receptive_field_analysis_toolbox icon indicating copy to clipboard operation
receptive_field_analysis_toolbox copied to clipboard

Published 20 hours ago • verified publisher icon MLRichter

YOLOv7-Tiny: Is this program recognize nn.upsample??

Open Jochiwon opened this issue 1 year ago • 1 comments

Hi, I'm trying to test this code to my yolov7-tiny model.

I found some errors at first time, but after fixing some code, it worked!

<MyCode.py>

from rfa_toolbox import create_graph_from_pytorch_model, visualize_architecture
import torch
import argparse
import torchvision


def do(model_path):

    model = torch.load(model_path, map_location=torch.device('cuda:0'))

    graph = create_graph_from_pytorch_model(model['model'])

    #model = torchvision.models.alexnet()
    #graph = create_graph_from_pytorch_model(model)

    visualize_architecture(
        graph, f"Yolov7-Tiny-pixel", input_res=416
    ).view()


if __name__ == "__main__":
    ap = argparse.ArgumentParser()
    ap.add_argument('--model', required=True, help='path to weight file')
    args = vars(ap.parse_args())

    do(args['model'])

    print('Program is terminated.\n')

<rfa_toolbox/encodings/pytorch/ingest_architecture.py>

def _obtain_variable_names(graph: torch._C.Graph) -> Dict[str, str]:
    result = {}
    for node in graph.nodes():
        try:
            x, y = str(node).split(" : ")
            key, value = x, y
            result[key] = value
            print(result[key])
        # This Part Added ======================
        except:
            temp = []
            temp = str(node).split(", %")
            for i in range(len(temp)):
                if i == 0:
                    x, y = str(temp[i]).split(" : ")
                else:
                    temp[i] = '%' + temp[i]
                    x, y = str(temp[i]).split(" : ")

                result[x] = y
                print(result[x])
            return result
        # =================================
    return result

def create_graph_from_model(
    model: torch.nn.Module,
    filter_rf: Optional[
        Union[
            Callable[[Tuple[ReceptiveFieldInfo, ...]], Tuple[ReceptiveFieldInfo, ...]],
            str,
        ]
    ] = None,
    input_res: Tuple[int, int, int, int] = (1, 3, 399, 399),
    custom_layers: Optional[List[str]] = None,
    display_se_modules: bool = False,
) -> EnrichedNetworkNode:
    """Create a graph of enriched network nodes from a PyTorch-Model.
    Args:
        model:          a PyTorch-Model.
        filter_rf:      a function that filters receptive field sizes.
                        Disabled by default.
        input_res:      input-tuple shape that can be processed by the model.
                        Needs to be a 4-Tuple of shape (batch_size,
                        color_channels, height, width) for CNNs.
                        Needs to be a 2-Tuple of shape (batch_size,
                        num_features) for fully connected networks.
        custom_layers:  Class-names of custom layers, like DropPath
                        or Involutions, which are not part of
                        torch.nn. Keep in mind that unknown layers
                        will defaulted to have no effect on the
                        receptive field size. You may need to
                        implement some additional layer handlers.
        display_se_modules: False by default. If True, displays the structure
                        inside Squeeze-and-Excitation modules and considers their
                        maximum receptive field size infinite, which is technically
                        closer to the truth but irrelevant in practice.
    Returns:
        The EnrichedNetworkNodeGraph
    """
    custom_layers = (
        ["ConvNormActivation"]
        if custom_layers is None
        else custom_layers + ["ConvNormActivation"]
    )
    if not display_se_modules:
        custom_layers.append("SqueezeExcitation")
    filter_func = (
        filter_rf
        if (not isinstance(filter_rf, str) and filter_rf is not None)
        else KNOWN_FILTER_MAPPING[filter_rf]
    )
    # This Part Added ======================
    inputTensor = torch.as_tensor(torch.randn(*input_res), dtype=torch.half).to('cuda:0')
    tm = torch.jit.trace(model, inputTensor)
    # =================================

    return make_graph(
        tm, filter_rf=filter_func, ref_mod=model, classes_to_not_visit=custom_layers
    ).to_graph()

After it worked, I looked result pdf file and recognized strange part.

visualized_2

After Upsample Layer, "Feature Map Res" is not changed..

Isn't it should be changed like below picture? It is tensor size of each layer.

tensor_shape

Sorry for unclean text, I'm not used to github.

Do you have any idea to solve this issue?

