tinygrad/examples
Kunwar Raj Singh 5d3310ce56
MaskRCNN Inference (#884)
* MaskRCNN weights loading

* backbone maybe works

* backbone works, but resnet body atol 1e-3

* RPN Call, but veryy wrong output

* fixed topk

* RPN maybe works, not sure about nms

* Fix cursed modules

* add back editorconfig

* Full call, wrong output

* Full call works

* fix mask

* use NMS from retinanet

* Removing extra funcs

* refactor

* readable

* Add example to run model

* remove filter

* Fix split, batched inference is worse

* Fix image sizes

* Matching reference

* merge master

* add filter on top detections

* cuda backend fixed

* add model eval and spec

* convert images to rgb

* fix eval

* simplify examples code

* remove extra code

* meshgrid using tinygrad

* removing numpy

* roi align, floor, ceil

* remove numpy from level_mapper

* remove numpy from pooler

* Revert "Merge branch 'master' of github.com:kunwar31/tinygrad into mrcnn-inference"

This reverts commit 4b95a3cb49, reversing
changes made to 98f2b1fa2e.

* roi align gather

* fix master merge

* revert to old floor, ceil as ints present in domain

* use log2 op

* fix indexes

* weird bug with ints and gpu

* weird bug with ints and gpu

* refactors, add env var for gather

* floor with contiguous, where

* refactor topk, sort

* remove staticmethod

* refactor stride

* remove log2 mlop

* realize -> contiguous

* refactor forward

* remove num_classes, stride_in_1x1 from state

* refactor forward

* refactoring

* flake8

* removing numpy in anchor gen, use numpy for gather, nonzero, optimize topk

* keep using tinygrad for smaller gathers

* fix empty tensors

* comms

* move from tensor.py

* resnet test passing

* add coco dataset back

* fix spaces

* add test for log2

* no need to create Tensors

* no need to create Tensors

---------

Co-authored-by: Kunwar Raj Singh <kunwar31@pop-os.localdomain>
2023-06-25 15:37:51 -07:00
..
mlperf MaskRCNN Inference (#884) 2023-06-25 15:37:51 -07:00
yolo Permute examples (#731) 2023-03-29 05:07:06 +04:00
__init__.py failing llama test 2023-03-11 16:28:10 -08:00
benchmark_train_efficientnet.py rename log_softmax, support dim, fix onnx Softmax 2023-02-24 10:11:24 -08:00
compile_efficientnet.py Fix input path in examples/compile_efficientnet.py, examples/efficientnet.py. (#1034) 2023-06-23 16:34:33 -07:00
compile_tensorflow.py moved extras/jit.py -> tinygrad/jit.py (#599) 2023-02-25 08:32:33 -08:00
deep_deterministic_policy_gradient.py Fixed DDPG example (#667) 2023-03-09 11:49:52 -08:00
efficientnet.py Fix input path in examples/compile_efficientnet.py, examples/efficientnet.py. (#1034) 2023-06-23 16:34:33 -07:00
hlb_cifar10.py nn init matches torch (#901) 2023-06-01 21:24:11 -07:00
hlb_cifar10_torch.py nn init matches torch (#901) 2023-06-01 21:24:11 -07:00
llama.py Adds tril & triu support (#936) 2023-06-09 22:13:20 -07:00
mask_rcnn.py MaskRCNN Inference (#884) 2023-06-25 15:37:51 -07:00
mnist_gan.py Cast Tensor data to float32 (#703) 2023-03-14 23:09:41 -07:00
serious_mnist.py rename log_softmax, support dim, fix onnx Softmax 2023-02-24 10:11:24 -08:00
stable_diffusion.py Adds tril & triu support (#936) 2023-06-09 22:13:20 -07:00
train_efficientnet.py train_efficientnet: only import datasets.imagenet when IMAGENET is set (#899) 2023-06-01 19:19:52 -07:00
train_resnet.py ResNet: match implementation with Nvidia and PyTorch (#770) 2023-05-10 09:01:22 -07:00
transformer.py add int64 as supported dtype from numpy (#699) 2023-03-18 17:15:04 -07:00
vgg7.py Remove Tensor.data (#565) 2023-02-18 16:36:12 -08:00
vit.py Remove Tensor.data (#565) 2023-02-18 16:36:12 -08:00
whisper.py there is a better way to do that! (#950) 2023-06-06 15:23:30 -07:00
yolov3.py Permute examples (#731) 2023-03-29 05:07:06 +04:00
yolov8-onnx.py Add yolov8 implementation (#806) 2023-06-16 18:55:19 -07:00
yolov8.py "Fixed argument passing in example yolov8" (#1004) 2023-06-18 14:29:39 -07:00