error trying to use yolov5+sahi on colab and gpu device

[lorenzlorg]

I'm trying to use gpu on Colab (I have Colab Pro+).

I'm setting the parameter 'device'

detection_model = AutoDetectionModel.from_pretrained(
    model_type='yolov5',
    model_path=yolov5_model_path,
    confidence_threshold=0.3,
    device='cuda:0' 
)

but I get this error:

('model_path is not a valid yolov5 model path: ', AssertionError("Invalid CUDA '--device 0' requested, use '--device cpu' or pass valid CUDA device(s)"))

[fcakyon]

Hello @lorenzlorg what are your yolov5-pip and sahi versions?

Your error means, yolov5 cannot use your Colab GPU. Are you sure you have selected a GPU instance?

What is your yolov5 path? is it a name (to be downloaded from git release) or a local weight path?

[lorenzlorg]

Hi,
yolov5==6.2.3
sahi==0.11.1

I'm pretty sure that I've selected a GPU instance because in other notebook I'm using GPU without any problems.

I'm using local weight path and with CPU I've not any issues.

[fcakyon]

Have you tried older yolov5 versions? (6.2.0 etc)

Can you try loading your model with yolov5? Because it may be a yolov5-pip issue instead of sahi issue.

You can try that by:

import yolov5

model = yolov5.load(weight_path, device='cuda:0')

[fcakyon]

What are your cuda, pytorch and torchvision versions btw?

[lorenzlorg]

What are your cuda, pytorch and torchvision versions btw?

Here you are the versions of installed packages:

