RuntimeError:[在CPUAllocator.cpp:65执行失败]。DefaultCPUAllocator:无法分配内存

Question

这是我正在尝试运行的python脚本：

import easyocr 
reader = easyocr.Reader(['en'])
result = reader.readtext('test.jpg')
print(result)

我在我的电脑上试过了，效果很好。 然而，当在覆盆子皮上尝试它时，它不会。 我使用的是虚拟环境

• numpy版本：1.20.2
• easyocr版本：1.3.0.1
• 火炬版本：1.7.0a0+e85d494
• Torchvision版本：0.8.0a0+45f960c
• Python版本：3.7.3

这是我通过终端运行时得到的结果：

CUDA not available - defaulting to CPU. Note: This module is much faster with a GPU.
Traceback (most recent call last):
  File "ocr.py", line 3, in <module>
    result = reader.readtext('test.jpg')
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/easyocr.py", line 379, in readtext
    add_margin, False)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/easyocr.py", line 273, in detect
    False, self.device, optimal_num_chars)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/detection.py", line 81, in get_textbox
    bboxes, polys = test_net(canvas_size, mag_ratio, detector, image, text_threshold, link_threshold, low_text, poly, device, estimate_num_chars)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/detection.py", line 38, in test_net
    y, feature = net(x)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/craft.py", line 60, in forward
    sources = self.basenet(x)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/easyocr/model/modules.py", line 61, in forward
    h = self.slice1(X)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/container.py", line 117, in forward
    input = module(input)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 423, in forward
    return self._conv_forward(input, self.weight)
  File "/home/pi/johara/ocri/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 420, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: [enforce fail at CPUAllocator.cpp:65] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 1519386624 bytes. Error code 12 (Cannot allocate memory)