Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU. Illegal instruction

[luisjose1996]

import easyocr
import cv2
import matplotlib.pyplot as plt

Create an EasyOCR reader instance

reader = easyocr.Reader(['en'], gpu=False) # Specify the languages you want to use

Function to extract text from an image

def extract_text_from_image(image_path):
# Read the image using OpenCV
image = cv2.imread(image_path)

# Use EasyOCR to extract text
results = reader.readtext(image)

# Extract text and bounding boxes
extracted_text = ""
for (bbox, text, prob) in results:
    extracted_text += f"{text} "
    # Optionally, you can draw bounding boxes on the image
    (top_left, top_right, bottom_right, bottom_left) = bbox
    top_left = tuple(map(int, top_left))
    bottom_right = tuple(map(int, bottom_right))
    cv2.rectangle(image, top_left, bottom_right, (0, 255, 0), 2)

return extracted_text.strip(), image

Example usage

if name == "main":
image_path = "1.png" # Replace with your image path
text, annotated_image = extract_text_from_image(image_path)
print("Extracted Text:", text)

# Display the image with bounding boxes
plt.imshow(cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB))
plt.axis('off')  # Hide axes
plt.show()

In this code, I got an issue like "Neither CUDA nor MPS are available - defaulting to CPU. Note: This module is much faster with a GPU. Illegal instruction".
How should I solve this issue?

[romanvelichkin]

It's not clear what is a problem. Easyocr doesn't scan image, so you don't have image + bbox output? Or image is showed, but you're bothered with a message?

It's a default message if you don't use gpu. You can change gpu=False -> gpu=True to fix it, but you will need GPU for that.

[hankchu6]

I also encountered the 'Illegal instruction' issue. The error message and my system information are as follows:

>>> reader = easyocr.Reader(['en'], gpu=False, model_storage_directory='models')
>>> img = 'initial_screen.png'
>>> reader.readtext(img)
[W1101 17:08:06.622021815 NNPACK.cpp:61] Could not initialize NNPACK! Reason: Unsupported hardware.
Illegal instruction (core dumped)

