07-10, 10:56–10:59 (Europe/Amsterdam), Method (1.5)
I spent about one year leveraging Julia for DL research in Computer Vision, including using Flux.jl, FastAI.jl, Metalhead.jl, and loading python models through PyChainCall.jl. Happy to discuss my experience.
I spent about one year leveraging Julia for DL research in Computer Vision, including using Flux.jl, FastAI.jl, Metalhead.jl, and loading python models through PyChainCall.jl.
Happy to discuss my experience, including the good (flexibililty, hacking packages, fast custom kernels), the bad (missing models, difficulty to collaborate), and the ugly (gradient bugs, precompile time).
- PhD Student at the Stanford Intelligent Systems Lab (SISL), developing certification guidelines for employing data-driven algorithms in safety-critical applications.