absl-py==1.3.0
aeppl==0.0.33
aesara==2.7.9
aiohttp==3.8.3
aiosignal==1.3.1
alabaster==0.7.12
albumentations==1.2.1
altair==4.2.0
appdirs==1.4.4
arviz==0.12.1
astor==0.8.1
astropy==4.3.1
astunparse==1.6.3
async-timeout==4.0.2
asynctest==0.13.0
atari-py==0.2.9
atomicwrites==1.4.1
attrs==22.1.0
audioread==3.0.0
autograd==1.5
Babel==2.11.0
backcall==0.2.0
beautifulsoup4==4.6.3
bleach==5.0.1
blis==0.7.9
bokeh==2.3.3
boto3==1.26.8
botocore==1.29.8
branca==0.6.0
bs4==0.0.1
CacheControl==0.12.11
cached-property==1.5.2
cachetools==5.2.0
catalogue==2.0.8
certifi==2022.9.24
cffi==1.15.1
cftime==1.6.2
chardet==3.0.4
charset-normalizer==2.1.1
click==8.0.4
clikit==0.6.2
cloudpickle==1.5.0
cmake==3.22.6
cmdstanpy==1.0.8
colorcet==3.0.1
colorlover==0.3.0
community==1.0.0b1
confection==0.0.3
cons==0.4.5
contextlib2==0.5.5
convertdate==2.4.0
crashtest==0.3.1
crcmod==1.7
cufflinks==0.17.3
cupy-cuda11x==11.0.0
cvxopt==1.3.0
cvxpy==1.2.2
cycler==0.11.0
cymem==2.0.7
Cython==0.29.32
daft==0.0.4
dask==2022.2.0
datascience==0.17.5
db-dtypes==1.0.4
debugpy==1.0.0
decorator==4.4.2
defusedxml==0.7.1
descartes==1.1.0
dill==0.3.6
distributed==2022.2.0
dlib==19.24.0
dm-tree==0.1.7
dnspython==2.2.1
docutils==0.17.1
dopamine-rl==1.0.5
earthengine-api==0.1.330
easydict==1.10
ecos==2.0.10
editdistance==0.5.3
en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1-py3-none-any.whl
entrypoints==0.4
ephem==4.1.3
et-xmlfile==1.1.0
etils==0.9.0
etuples==0.3.8
fa2==0.3.5
fastai==2.7.10
fastcore==1.5.27
fastdownload==0.0.7
fastdtw==0.3.4
fastjsonschema==2.16.2
fastprogress==1.0.3
fastrlock==0.8.1
feather-format==0.4.1
filelock==3.8.0
fire==0.4.0
firebase-admin==5.3.0
fix-yahoo-finance==0.0.22
Flask==1.1.4
flatbuffers==1.12
folium==0.12.1.post1
frozenlist==1.3.3
fsspec==2022.10.0
future==0.16.0
gast==0.4.0
GDAL==2.2.2
gdown==4.4.0
gensim==3.6.0
geographiclib==1.52
geopy==1.17.0
gin-config==0.5.0
glob2==0.7
google==2.0.3
google-api-core==2.8.2
google-api-python-client==1.12.11
google-auth==2.14.1
google-auth-httplib2==0.0.4
google-auth-oauthlib==0.4.6
google-cloud-bigquery==3.3.6
google-cloud-bigquery-storage==2.16.2
google-cloud-core==2.3.2
google-cloud-datastore==2.9.0
google-cloud-firestore==2.7.2
google-cloud-language==2.6.1
google-cloud-storage==2.5.0
google-cloud-translate==3.8.4
google-colab @ file:///colabtools/dist/google-colab-1.0.0.tar.gz
google-crc32c==1.5.0
google-pasta==0.2.0
google-resumable-media==2.4.0
googleapis-common-protos==1.56.4
googledrivedownloader==0.4
graphviz==0.10.1
greenlet==2.0.1
grpcio==1.50.0
grpcio-status==1.48.2
gspread==3.4.2
gspread-dataframe==3.0.8
gym==0.25.2
gym-notices==0.0.8
h5py==3.1.0
HeapDict==1.0.1
hijri-converter==2.2.4
holidays==0.16
holoviews==1.14.9
html5lib==1.0.1
httpimport==0.5.18
httplib2==0.17.4
httpstan==4.6.1
humanize==0.5.1
hyperopt==0.1.2
idna==2.10
imageio==2.9.0
imagesize==1.4.1
imbalanced-learn==0.8.1
imblearn==0.0
imgaug==0.4.0
importlib-metadata==4.13.0
importlib-resources==5.10.0
imutils==0.5.4
inflect==2.1.0
intel-openmp==2022.2.1
intervaltree==2.1.0
ipykernel==5.3.4
ipython==7.9.0
ipython-genutils==0.2.0
ipython-sql==0.3.9
ipywidgets==7.7.1
itsdangerous==1.1.0
jax==0.3.23
jaxlib @ https://storage.googleapis.com/jax-releases/cuda11/jaxlib-0.3.22+cuda11.cudnn805-cp37-cp37m-manylinux2014_x86_64.whl
jedi==0.18.1
jieba==0.42.1
Jinja2==2.11.3
jmespath==1.0.1
joblib==1.2.0
jpeg4py==0.1.4
jsonschema==4.3.3
jupyter-client==6.1.12
jupyter-console==6.1.0
jupyter-core==4.11.2
jupyterlab-widgets==3.0.3
kaggle==1.5.12
kapre==0.3.7
keras==2.9.0
Keras-Preprocessing==1.1.2
keras-vis==0.4.1
kiwisolver==1.4.4
korean-lunar-calendar==0.3.1
langcodes==3.3.0
libclang==14.0.6
librosa==0.8.1
lightgbm==2.2.3
llvmlite==0.39.1
lmdb==0.99
locket==1.0.0
logical-unification==0.4.5
LunarCalendar==0.0.9
lxml==4.9.1
Markdown==3.4.1
MarkupSafe==2.0.1
marshmallow==3.18.0
matplotlib==3.2.2
matplotlib-venn==0.11.7
miniKanren==1.0.3
missingno==0.5.1
mistune==0.8.4
mizani==0.7.3
mkl==2019.0