My env:

Detail

name: base channels:

  • conda-forge
  • defaults dependencies:
  • _ipyw_jlab_nb_ext_conf=0.1.0=py39h06a4308_1
  • _libgcc_mutex=0.1=main
  • _openmp_mutex=5.1=1_gnu
  • alabaster=0.7.12=pyhd3eb1b0_0
  • anaconda=2022.10=py39_0
  • anaconda-client=1.11.0=py39h06a4308_0
  • anaconda-navigator=2.4.0=py39h06a4308_0
  • anaconda-project=0.11.1=py39h06a4308_0
  • anyio=3.5.0=py39h06a4308_0
  • appdirs=1.4.4=pyhd3eb1b0_0
  • argon2-cffi=21.3.0=pyhd3eb1b0_0
  • argon2-cffi-bindings=21.2.0=py39h7f8727e_0
  • arrow=1.2.2=pyhd3eb1b0_0
  • astroid=2.11.7=py39h06a4308_0
  • astropy=5.1=py39h7deecbd_0
  • atk-1.0=2.36.0=ha1a6a79_0
  • atomicwrites=1.4.0=py_0
  • attrs=21.4.0=pyhd3eb1b0_0
  • automat=20.2.0=py_0
  • autopep8=1.6.0=pyhd3eb1b0_1
  • babel=2.9.1=pyhd3eb1b0_0
  • backcall=0.2.0=pyhd3eb1b0_0
  • backports=1.1=pyhd3eb1b0_0
  • backports.functools_lru_cache=1.6.4=pyhd3eb1b0_0
  • backports.tempfile=1.0=pyhd3eb1b0_1
  • backports.weakref=1.0.post1=py_1
  • bcrypt=3.2.0=py39h5eee18b_1
  • beautifulsoup4=4.11.1=py39h06a4308_0
  • binaryornot=0.4.4=pyhd3eb1b0_1
  • bitarray=2.5.1=py39h5eee18b_0
  • bkcharts=0.2=py39h06a4308_1
  • black=22.6.0=py39h06a4308_0
  • blas=1.0=mkl
  • bleach=4.1.0=pyhd3eb1b0_0
  • blosc=1.21.0=h4ff587b_1
  • bokeh=2.4.3=py39h06a4308_0
  • boto3=1.24.28=py39h06a4308_0
  • botocore=1.27.28=py39h06a4308_0
  • bottleneck=1.3.5=py39h7deecbd_0
  • brotli=1.0.9=h5eee18b_7
  • brotli-bin=1.0.9=h5eee18b_7
  • brotlipy=0.7.0=py39h27cfd23_1003
  • brunsli=0.1=h2531618_0
  • bzip2=1.0.8=h7b6447c_0
  • c-ares=1.18.1=h7f8727e_0
  • ca-certificates=2022.07.19=h06a4308_0
  • cairo=1.16.0=h19f5f5c_2
  • certifi=2022.9.14=py39h06a4308_0
  • cffi=1.15.1=py39h74dc2b5_0
  • cfitsio=3.470=h5893167_7
  • chardet=4.0.0=py39h06a4308_1003
  • charls=2.2.0=h2531618_0
  • charset-normalizer=2.0.4=pyhd3eb1b0_0
  • click=8.0.4=py39h06a4308_0
  • cloudpickle=2.0.0=pyhd3eb1b0_0
  • clyent=1.2.2=py39h06a4308_1
  • colorama=0.4.5=py39h06a4308_0
  • colorcet=3.0.0=py39h06a4308_0
  • conda=23.1.0=py39h06a4308_0
  • conda-build=3.22.0=py39h06a4308_0
  • conda-content-trust=0.1.3=py39h06a4308_0
  • conda-env=2.6.0=1
  • conda-pack=0.6.0=pyhd3eb1b0_0
  • conda-package-handling=1.9.0=py39h5eee18b_0
  • conda-repo-cli=1.0.20=py39h06a4308_0
  • conda-token=0.4.0=pyhd3eb1b0_0
  • conda-verify=3.4.2=py_1
  • constantly=15.1.0=pyh2b92418_0
  • cookiecutter=1.7.3=pyhd3eb1b0_0
  • cryptography=37.0.1=py39h9ce1e76_0
  • cssselect=1.1.0=pyhd3eb1b0_0
  • curl=7.84.0=h5eee18b_0
