2020-10-18 13:57:01 +08:00
|
|
|
__pycache__
|
2023-05-02 00:37:46 +08:00
|
|
|
.venv/
|
|
|
|
|
.vscode
|
Stable diffusion WebGPU port (#1370)
* WIP: Stable diffusion WebGPU port
* Load whole model: split safetensor to avoid Chrome allocation limit
* Gitignore .DS_Store, remove debug print
* Clip tokenizer in JS
* WIP: Compile model in parts (text model, diffusor, get_x_prev_and_pred_x0, decoder), and recreate forward logic in JS
* e2e stable diffusion flow
* Create initial random latent tensor in JS
* SD working e2e
* Log if some weights were not loaded properly
* Remove latent_tensor.npy used for debugging
* Cleanup, remove useless logs
* Improve UI
* Add progress bar
* Remove .npy files used for debugging
* Add clip tokenizer as external dependency
* Remove alphas_cumprod.js and load it from safetensors
* Refactor
* Simplify a lot
* Dedup base when limiting elementwise merge (webgpu)
* Add return type to safe_load_metadata
* Do not allow run when webgpu is not supported
* Add progress bar, refactor, fix special names
* Add option to chose from local vs huggingface weights
* lowercase tinygrad :)
* fp16 model dl, decompression client side
* Cache f16 model in browser, better progress
* Cache miss recovery
---------
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
2023-11-04 09:29:16 +08:00
|
|
|
.DS_Store
|
2020-10-18 13:57:01 +08:00
|
|
|
notebooks
|
|
|
|
|
.*.swp
|
2020-11-08 02:46:36 +08:00
|
|
|
.*.swo
|
[WIP] YOLO working on tinygrad! (#245)
* Some progress on yolov3
* Removed some debugging comments… Also, the forward pass eats all RAM for some reason
* forward pass almost runs
* forward pass runs almost
* forward pass runs, now we gotta load the weights
* loading weights works
* fetches config and weights
* everything kind of works, postprocessing of output still needs to be implemented, temp_process_results kind of works, but its kind of terrible, and not how things should be done
* some changes
* fixed some bugs in the forward pass and load_weights function, now outputs more correct values, however some values are still loaded incorrectly
* Something is wrong with the forward pass, Conv2d tests added
* forward pass almost outputs correct values, gotta fix one more thign
* yolo works
* some final changes
* reverting changes
* removed dataloader
* fixed some indentation
* comment out failing test, somehow it fails CI even though it passes on my computer…
* fixed wrong probabilities
* added webcam option to YOLO, now just need to add bounding boxes and speed it up
* some progress towards adding bounding boxes
* trying to speed up yolo layer on GPU, still faster on CPU but with 30GB ram usage
* Faster inference times, bounding boxes added correctly, webcam works, but is slow, and there is a memory leak when running on CPU... Also added tinygrads output on the classic dog image
* removed some debugging print statements
* updated result image
* something weird is going on, mean op on GPU tensor randomly faults, copying a tensor from GPU->CPU takes 10+ seconds…
2021-04-26 09:06:52 +08:00
|
|
|
*.pyc
|
2023-02-08 23:56:51 +08:00
|
|
|
*.so
|
2023-08-30 22:53:04 +08:00
|
|
|
*.txt
|
2020-10-26 23:19:50 +08:00
|
|
|
build
|
2023-08-11 01:00:51 +08:00
|
|
|
/dist
|
2020-10-26 23:19:50 +08:00
|
|
|
*.egg-info
|
2020-11-08 02:46:36 +08:00
|
|
|
/env
|
2020-12-04 02:32:26 +08:00
|
|
|
a.out
|
2021-10-31 10:40:44 +08:00
|
|
|
boxes.jpg
|
2023-02-18 04:31:05 +08:00
|
|
|
pandecode.dump
|
|
|
|
|
vertex.bin
|
2023-02-21 10:18:18 +08:00
|
|
|
recognize*
|
2023-02-25 12:14:38 +08:00
|
|
|
.idea
|
2023-03-06 03:21:12 +08:00
|
|
|
disassemblers/applegpu
|
2023-05-04 16:04:58 +08:00
|
|
|
disassemblers/cuda_ioctl_sniffer
|
2023-03-10 12:51:22 +08:00
|
|
|
*.prof
|
2023-07-08 01:43:44 +08:00
|
|
|
extra/datasets/cifar-10-python.tar.gz
|
|
|
|
|
extra/datasets/librispeech/
|
|
|
|
|
extra/datasets/imagenet/
|
|
|
|
|
extra/datasets/kits19/
|
|
|
|
|
extra/datasets/squad/
|
|
|
|
|
extra/datasets/img_align_celeba*
|
|
|
|
|
extra/datasets/open-images-v6-mlperf
|
|
|
|
|
extra/datasets/kits/
|
|
|
|
|
extra/datasets/COCO/
|
|
|
|
|
extra/datasets/audio*
|
2023-11-29 09:36:55 +08:00
|
|
|
extra/weights
|
2023-05-30 02:09:20 +08:00
|
|
|
venv
|
Stable diffusion WebGPU port (#1370)
* WIP: Stable diffusion WebGPU port
* Load whole model: split safetensor to avoid Chrome allocation limit
* Gitignore .DS_Store, remove debug print
* Clip tokenizer in JS
* WIP: Compile model in parts (text model, diffusor, get_x_prev_and_pred_x0, decoder), and recreate forward logic in JS
* e2e stable diffusion flow
* Create initial random latent tensor in JS
* SD working e2e
* Log if some weights were not loaded properly
* Remove latent_tensor.npy used for debugging
* Cleanup, remove useless logs
* Improve UI
* Add progress bar
* Remove .npy files used for debugging
* Add clip tokenizer as external dependency
* Remove alphas_cumprod.js and load it from safetensors
* Refactor
* Simplify a lot
* Dedup base when limiting elementwise merge (webgpu)
* Add return type to safe_load_metadata
* Do not allow run when webgpu is not supported
* Add progress bar, refactor, fix special names
* Add option to chose from local vs huggingface weights
* lowercase tinygrad :)
* fp16 model dl, decompression client side
* Cache f16 model in browser, better progress
* Cache miss recovery
---------
Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
2023-11-04 09:29:16 +08:00
|
|
|
examples/**/net.*[js,json]
|
|
|
|
|
examples/**/*.safetensors
|
2023-07-13 03:52:06 +08:00
|
|
|
node_modules
|
|
|
|
|
package.json
|
2023-07-20 00:37:23 +08:00
|
|
|
package-lock.json
|
2023-08-03 00:26:41 +08:00
|
|
|
temp
|
2023-08-06 14:35:01 +08:00
|
|
|
*.csv
|
2023-08-20 23:12:16 +08:00
|
|
|
.coverage
|
|
|
|
|
coverage.xml
|
|
|
|
|
htmlcov
|
2023-10-09 06:10:18 +08:00
|
|
|
outputs_yolov8
|
2023-11-23 09:41:12 +08:00
|
|
|
wandb
|
2023-12-01 09:07:16 +08:00
|
|
|
model.safetensors
|
|
|
|
|
quickstart.py
|
2023-12-07 00:15:46 +08:00
|
|
|
.hypothesis
|