mlxtend==0.14.0
more-itertools==9.0.0
moviepy==0.2.3.5
mpmath==1.2.1
msgpack==1.0.4
multidict==6.0.2
multipledispatch==0.6.0
multitasking==0.0.11
murmurhash==1.0.9
music21==5.5.0
natsort==5.5.0
nbconvert==5.6.1
nbformat==5.7.0
netCDF4==1.6.1
networkx==2.6.3
nibabel==3.0.2
nltk==3.7
notebook==5.7.16
numba==0.56.4
numexpr==2.8.4
numpy==1.21.6
oauth2client==4.1.3
oauthlib==3.2.2
okgrade==0.4.3
opencv-contrib-python==4.6.0.66
opencv-python==4.6.0.66
opencv-python-headless==4.6.0.66
openpyxl==3.0.10
opt-einsum==3.3.0
osqp==0.6.2.post0
packaging==21.3
palettable==3.3.0
pandas==1.3.5
pandas-datareader==0.9.0
pandas-gbq==0.17.9
pandas-profiling==1.4.1
pandocfilters==1.5.0
panel==0.12.1
param==1.12.2
parso==0.8.3
partd==1.3.0
pastel==0.2.1
pathlib==1.0.1
pathy==0.6.2
patsy==0.5.3
pep517==0.13.0
pexpect==4.8.0
pickleshare==0.7.5
Pillow==9.3.0
pip-tools==6.2.0
plotly==5.5.0
plotnine==0.8.0
pluggy==0.7.1
pooch==1.6.0
portpicker==1.3.9
prefetch-generator==1.0.1
preshed==3.0.8
prettytable==3.5.0
progressbar2==3.38.0
prometheus-client==0.15.0
promise==2.3
prompt-toolkit==2.0.10
prophet==1.1.1
proto-plus==1.22.1
protobuf==3.19.6
psutil==5.4.8
psycopg2==2.9.5
ptyprocess==0.7.0
py==1.11.0
pyarrow==6.0.1
pyasn1==0.4.8
pyasn1-modules==0.2.8
pybboxes==0.1.5
pycocotools==2.0.6
pycparser==2.21
pyct==0.4.8
pydantic==1.10.2
pydata-google-auth==1.4.0
pydot==1.3.0
pydot-ng==2.0.0
pydotplus==2.0.2
PyDrive==1.3.1
pyemd==0.5.1
pyerfa==2.0.0.1
Pygments==2.6.1
pygobject==3.26.1
pylev==1.4.0
pymc==4.1.4
PyMeeus==0.5.11
pymongo==4.3.2
pymystem3==0.2.0
PyOpenGL==3.1.6
pyparsing==3.0.9
pyrsistent==0.19.2
pysimdjson==3.2.0
pysndfile==1.3.8
PySocks==1.7.1
pystan==3.3.0
pytest==3.6.4
python-apt==0.0.0
python-dateutil==2.8.2
python-louvain==0.16
python-slugify==6.1.2
python-utils==3.4.5
pytz==2022.6
pyviz-comms==2.2.1
PyWavelets==1.3.0
PyYAML==6.0
pyzmq==23.2.1
qdldl==0.1.5.post2
qudida==0.0.4
regex==2022.6.2
requests==2.23.0
requests-oauthlib==1.3.1
resampy==0.4.2
rpy2==3.5.5
rsa==4.9
s3transfer==0.6.0
sahi==0.11.2
scikit-image==0.18.3
scikit-learn==1.0.2
scipy==1.7.3
screen-resolution-extra==0.0.0
scs==3.2.2
seaborn==0.11.2
Send2Trash==1.8.0
setuptools-git==1.2
Shapely==1.8.5.post1
six==1.15.0
sklearn-pandas==1.8.0
smart-open==5.2.1
snowballstemmer==2.2.0
sortedcontainers==2.4.0
soundfile==0.11.0
spacy==3.4.2
spacy-legacy==3.0.10
spacy-loggers==1.0.3
Sphinx==1.8.6
sphinxcontrib-serializinghtml==1.1.5
sphinxcontrib-websupport==1.2.4
SQLAlchemy==1.4.43
sqlparse==0.4.3
srsly==2.4.5
statsmodels==0.12.2
sympy==1.7.1
tables==3.7.0
tabulate==0.8.10
tblib==1.7.0
tenacity==8.1.0
tensorboard==2.9.1
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
tensorflow==2.9.2
tensorflow-datasets==4.6.0
tensorflow-estimator==2.9.0
tensorflow-gcs-config==2.9.1
tensorflow-hub==0.12.0
tensorflow-io-gcs-filesystem==0.27.0
tensorflow-metadata==1.10.0
tensorflow-probability==0.17.0
termcolor==2.1.0
terminado==0.13.3
terminaltables==3.1.10
testpath==0.6.0
text-unidecode==1.3
textblob==0.15.3
thinc==8.1.5
thop==0.1.1.post2209072238
threadpoolctl==3.1.0
tifffile==2021.11.2
toml==0.10.2
tomli==2.0.1
toolz==0.12.0
torch @ https://download.pytorch.org/whl/cu113/torch-1.12.1%2Bcu113-cp37-cp37m-linux_x86_64.whl
torchaudio @ https://download.pytorch.org/whl/cu113/torchaudio-0.12.1%2Bcu113-cp37-cp37m-linux_x86_64.whl
torchsummary==1.5.1
torchtext==0.13.1
torchvision @ https://download.pytorch.org/whl/cu113/torchvision-0.13.1%2Bcu113-cp37-cp37m-linux_x86_64.whl
tornado==6.0.4
tqdm==4.64.1
traitlets==5.1.1
tweepy==3.10.0
typeguard==2.7.1
typer==0.4.2
typing-extensions==4.1.1
tzlocal==1.5.1
uritemplate==3.0.1
urllib3==1.25.11
vega-datasets==0.9.0
wasabi==0.10.1
wcwidth==0.2.5
webargs==8.2.0
webencodings==0.5.1
Werkzeug==1.0.1
widgetsnbextension==3.6.1
wordcloud==1.8.2.2
wrapt==1.14.1
xarray==0.20.2
xarray-einstats==0.2.2
xgboost==0.90
xkit==0.0.0
xlrd==1.1.0
xlwt==1.3.0
yarl==1.8.1
yellowbrick==1.5
yolov5==6.2.3
zict==2.2.0
zipp==3.10.0

