demo.git/cnn_v3/training/dataset, branch main Vide-coded 64k demo system https://git.taar-o.com/demo.git/atom?h=main 2026-03-29T14:39:53Z update assets and weights 2026-03-29T14:39:53Z skal pascal.massimino@gmail.com 2026-03-29T14:38:10Z urn:sha1:45f8436a5c2410e2f15a0006f6a4540de0d913a5 more 3d assets for cnn_v3 2026-03-29T14:07:09Z skal pascal.massimino@gmail.com 2026-03-29T14:07:09Z urn:sha1:febd68030e8ef1a51411a0ab8593343a954e152b new script 2026-03-29T13:18:54Z skal pascal.massimino@gmail.com 2026-03-29T13:18:54Z urn:sha1:c82ddfa3fda67e50ee73a578500b56282c377476 add more samples + tool html 2026-03-24T22:14:57Z skal pascal.massimino@gmail.com 2026-03-24T22:14:13Z urn:sha1:0d561bed8772c28da8f49cd0b16f503c93b0f77d add full dataset 2026-03-22T16:59:45Z skal pascal.massimino@gmail.com 2026-03-22T16:59:45Z urn:sha1:01df602ea6580edc418b70f121e521a8217f954c fix size 2026-03-22T11:21:45Z skal pascal.massimino@gmail.com 2026-03-22T11:21:45Z urn:sha1:ae4542f9838533efc40d8715afca085123aa0145 https://colorifyai.art/photo-to-sketch/#playground with 'Ink Sketch' does a small zooming and resize normalize sample dimension 2026-03-22T11:02:06Z skal pascal.massimino@gmail.com 2026-03-22T11:02:06Z urn:sha1:24397204670dff183df2c4b56fa3fcdf87411f08 feat(cnn_v3): gen_sample tool + 7 simple training samples 2026-03-22T06:51:28Z skal pascal.massimino@gmail.com 2026-03-22T06:33:28Z urn:sha1:56f5d86e3f15e703ab0a577aeef6a1038e71115a - pack_photo_sample.py: --target now required (no albedo fallback) - gen_sample.py: bash wrapper with positional args (input target output_dir) - input/photo7.jpg: copy of photo2 (second style target) - target_1: photo2_1_out→photo2_out, photo2_2_out→photo7_out - dataset/simple/sample_001..007: 7 packed photo/target pairs handoff(Gemini): training data ready; next step is train_cnn_v3.py run feat(cnn_v3): gen_sample tool + 7 simple training samples 2026-03-22T06:33:28Z skal pascal.massimino@gmail.com 2026-03-22T06:33:28Z urn:sha1:fcd1ceb2168de76659091208f911d2c4d0c59ad7 - pack_photo_sample.py: --target now required (no albedo fallback) - gen_sample: bash wrapper with positional args (input target output_dir) - input/photo7.jpg: copy of photo2 (second style target) - target_1: photo2_1_out→photo2_out, photo2_2_out→photo7_out - dataset/simple/sample_001..007: 7 packed photo/target pairs handoff(Gemini): training data ready; next step is train_cnn_v3.py run