Invalid dimensions size(8) for gpu tensor error while running on GPU

[kenilaivid]

I want to run a FP32 model on GPU. Here is my code which I am using for inference:

from openvino.runtime import Core, Model
import numpy as np
import time
core = Core()
ov_model = core.read_model("/home/aivid12/Desktop/kenil/Shoplifting/model.xml") 
input_layer_ir = ov_model.input(0)
compiled_model = core.compile_model(ov_model,"GPU")
output_layer = compiled_model.output(0)
import openvino.runtime as ov

train_y, train_y_cap = [], []
frame_count = 0
start_time = time.time()
for i in range(100):
    videos = np.random.rand(1,80,3,320,320)
    result = compiled_model(videos)[output_layer]
    y_cap = result[0][0]
    frame_count +=1 
    try:
        print("FPS: ",(frame_count/(int(time.time())-int(start_time))))
    except:
        pass

But I am getting this error

beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
Traceback (most recent call last):
  File "/home/aivid12/Desktop/kenil/Shoplifting/shoplifting.py", line 42, in <module>
    compiled_model = core.compile_model(ov_model,"GPU")
  File "/home/aivid12/anaconda3/lib/python3.9/site-packages/openvino/runtime/ie_api.py", line 399, in compile_model
    super().compile_model(model, device_name, {} if config is None else config),
RuntimeError: Invalid dimensions size(8) for gpu tensor

Whereas it is working. When I am running it on CPU.

Here is clinfo

beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)
Number of platforms                               2
  Platform Name                                   Intel(R) OpenCL HD Graphics
  Platform Vendor                                 Intel(R) Corporation
  Platform Version                                OpenCL 2.1 
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_depth_images cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_media_block_io cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_khr_fp64 cl_khr_subgroups cl_khr_il_program cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_unified_shared_memory_preview cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_intel_va_api_media_sharing 
  Platform Host timer resolution                  1ns
  Platform Extensions function suffix             INTEL

  Platform Name                                   Intel Gen OCL Driver
  Platform Vendor                                 Intel
  Platform Version                                OpenCL 2.0 beignet 1.3
  Platform Profile                                FULL_PROFILE
  Platform Extensions                             cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_3d_image_writes cl_khr_image2d_from_buffer cl_khr_depth_images cl_khr_spir cl_khr_icd cl_intel_accelerator cl_intel_subgroups cl_intel_subgroups_short cl_khr_gl_sharing
  Platform Extensions function suffix             Intel
beignet-opencl-icd: no supported GPU found, this is probably the wrong opencl-icd package for this hardware
(If you have multiple ICDs installed and OpenCL works, you can ignore this message)

  Platform Name                                   Intel(R) OpenCL HD Graphics
Number of devices                                 1
  Device Name                                     Intel(R) Gen9 HD Graphics NEO
  Device Vendor                                   Intel(R) Corporation
  Device Vendor ID                                0x8086
  Device Version                                  OpenCL 2.1 NEO 
  Driver Version                                  19.51.15145
  Device OpenCL C Version                         OpenCL C 2.0 
  Device Type                                     GPU
  Device Profile                                  FULL_PROFILE
  Device Available                                Yes
  Compiler Available                              Yes
  Linker Available                                Yes
  Max compute units                               23
  Max clock frequency                             1100MHz
  Device Partition                                (core)
    Max number of sub-devices                     0
    Supported partition types                     None
  Max work item dimensions                        3
  Max work item sizes                             256x256x256
  Max work group size                             256
  Preferred work group size multiple              <getWGsizes:675: build program : error -6>
  Max sub-groups per work group                   32
  Sub-group sizes (Intel)                         8, 16, 32
  Preferred / native vector sizes                 
    char                                                16 / 16      
    short                                                8 / 8       
    int                                                  4 / 4       
    long                                                 1 / 1       
    half                                                 8 / 8        (cl_khr_fp16)
    float                                                1 / 1       
    double                                               1 / 1        (cl_khr_fp64)
  Half-precision Floating-point support           (cl_khr_fp16)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Single-precision Floating-point support         (core)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
    Correctly-rounded divide and sqrt operations  Yes
  Double-precision Floating-point support         (cl_khr_fp64)
    Denormals                                     Yes
    Infinity and NANs                             Yes
    Round to nearest                              Yes
    Round to zero                                 Yes
    Round to infinity                             Yes
    IEEE754-2008 fused multiply-add               Yes
    Support is emulated in software               No
  Address bits                                    64, Little-Endian
  Global memory size                              26818772992 (24.98GiB)
  Error Correction support                        No
  Max memory allocation                           4294959104 (4GiB)
  Unified memory for Host and Device              Yes
  Shared Virtual Memory (SVM) capabilities        (core)
    Coarse-grained buffer sharing                 Yes
    Fine-grained buffer sharing                   No
    Fine-grained system sharing                   No
    Atomics                                       No
  Minimum alignment for any data type             128 bytes
  Alignment of base address                       1024 bits (128 bytes)
  Preferred alignment for atomics                 
    SVM                                           64 bytes
    Global                                        64 bytes
    Local                                         64 bytes
  Max size for global variable                    65536 (64KiB)
  Preferred total size of global vars             4294959104 (4GiB)
  Global Memory cache type                        Read/Write
  Global Memory cache size                        524288 (512KiB)
  Global Memory cache line size                   64 bytes
  Image support                                   Yes
    Max number of samplers per kernel             16
    Max size for 1D images from buffer            268434944 pixels
    Max 1D or 2D image array size                 2048 images
    Base address alignment for 2D image buffers   4 bytes
    Pitch alignment for 2D image buffers          4 pixels
    Max 2D image size                             16384x16384 pixels
    Max planar YUV image size                     16384x16352 pixels
    Max 3D image size                             16384x16384x2048 pixels
    Max number of read image args                 128
    Max number of write image args                128
    Max number of read/write image args           128
  Max number of pipe args                         16
  Max active pipe reservations                    1
  Max pipe packet size                            1024
  Local memory type                               Local
  Local memory size                               65536 (64KiB)
  Max number of constant args                     8
  Max constant buffer size                        4294959104 (4GiB)
  Max size of kernel argument                     1024
  Queue properties (on host)                      
    Out-of-order execution                        Yes
    Profiling                                     Yes
  Queue properties (on device)                    
    Out-of-order execution                        Yes
    Profiling                                     Yes
    Preferred size                                131072 (128KiB)
    Max size                                      67108864 (64MiB)
  Max queues on device                            1
  Max events on device                            1024
  Prefer user sync for interop                    Yes
  Profiling timer resolution                      83ns
  Execution capabilities                          
    Run OpenCL kernels                            Yes
    Run native kernels                            No
    Sub-group independent forward progress        Yes
    IL version                                    SPIR-V_1.2 
    SPIR versions                                 1.2 
  printf() buffer size                            4194304 (4MiB)
  Built-in kernels                                block_motion_estimate_intel;block_advanced_motion_estimate_check_intel;block_advanced_motion_estimate_bidirectional_check_intel;
  Motion Estimation accelerator version (Intel)   2
    Device-side AVC Motion Estimation version     1
      Supports texture sampler use                Yes
      Supports preemption                         No
  Device Extensions                               cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_fp16 cl_khr_depth_images cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_intel_subgroups cl_intel_required_subgroup_size cl_intel_subgroups_short cl_khr_spir cl_intel_accelerator cl_intel_media_block_io cl_intel_driver_diagnostics cl_khr_priority_hints cl_khr_throttle_hints cl_khr_create_command_queue cl_khr_fp64 cl_khr_subgroups cl_khr_il_program cl_intel_spirv_device_side_avc_motion_estimation cl_intel_spirv_media_block_io cl_intel_spirv_subgroups cl_khr_spirv_no_integer_wrap_decoration cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_intel_unified_shared_memory_preview cl_intel_planar_yuv cl_intel_packed_yuv cl_intel_motion_estimation cl_intel_device_side_avc_motion_estimation cl_intel_advanced_motion_estimation cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_intel_va_api_media_sharing 