ov  1 17:08:06 ct05 kernel: traps: python[2197] trap invalid opcode ip:7ff9b9728a51 sp:7ffcfad76a80 error:0 in libtorch_cpu.so[7ff9b1600000+13dce000]
Nov  1 17:08:06 ct05 systemd[1]: Started Process Core Dump (PID 2211/UID 0).
Nov  1 17:08:13 ct05 systemd-coredump[2212]: Process 2197 (python) of user 0 dumped core.#012#012Module libz.e05c5b49.so.1 without build-id.#012Stack trace of thread 2197:#012#0  0x00007ff9b9728a51 _ZN6fbgemm10FindMinMaxEPKfPfS2_l (libtorch_cpu.so + 0x8128a51)#012#1  0x00007ff9b3a6261f _ZN25PackedLinearWeightsOnednn18apply_dynamic_implILb0EEEN2at6TensorES2_b (libtorch_cpu.so + 0x246261f)#012#2  0x00007ff9b3a599bd _ZN25PackedLinearWeightsOnednn13apply_dynamicEN2at6TensorEb (libtorch_cpu.so + 0x24599bd)#012#3  0x00007ff9b3556740 _ZNK2at6native12_GLOBAL__N_126QuantizedCellParamsDynamic9linear_ihERKNS_6TensorE (libtorch_cpu.so + 0x1f56740)#012#4  0x00007ff9b3569f7a _ZNK2at6native12_GLOBAL__N_122FullBidirectionalLayerISt5tupleIJNS_6TensorES4_EENS1_21QRNNCellParamsWrapperEEclERKS4_RKSt4pairIS5_S5_ERKSA_IS6_S6_E (libtorch_cpu.so + 0x1f69f7a)#012#5  0x00007ff9b356cb34 _ZN2at6nativeL20quantized_lstm_inputERKNS_6TensorEN3c104ListIS1_EENS5_INS4_13intrusive_ptrINS0_12_GLOBAL__N_114CellParamsBaseENS4_6detail34intrusive_target_default_null_typeIS9_EEEEEEbldbbbSt8optionalINS4_10ScalarTypeEEb.constprop.0 (libtorch_cpu.so + 0x1f6cb34)#012#6  0x00007ff9b356d8de _ZN3c104impl31make_boxed_from_unboxed_functorINS0_6detail24WrapFunctionIntoFunctor_INS_26CompileTimeFunctionPointerIFSt5tupleIJN2at6TensorES7_S7_EERKS7_NS_4ListIS7_EENSB_INS_13intrusive_ptrINS6_6native12_GLOBAL__N_114CellParamsBaseENS_6detail34intrusive_target_default_null_typeISG_EEEEEEbldbbbSt8optionalINS_10ScalarTypeEEbEXadL_ZNSE_L20quantized_lstm_inputESA_SC_SL_bldbbbSO_bEEEES8_NS_4guts8typelist8typelistIJSA_SC_SL_bldbbbSO_bEEEEELb0EE4callEPNS_14OperatorKernelERKNS_14OperatorHandleENS_14DispatchKeySetEPSt6vectorINS_6IValueESaIS14_EE (libtorch_cpu.so + 0x1f6d8de)#012#7  0x00007ff9b6c939ab _ZNK3c1014OperatorHandle15redispatchBoxedENS_14DispatchKeySetEPSt6vectorINS_6IValueESaIS3_EE (libtorch_cpu.so + 0x56939ab)#012#8  0x00007ff9b6c91229 _ZN5torch8autogradL39basicAutogradNotImplementedFallbackImplERKN3c1014OperatorHandleENS1_14DispatchKeySetEPSt6vectorINS1_6IValueESaIS7_EE (libtorch_cpu.so + 0x5691229)#012#9  0x00007ff9b316bd48 _ZN3c1011BoxedKernel19make_boxed_functionIXadL_ZN12_GLOBAL__N_117autograd_fallbackERKNS_14OperatorHandleENS_14DispatchKeySetEPSt6vectorINS_6IValueESaIS8_EEEEEEvPNS_14OperatorKernelES5_S6_SB_ (libtorch_cpu.so + 0x1b6bd48)#012#10 0x00007ff9c6cfdd88 _ZNK3c1010Dispatcher9callBoxedERKNS_14OperatorHandleEPSt6vectorINS_6IValueESaIS5_EE (libtorch_python.so + 0xcfdd88)#012#11 0x00007ff9c6a8c796 _ZN5torch3jit24invokeOperatorFromPythonERKSt6vectorISt10shared_ptrINS0_8OperatorEESaIS4_EERKN8pybind114argsERKNS9_6kwargsESt8optionalIN3c1011DispatchKeyEE (libtorch_python.so + 0xa8c796)#012#12 0x00007ff9c6a8caa7 _ZN5torch3jit37_get_operation_for_overload_or_packetERKSt6vectorISt10shared_ptrINS0_8OperatorEESaIS4_EEN3c106SymbolERKN8pybind114argsERKNSB_6kwargsEbSt8optionalINS9_11DispatchKeyEE (libtorch_python.so + 0xa8caa7)#012#13 0x00007ff9c6974fb2 _ZZN8pybind1112cpp_function10initializeIZZN5torch3jit15initJITBindingsEP7_objectENKUlRKSsE215_clES7_EUlRKNS_4argsERKNS_6kwargsEE_NS_6objectEJSB_SE_EJNS_4nameENS_3docEEEEvOT_PFT0_DpT1_EDpRKT2_ENUlRNS_6detail13function_callEE1_4_FUNESW_ (libtorch_python.so + 0x974fb2)#012#14 0x00007ff9c64cf48f _ZN8pybind1112cpp_function10dispatcherEP7_objectS2_S2_ (libtorch_python.so + 0x4cf48f)#012#15 0x00007ff9c8d51c32 cfunction_call (libpython3.9.so.1.0 + 0x151c32)#012#16 0x00007ff9c8d4ff8b PyObject_Call (libpython3.9.so.1.0 + 0x14ff8b)#012#17 0x00007ff9c8d362c7 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1362c7)#012#18 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#19 0x00007ff9c8d41055 _PyFunction_Vectorcall (libpython3.9.so.1.0 + 0x141055)#012#20 0x00007ff9c8d391c5 _PyObject_FastCallDictTstate (libpython3.9.so.1.0 + 0x1391c5)#012#21 0x00007ff9c8d4cce5 _PyObject_Call_Prepend (libpython3.9.so.1.0 + 0x14cce5)#012#22 0x00007ff9c8e1b242 slot_tp_call (libpython3.9.so.1.0 + 0x21b242)#012#23 