github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-02-18 10:31:41 -05:00
Code Issues Packages Projects Releases Wiki Activity

MaskRCNN Inference (#884)

Browse Source 
* 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>
This commit is contained in:
Kunwar Raj Singh
2023-06-26 04:07:51 +05:30
committed by GitHub
parent 0f281e7b18
commit 5d3310ce56
8 changed files with 1854 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tinygrad/tensor.py
View File

@@ -7,7 +7,7 @@ import operator
import numpy as np
from typing import List, Tuple, Callable, Optional, ClassVar, Type, Union, Sequence, cast
from tinygrad.helpers import ImageDType, argfix, make_pair, getenv, IMAGE, DEBUG, flatten, DType, dtypes
from math import ceil, pi, prod, sqrt
from math import ceil, pi, prod, sqrt, log
from tinygrad.lazy import Device, LazyBuffer
from tinygrad.ops import LoadOps
@@ -481,6 +481,7 @@ class Tensor:
def contiguous(self): return mlops.Contiguous.apply(self)
def log(self): return mlops.Log.apply(self)
def log2(self): return mlops.Log.apply(self)/log(2)
def exp(self): return mlops.Exp.apply(self)
def relu(self): return mlops.Relu.apply(self)
def sin(self): return mlops.Sin.apply(self)