You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The attached model was generated in Keras/TF and exported via a Python module by a colleague. As noted in another posted issue, I cannot get ] test ONNX to run, but executing ONNX.load_model("ONNX_model.onnx" does generate weights.bson before dumping the following stack trace. Here ONNX_model.onnx is the name of the uploaded model file (hopefully that will be preserved in uploading). I'll also post my ] status output in case that helps.
`julia> ONNX.load_model("ONNX_Model.onnx")
ERROR: KeyError: key "conv2d/kernel:0" not found
Stacktrace:
[1] getindex at ./dict.jl:477 [inlined]
[2] (::ONNX.var"#120#122"{Dict{String,IVertex}})(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:57
[3] iterate at ./generator.jl:47 [inlined]
[4] collect_to!(::Array{IVertex,1}, ::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}, ::Int64, ::Int64) at ./array.jl:710
[5] collect_to_with_first! at ./array.jl:689 [inlined]
[6] _collect(::Array{AbstractString,1},
::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}, ::Base.EltypeUnknown, ::Base.HasShape{1}) at ./array.jl:683
[7] collect_similar(::Array{AbstractString,1}, ::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}) at ./array.jl:607
[8] map(::Function, ::Array{AbstractString,1}) at ./abstractarray.jl:2072
[9] _graph(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:57
[10] graph(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:92
[11] code(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:100
[12] write_julia_file(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/convert.jl:235
[13] load_model(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/convert.jl:250
The attached model was generated in Keras/TF and exported via a Python module by a colleague. As noted in another posted issue, I cannot get
] test ONNX
to run, but executingONNX.load_model("ONNX_model.onnx"
does generate weights.bson before dumping the following stack trace. HereONNX_model.onnx
is the name of the uploaded model file (hopefully that will be preserved in uploading). I'll also post my] status
output in case that helps.`julia> ONNX.load_model("ONNX_Model.onnx")
ERROR: KeyError: key "conv2d/kernel:0" not found
Stacktrace:
[1] getindex at ./dict.jl:477 [inlined]
[2] (::ONNX.var"#120#122"{Dict{String,IVertex}})(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:57
[3] iterate at ./generator.jl:47 [inlined]
[4] collect_to!(::Array{IVertex,1}, ::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}, ::Int64, ::Int64) at ./array.jl:710
[5] collect_to_with_first! at ./array.jl:689 [inlined]
[6] _collect(::Array{AbstractString,1},
::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}, ::Base.EltypeUnknown, ::Base.HasShape{1}) at ./array.jl:683
[7] collect_similar(::Array{AbstractString,1}, ::Base.Generator{Array{AbstractString,1},ONNX.var"#120#122"{Dict{String,IVertex}}}) at ./array.jl:607
[8] map(::Function, ::Array{AbstractString,1}) at ./abstractarray.jl:2072
[9] _graph(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:57
[10] graph(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:92
[11] code(::ONNX.Types.Graph) at /Users/rick/.julia/packages/ONNX/iz0dL/src/graph/graph.jl:100
[12] write_julia_file(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/convert.jl:235
[13] load_model(::String) at /Users/rick/.julia/packages/ONNX/iz0dL/src/convert.jl:250
[14] top-level scope at REPL[30]:1`
(@v1.4) pkg> status Status
~/.julia/environments/v1.4/Project.toml`[621f4979] AbstractFFTs v0.5.0
[537997a7] AbstractPlotting v0.10.6
[7d9fca2a] Arpack v0.4.0
[c52e3926] Atom v0.12.10
[fbb218c0] BSON v0.2.6
[6e4b80f9] BenchmarkTools v0.5.0
[3a3ce9e8] BitConverter v0.1.1
[ad839575] Blink v0.12.3
[5d785b6c] CImGui v1.75.0
[336ed68f] CSV v0.6.2
[aaaa29a8] Clustering v0.14.0
[35d6a980] ColorSchemes v3.9.0
[5ae59095] Colors v0.11.2
[717857b8] DSP v0.6.7
[a93c6f00] DataFrames v0.21.0
[1313f7d8] DataFramesMeta v0.5.1
[aae7a2af] DiffEqFlux v1.10.0
[b4f34e82] Distances v0.8.2
[31c24e10] Distributions v0.22.6
[7a1cc6ca] FFTW v1.2.1
[5789e2e9] FileIO v1.3.0
[587475ba] Flux v0.10.4
[f6369f11] ForwardDiff v0.10.10
[5752ebe1] GMT v0.18.0
[4d00f742] GeometryTypes v0.8.3
[f67ccb44] HDF5 v0.12.3
[7073ff75] IJulia v1.21.2
[6a3955dd] ImageFiltering v0.6.11
[82e4d734] ImageIO v0.1.1
[02fcd773] ImageTransformations v0.8.4
[86fae568] ImageView v0.10.8
[916415d5] Images v0.22.2
[c601a237] Interact v0.10.3
[c8e1da08] IterTools v1.3.0
[e5e0dc1b] Juno v0.8.1
[2fda8390] LsqFit v0.10.0
[ee78f7c6] Makie v0.10.0
[dbeba491] Metalhead v0.5.0
[51fcb6bd] NamedColors v0.2.0
[d0dd6a25] ONNX v0.1.1
[91a5bcdd] Plots v1.0.14
[08abe8d2] PrettyTables v0.9.0
[dca85d43] QuartzImageIO v0.7.1
[295af30f] Revise v2.6.6
[b372bb87] SeisIO v1.0.0
[2913bbd2] StatsBase v0.32.2
[f3b207a7] StatsPlots v0.14.6
[112f6efa] VegaLite v2.1.3
[fdbf4ff8] XLSX v0.6.2
[e88e6eb3] Zygote v0.4.20
[8dfed614] Test
ONNX_Model.onnx.gz
`
The text was updated successfully, but these errors were encountered: