = BatchNorm(
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/nn.py in __init__(self, num_channels, num_filters, filter_size, stride, padding, dilation, groups, param_attr, bias_attr, use_cudnn, act, dtype)
    215             shape=filter_shape,
    216             dtype=self._dtype,
--> 217             default_initializer=_get_default_param_initializer())
    218 
    219         self.bias = self.create_parameter(
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py in create_parameter(self, shape, attr, dtype, is_bias, default_initializer)
    260             temp_attr = None
    261         return self._helper.create_parameter(temp_attr, shape, dtype, is_bias,
--> 262                                              default_initializer)
    263 
    264     # TODO: Add more parameter list when we need them
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layer_helper_base.py in create_parameter(self, attr, shape, dtype, is_bias, default_initializer, stop_gradient, type)
    345                 type=type,
    346                 stop_gradient=stop_gradient,
--> 347                 **attr._to_kwargs(with_initializer=True))
    348         else:
    349             self.startup_program.global_block().create_parameter(
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值