0x00007ff9c8d39903 _PyObject_MakeTpCall (libpython3.9.so.1.0 + 0x139903)#012#24 0x00007ff9c8d35984 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x135984)#012#25 0x00007ff9c8d4134b function_code_fastcall (libpython3.9.so.1.0 + 0x14134b)#012#26 0x00007ff9c8d4f643 method_vectorcall (libpython3.9.so.1.0 + 0x14f643)#012#27 0x00007ff9c8d351eb _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1351eb)#012#28 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#29 0x00007ff9c8d4f6e5 method_vectorcall (libpython3.9.so.1.0 + 0x14f6e5)#012#30 0x00007ff9c8d351eb _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1351eb)#012#31 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#32 0x00007ff9c8d41055 _PyFunction_Vectorcall (libpython3.9.so.1.0 + 0x141055)#012#33 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#34 0x00007ff9c8d332a9 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1332a9)#012#35 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#36 0x00007ff9c8d41055 _PyFunction_Vectorcall (libpython3.9.so.1.0 + 0x141055)#012#37 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#38 0x00007ff9c8d332a9 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1332a9)#012#39 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#40 0x00007ff9c8d3915e _PyObject_FastCallDictTstate (libpython3.9.so.1.0 + 0x13915e)#012#41 0x00007ff9c8d4cc6c _PyObject_Call_Prepend (libpython3.9.so.1.0 + 0x14cc6c)#012#42 0x00007ff9c8e1b242 slot_tp_call (libpython3.9.so.1.0 + 0x21b242)#012#43 0x00007ff9c8d39903 _PyObject_MakeTpCall (libpython3.9.so.1.0 + 0x139903)#012#44 0x00007ff9c8d3580e _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x13580e)#012#45 0x00007ff9c8d4134b function_code_fastcall (libpython3.9.so.1.0 + 0x14134b)#012#46 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#47 0x00007ff9c8d332a9 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1332a9)#012#48 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#49 0x00007ff9c8d41055 _PyFunction_Vectorcall (libpython3.9.so.1.0 + 0x141055)#012#50 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#51 0x00007ff9c8d332a9 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1332a9)#012#52 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#53 0x00007ff9c8d3915e _PyObject_FastCallDictTstate (libpython3.9.so.1.0 + 0x13915e)#012#54 0x00007ff9c8d4cc6c _PyObject_Call_Prepend (libpython3.9.so.1.0 + 0x14cc6c)#012#55 0x00007ff9c8e1b242 slot_tp_call (libpython3.9.so.1.0 + 0x21b242)#012#56 0x00007ff9c8d39903 _PyObject_MakeTpCall (libpython3.9.so.1.0 + 0x139903)#012#57 0x00007ff9c8d3516c _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x13516c)#012#58 0x00007ff9c8d4134b function_code_fastcall (libpython3.9.so.1.0 + 0x14134b)#012#59 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#60 0x00007ff9c8d332a9 _PyEval_EvalFrameDefault (libpython3.9.so.1.0 + 0x1332a9)#012#61 0x00007ff9c8d2e9d9 _PyEval_EvalCode (libpython3.9.so.1.0 + 0x12e9d9)#012#62 0x00007ff9c8d41055 _PyFunction_Vectorcall (libpython3.9.so.1.0 + 0x141055)#012#63 0x00007ff9c8d4f7c5 method_vectorcall (libpython3.9.so.1.0 + 0x14f7c5)#012#012Stack trace of thread 2203:#012#0  0x00007ff9c888691a __futex_abstimed_wait_common (libc.so.6 + 0x8691a)#012#1  0x00007ff9c8889120 pthread_cond_wait@@GLIBC_2.3.2 (libc.so.6 + 0x89120)#012#2  0x00007ff98e35009b blas_thread_server (libopenblasp-r0-01191904.3.27.so + 0x35009b)#012#3  0x00007ff9c8889d82 start_thread (libc.so.6 + 0x89d82)#012#4  0x00007ff9c890ee20 __clone3 (libc.so.6 + 0x10ee20)#012#012Stack trace of thread 2204:#012#0  0x00007ff9c888691a __futex_abstimed_wait_common (libc.so.6 + 0x8691a)#012#1  0x00007ff9c8889120 pthread_cond_wait@@GLIBC_2.3.2 (libc.so.6 + 0x89120)#012#2  0x00007ff98e35009b blas_thread_server (libopenblasp-r0-01191904.3.27.so + 0x35009b)#012#3  0x00007ff9c8889d82 start_thread (libc.so.6 + 0x89d82)#012#4  0x00007ff9c890ee20 __clone3 (libc.so.6 + 0x10ee20)#012#012Stack trace of thread 2205:#012#0  0x00007ff9c7418b21 n/a (libgomp-a34b3233.so.1 + 0x18
Nov  1 17:08:13 ct05 systemd[1]: systemd-coredump@2-2211-0.service: Deactivated successfully.
Nov  1 17:08:13 ct05 systemd[1]: systemd-coredump@2-2211-0.service: Consumed 5.035s CPU time.