  • cycler=0.11.0=pyhd3eb1b0_0
  • cython=0.29.32=py39h6a678d5_0
  • cytoolz=0.11.0=py39h27cfd23_0
  • daal4py=2021.6.0=py39h79cecc1_1
  • dal=2021.6.0=hdb19cb5_916
  • dask=2022.7.0=py39h06a4308_0
  • dask-core=2022.7.0=py39h06a4308_0
  • dataclasses=0.8=pyh6d0b6a4_7
  • datashader=0.14.1=py39h06a4308_0
  • datashape=0.5.4=py39h06a4308_1
  • dbus=1.13.18=hb2f20db_0
  • debugpy=1.5.1=py39h295c915_0
  • decorator=5.1.1=pyhd3eb1b0_0
  • defusedxml=0.7.1=pyhd3eb1b0_0
  • diff-match-patch=20200713=pyhd3eb1b0_0
  • dill=0.3.4=pyhd3eb1b0_0
  • distributed=2022.7.0=py39h06a4308_0
  • docutils=0.18.1=py39h06a4308_3
  • entrypoints=0.4=py39h06a4308_0
  • et_xmlfile=1.1.0=py39h06a4308_0
  • expat=2.4.9=h6a678d5_0
  • fftw=3.3.9=h27cfd23_1
  • filelock=3.6.0=pyhd3eb1b0_0
  • flake8=4.0.1=pyhd3eb1b0_1
  • flask=1.1.2=pyhd3eb1b0_0
  • font-ttf-dejavu-sans-mono=2.37=hd3eb1b0_0
  • font-ttf-inconsolata=2.001=hcb22688_0
  • font-ttf-source-code-pro=2.030=hd3eb1b0_0
  • font-ttf-ubuntu=0.83=h8b1ccd4_0
  • fontconfig=2.13.1=h6c09931_0
  • fonts-anaconda=1=h8fa9717_0
  • fonts-conda-ecosystem=1=hd3eb1b0_0
  • fonttools=4.25.0=pyhd3eb1b0_0
  • freetype=2.11.0=h70c0345_0
  • fribidi=1.0.10=h7b6447c_0
  • fsspec=2022.7.1=py39h06a4308_0
  • future=0.18.2=py39h06a4308_1
  • gdk-pixbuf=2.42.8=h433bba3_1
  • gensim=4.1.2=py39h295c915_0
  • giflib=5.2.1=h7b6447c_0
  • glib=2.69.1=h4ff587b_1
  • glob2=0.7=pyhd3eb1b0_0
  • gmp=6.2.1=h295c915_3
  • gmpy2=2.1.2=py39heeb90bb_0
  • gobject-introspection=1.72.0=py39hbb6d50b_0
  • graphite2=1.3.14=h295c915_1
  • graphviz=2.50.0=h3cd0ef9_0
  • greenlet=1.1.1=py39h295c915_0
  • gst-plugins-base=1.14.0=h8213a91_2
  • gstreamer=1.14.0=h28cd5cc_2
  • gtk2=2.24.33=h73c1081_2
  • gts=0.7.6=hb67d8dd_3
  • h5py=3.7.0=py39h737f45e_0
  • harfbuzz=4.3.0=hf52aaf7_1
  • hdf5=1.10.6=h3ffc7dd_1
  • heapdict=1.0.1=pyhd3eb1b0_0
  • holoviews=1.15.0=py39h06a4308_0
  • hvplot=0.8.0=py39h06a4308_0
  • hyperlink=21.0.0=pyhd3eb1b0_0
  • icu=58.2=he6710b0_3
  • idna=3.3=pyhd3eb1b0_0
  • imagecodecs=2021.8.26=py39hf0132c2_1
  • imageio=2.19.3=py39h06a4308_0
  • imagesize=1.4.1=py39h06a4308_0
  • importlib-metadata=4.11.3=py39h06a4308_0
  • importlib_metadata=4.11.3=hd3eb1b0_0
  • incremental=21.3.0=pyhd3eb1b0_0
  • inflection=0.5.1=py39h06a4308_0
  • iniconfig=1.1.1=pyhd3eb1b0_0
  • intake=0.6.5=pyhd3eb1b0_0
  • intel-openmp=2021.4.0=h06a4308_3561
  • intervaltree=3.1.0=pyhd3eb1b0_0
  • ipykernel=6.15.2=py39h06a4308_0
  • ipython=7.31.1=py39h06a4308_1
  • ipython_genutils=0.2.0=pyhd3eb1b0_1