[fcakyon]

I have just tried this notebook on Google Colab GPU instance: https://github.com/obss/sahi/blob/main/demo/inference_for_yolov5.ipynb

Updated first command with:
!pip install -U torch==1.11.0 torchvision==0.12.0 pillow==8.* sahi yolov5

and device with 'cuda:0'

Did not have any issues.

[fcakyon]

Glad to hear you fixed it! Also thank you for the useful information 👍

[lorenzlorg]

@fcakyon last question!

Is it possibile that this method gets different results depending on which input (image vs video)?

For image I've used:

detection_model = AutoDetectionModel.from_pretrained(
    model_type='yolov5',
    model_path=yolov5_model_path,
    confidence_threshold=0.3,
    #device = 'cpu'
    device = 'cuda:0'
)

result = get_sliced_prediction(
    "/content/drive/MyDrive/duomo.jpg",
    detection_model,
    slice_height = 256,
    slice_width = 256,
    overlap_height_ratio = 0.2,
    overlap_width_ratio = 0.2
)

and I get:

while for video i?ve used:
!sahi predict --model_path /content/drive/MyDrive/best50_yolov5.pt --model_type yolov5 --source /content/drive/MyDrive/duomo2sec.mp4 --slice_height 256 --slice_width 256 --overlap_height_ratio 0.2 --overlap_width_ratio 0.2 --model_device 'cuda:0'

and taking a single frame I get this:

It seems that even if I use the same parameters I get less detections.

[fcakyon]

You provide threshold as 0.3 with confidence_threshold=0.3.

However, default threshold is 0.25 in predict cli:

sahi/sahi/predict.py

Line 297 in 1e1e965

model_confidence_threshold: float = 0.25,

There might be other differences in the parameters you are using.

[fcakyon]

Also the ss quality and video decoding quality might be different.

[lorenzlorg]

thanks again for your help @fcakyon !!!

[kolingv]

Cause may be weight downloading is't finished, while code runs to laoding model. I got model size of around 16M at the first time when facing the same issue; After seting breakpoint after download part and wait for download fiinsh, I got the model of 25M. Then no more eroor.

[dsnsabari]

@lorenzlorg how can i use the sahi for tensorflow models?