search

ARM-software / ComputeLibrary

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
MIT License
2.81k stars 774 forks source link

File not found conv1_weights.npy in Example graph_resnet50.cpp in computeLibrary #1104

Closed RavikumarLav closed 3 months ago

RavikumarLav commented 5 months ago

Output of 'strings libarm_compute.so | grep arm_compute_version': ->V24.02.1 Platform: ->Neon Operating System: ->Linux

File not found conv1_weights.npy in Example graph_resnet50.cpp in computeLibrary. Hello I am trying test graph_resnet50.cpp on arm a78 core but getting failed at convolution layer file conv1_weights.npy not found << ConvolutionLayer( 7U, 7U, 64U, get_weights_accessor(data_path, "**/cnn_data/resnet50_model/conv1_weights.npy**", weights_layout), std::unique_ptr(nullptr), PadStrideInfo(2, 2, 3, 3)) .set_name("conv1/convolution") << BatchNormalizationLayer( get_weights_accessor(data_path, "**/cnn_data/resnet50_model/conv1_BatchNorm_moving_mean.npy**"), get_weights_accessor(data_path, "/cnn_data/resnet50_model/conv1_BatchNorm_moving_variance.npy"), get_weights_accessor(data_path, "/cnn_data/resnet50_model/conv1_BatchNorm_gamma.npy"), get_weights_accessor(data_path, "/cnn_data/resnet50_model/conv1_BatchNorm_beta.npy"), 0.0000100099996416f) .set_name("conv1/BatchNorm") I am not able find these files in repo please let us know Where we can get these weights in the git repo to test above example. **Problem description:**
morgolock commented 3 months ago

Hi @RavikumarLav

The best way to run models is be to use ArmNN's ExecuteNetwork. You can download the resnet50 tflite model and run it with ArmNN.

For more information about this please have a look at https://github.com/ARM-software/ComputeLibrary/issues/1077#issuecomment-1792265699

Hope this helps