  • ipywidgets=7.6.5=pyhd3eb1b0_1
  • isort=5.9.3=pyhd3eb1b0_0
  • itemadapter=0.3.0=pyhd3eb1b0_0
  • itemloaders=1.0.4=pyhd3eb1b0_1
  • itsdangerous=2.0.1=pyhd3eb1b0_0
  • jdcal=1.4.1=pyhd3eb1b0_0
  • jedi=0.18.1=py39h06a4308_1
  • jeepney=0.7.1=pyhd3eb1b0_0
  • jellyfish=0.9.0=py39h7f8727e_0
  • jinja2=2.11.3=pyhd3eb1b0_0
  • jinja2-time=0.2.0=pyhd3eb1b0_3
  • jmespath=0.10.0=pyhd3eb1b0_0
  • joblib=1.1.0=pyhd3eb1b0_0
  • jpeg=9e=h7f8727e_0
  • jq=1.6=h27cfd23_1000
  • json5=0.9.6=pyhd3eb1b0_0
  • jsonschema=4.16.0=py39h06a4308_0
  • jupyter=1.0.0=py39h06a4308_8
  • jupyter_client=7.3.4=py39h06a4308_0
  • jupyter_console=6.4.3=pyhd3eb1b0_0
  • jupyter_core=4.11.1=py39h06a4308_0
  • jupyter_server=1.18.1=py39h06a4308_0
  • jupyterlab=3.4.4=py39h06a4308_0
  • jupyterlab_pygments=0.1.2=py_0
  • jupyterlab_server=2.10.3=pyhd3eb1b0_1
  • jupyterlab_widgets=1.0.0=pyhd3eb1b0_1
  • jxrlib=1.1=h7b6447c_2
  • keyring=23.4.0=py39h06a4308_0
  • kiwisolver=1.4.2=py39h295c915_0
  • krb5=1.19.2=hac12032_0
  • lazy-object-proxy=1.6.0=py39h27cfd23_0
  • lcms2=2.12=h3be6417_0
  • ld_impl_linux-64=2.38=h1181459_1
  • lerc=3.0=h295c915_0
  • libaec=1.0.4=he6710b0_1
  • libarchive=3.6.1=hab531cd_0
  • libbrotlicommon=1.0.9=h5eee18b_7
  • libbrotlidec=1.0.9=h5eee18b_7
  • libbrotlienc=1.0.9=h5eee18b_7
  • libcurl=7.84.0=h91b91d3_0
  • libdeflate=1.8=h7f8727e_5
  • libedit=3.1.20210910=h7f8727e_0
  • libev=4.33=h7f8727e_1
  • libevent=2.1.12=h8f2d780_0
  • libffi=3.3=he6710b0_2
  • libgcc-ng=11.2.0=h1234567_1
  • libgd=2.3.3=h695aa2c_1
  • libgfortran-ng=11.2.0=h00389a5_1
  • libgfortran5=11.2.0=h1234567_1
  • libgomp=11.2.0=h1234567_1
  • libidn2=2.3.2=h7f8727e_0
  • liblief=0.11.5=h295c915_1
  • libllvm10=10.0.1=hbcb73fb_5
  • libllvm11=11.1.0=h9e868ea_5
  • libnghttp2=1.46.0=hce63b2e_0
  • libpng=1.6.37=hbc83047_0
  • libpq=12.9=h16c4e8d_3
  • librsvg=2.54.4=h19fe530_0
  • libsodium=1.0.18=h7b6447c_0
  • libspatialindex=1.9.3=h2531618_0
  • libssh2=1.10.0=h8f2d780_0
  • libstdcxx-ng=11.2.0=h1234567_1
  • libtiff=4.4.0=hecacb30_0
  • libtool=2.4.6=h6a678d5_1009
  • libunistring=0.9.10=h27cfd23_0
  • libuuid=1.0.3=h7f8727e_2
  • libwebp=1.2.2=h55f646e_0
  • libwebp-base=1.2.2=h7f8727e_0
  • libxcb=1.15=h7f8727e_0
  • libxkbcommon=1.0.1=hfa300c1_0
  • libxml2=2.9.14=h74e7548_0
  • libxslt=1.1.35=h4e12654_0
  • libzopfli=1.0.3=he6710b0_0
  • llvmlite=0.38.0=py39h4ff587b_0
  • locket=1.0.0=py39h06a4308_0
  • lxml=4.9.1=py39h1edc446_0
  • lz4=3.1.3=py39h27cfd23_0
  • lz4-c=1.9.3=h295c915_1