easyocr                  1.7.1

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 191
model name      : Intel(R) Core(TM) i5-14500
stepping        : 2
microcode       : 0xffffffff
cpu MHz         : 2611.200
cache size      : 24576 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 4
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 22
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 cx16 sse4_1 sse4_2 movbe popcnt aes rdrand hypervisor lahf_lm abm 3dnowprefetch ibrs_enhanced fsgsbase bmi1 bmi2 invpcid rdseed clflushopt arat md_clear flush_l1d arch_capabilities
bugs            : spectre_v1 spectre_v2 spec_store_bypass swapgs retbleed eibrs_pbrsb rfds bhi
bogomips        : 5222.40
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual

[kulikala]

Hi there! I’ve successfully configured this module to run on the CPU only. Below is a working Dockerfile setup:

FROM python:3.8-slim AS compile-image

# if you forked EasyOCR, you can pass in your own GitHub username to use your fork
# i.e. GH_USERNAME=myname
ARG GH_USERNAME="JaidedAI"
ARG GH_VERSION="v1.7.1"
ARG PIP_PILLOW="9.3.0"
ARG PIP_TORCH="1.12.1"
ARG PIP_TORCHVISION="0.13.1"
ARG MODEL_HOME="/root/.EasyOCR/model"
ARG SERVICE_HOME="/home/EasyOCR"
ARG LANG_MODELS="pre-v1.1.6/craft_mlt_25k,v1.3/english_g2"

# Configure apt and install packages
RUN apt-get update -y \
    && apt-get install -y \
        git \
        curl \
        unzip \
    # cleanup
    && apt-get autoremove -y \
    && apt-get clean -y \
    && rm -rf /var/lib/apt/lists

# Download models
RUN mkdir -p "${MODEL_HOME}" \
    && cd "${MODEL_HOME}" \
    && IFS=',' L_ARR="${LANG_MODELS}" \
    && for l in ${L_ARR}; do \
        curl -L -O "https://github.com/JaidedAI/EasyOCR/releases/download/${l}.zip" \
        ; done \
    && unzip '*.zip'

# Clone EasyOCR repo
RUN mkdir "${SERVICE_HOME}" \
    && git clone "https://github.com/${GH_USERNAME}/EasyOCR.git" "${SERVICE_HOME}" \
    && cd "${SERVICE_HOME}" \
    && git remote add upstream "https://github.com/JaidedAI/EasyOCR.git" \
    && git fetch upstream tag "${GH_VERSION}" \
    && git checkout tags/"${GH_VERSION}"

# Update pip
RUN cd "${SERVICE_HOME}" \
    && python -m pip install \
        --upgrade \
        pip

# Install torch/torchvision
RUN cd "${SERVICE_HOME}" \
    && python -m pip install \
        --index-url https://download.pytorch.org/whl/cpu \
        --use-deprecated=legacy-resolver \
        Pillow=="${PIP_PILLOW}" \
        torch=="${PIP_TORCH}" \
        torchvision=="${PIP_TORCHVISION}"

# Build
RUN cd "${SERVICE_HOME}" \
    && python setup.py build_ext --inplace -j $(nproc) \
    && python -m pip install -e .

########

FROM python:3.8-slim AS production-image

ARG MODEL_HOME="/root/.EasyOCR/model"
ARG SERVICE_HOME="/home/EasyOCR"
ARG PIP_LOCATION="/usr/local/lib/python3.8/site-packages"

# Copy models
COPY --from=compile-image "${MODEL_HOME}" "${MODEL_HOME}"

# Copy home
COPY --from=compile-image "${SERVICE_HOME}" "${SERVICE_HOME}"

# Copy site packages
COPY --from=compile-image "${PIP_LOCATION}" "${PIP_LOCATION}"

# Copy executables
COPY --from=compile-image /usr/local/bin /usr/local/bin

Please note that changing versions may lead to build or runtime failures.
Hope this is helpful!