  Platform Name                                   Intel Gen OCL Driver
Number of devices                                 0

NULL platform behavior
  clGetPlatformInfo(NULL, CL_PLATFORM_NAME, ...)  Intel(R) OpenCL HD Graphics
  clGetDeviceIDs(NULL, CL_DEVICE_TYPE_ALL, ...)   Success [INTEL]
  clCreateContext(NULL, ...) [default]            Success [INTEL]
  clCreateContext(NULL, ...) [other]              <error: no devices in non-default plaforms>
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_DEFAULT)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen9 HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CPU)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen9 HD Graphics NEO
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ACCELERATOR)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_CUSTOM)  No devices found in platform
  clCreateContextFromType(NULL, CL_DEVICE_TYPE_ALL)  Success (1)
    Platform Name                                 Intel(R) OpenCL HD Graphics
    Device Name                                   Intel(R) Gen9 HD Graphics NEO

ICD loader properties
  ICD loader Name                                 OpenCL ICD Loader
  ICD loader Vendor                               OCL Icd free software
  ICD loader Version                              2.2.11
  ICD loader Profile                              OpenCL 2.1

[sshlyapn]

Hi @kenilaivid, could you please share more details: which OpenVINO version you use, share the model if possible?

[kenilaivid]

Hi @sshlyapn, I am using openvino 2022.3.0.

[sshlyapn]

Thanks @kenilaivid As of now, GPU plugin supports tensor's rank size equal to 6 or less and that could be the reason. Could you please check your model's IR if it has some layers with rank > 6? Otherwise it may be some bug in GPU Plugin and we need to investigate it.

[kenilaivid]

@sshlyapn How can I check the rank of layer in models IR file?

[sshlyapn]

@kenilaivid, you can open your model (/home/aivid12/Desktop/kenil/Shoplifting/model.xml) in any text editor and check if there are any layers with more than 6 dimensions in inputs or outputs shape description. For example, this shape is of rank 3:

<port id="3" precision="FP32" names="223">
    <dim>1</dim>
    <dim>128</dim>
    <dim>768</dim>
</port>

[kenilaivid]

@sshlyapn yes I do have layers with more than 6 dimensions in output shape description. So what can be the solution to this?

<port id="2" precision="FP32" names="Reshape_output_0">
    <dim>1</dim>
    <dim>5</dim>
    <dim>16</dim>
    <dim>3</dim>
    <dim>16</dim>
    <dim>20</dim>
    <dim>16</dim>
    <dim>20</dim>
</port>

[sshlyapn]

@kenilaivid unfortunately, there is no simple solution. We have plans to extend the range of supported ranks in the further releases to align the behavior with CPU Plugin. As work around you can try to use hetero plugin if it is okay for you (HETERO:GPU,CPU), which will try to sort out unsupported operations for GPU and execute them on CPU. But even with such solution you may face the similar problems. And then the single option will be to wait for the wider range of ranks support from GPU Plugin.

[vladimir-paramuzov]

@kenilaivid Could you try to run with latest master? We've added support of 7d and 8d tensors for several primitives (eltwise, transpose, reshape, reduce) here: https://github.com/openvinotoolkit/openvino/pull/16810 Please let us know if that fixes your model or some issues still exist.

[avitial]

Ref. 101932

Closing this as referenced PR has been merged to master branch. I hope previous responses were sufficient to help you proceed, feel free to reopen and ask additional questions related to this topic.