  • lzo=2.10=h7b6447c_2
  • markdown=3.3.4=py39h06a4308_0
  • markupsafe=2.0.1=py39h27cfd23_0
  • matplotlib=3.5.2=py39h06a4308_0
  • matplotlib-base=3.5.2=py39hf590b9c_0
  • matplotlib-inline=0.1.6=py39h06a4308_0
  • mccabe=0.7.0=pyhd3eb1b0_0
  • mistune=0.8.4=py39h27cfd23_1000
  • mkl=2021.4.0=h06a4308_640
  • mkl-service=2.4.0=py39h7f8727e_0
  • mkl_fft=1.3.1=py39hd3c417c_0
  • mkl_random=1.2.2=py39h51133e4_0
  • mock=4.0.3=pyhd3eb1b0_0
  • mpc=1.1.0=h10f8cd9_1
  • mpfr=4.0.2=hb69a4c5_1
  • mpi=1.0=mpich
  • mpich=3.3.2=external_0
  • mpmath=1.2.1=py39h06a4308_0
  • msgpack-python=1.0.3=py39hd09550d_0
  • multipledispatch=0.6.0=py39h06a4308_0
  • munkres=1.1.4=py_0
  • mypy_extensions=0.4.3=py39h06a4308_1
  • navigator-updater=0.3.0=py39h06a4308_0
  • nbclassic=0.3.5=pyhd3eb1b0_0
  • nbclient=0.5.13=py39h06a4308_0
  • nbconvert=6.4.4=py39h06a4308_0
  • nbformat=5.5.0=py39h06a4308_0
  • ncurses=6.3=h5eee18b_3
  • nest-asyncio=1.5.5=py39h06a4308_0
  • networkx=2.8.4=py39h06a4308_0
  • ninja=1.10.2=h06a4308_5
  • ninja-base=1.10.2=hd09550d_5
  • nltk=3.7=pyhd3eb1b0_0
  • nose=1.3.7=pyhd3eb1b0_1008
  • notebook=6.4.12=py39h06a4308_0
  • nspr=4.33=h295c915_0
  • nss=3.74=h0370c37_0
  • numba=0.55.1=py39h51133e4_0
  • numexpr=2.8.3=py39h807cd23_0
  • numpy=1.21.5=py39h6c91a56_3
  • numpy-base=1.21.5=py39ha15fc14_3
  • numpydoc=1.4.0=py39h06a4308_0
  • olefile=0.46=pyhd3eb1b0_0
  • oniguruma=6.9.7.1=h27cfd23_0
  • openjpeg=2.4.0=h3ad879b_0
  • openpyxl=3.0.10=py39h5eee18b_0
  • openssl=1.1.1q=h7f8727e_0
  • packaging=21.3=pyhd3eb1b0_0
  • pandas=1.4.4=py39h6a678d5_0
  • pandocfilters=1.5.0=pyhd3eb1b0_0
  • panel=0.13.1=py39h06a4308_0
  • pango=1.50.7=h05da053_0
  • param=1.12.0=pyhd3eb1b0_0
  • parsel=1.6.0=py39h06a4308_0
  • parso=0.8.3=pyhd3eb1b0_0
  • partd=1.2.0=pyhd3eb1b0_1
  • patch=2.7.6=h7b6447c_1001
  • patchelf=0.13=h295c915_0
  • pathlib=1.0.1=pyhd3eb1b0_1
  • pathspec=0.9.0=py39h06a4308_0
  • patsy=0.5.2=py39h06a4308_1
  • pcre=8.45=h295c915_0
  • pep8=1.7.1=py39h06a4308_1
  • pexpect=4.8.0=pyhd3eb1b0_3
  • pickleshare=0.7.5=pyhd3eb1b0_1003
  • pillow=9.2.0=py39hace64e9_1
  • pip=22.2.2=py39h06a4308_0
  • pixman=0.40.0=h7f8727e_1
  • pkginfo=1.8.2=pyhd3eb1b0_0
  • platformdirs=2.5.2=py39h06a4308_0
  • plotly=5.9.0=py39h06a4308_0
  • pluggy=1.0.0=py39h06a4308_1
  • ply=3.11=py39h06a4308_0
  • poyo=0.5.0=pyhd3eb1b0_0
  • prometheus_client=0.14.1=py39h06a4308_0
  • prompt-toolkit=3.0.20=pyhd3eb1b0_0
  • prompt_toolkit=3.0.20=hd3eb1b0_0
  • protego=0.1.16=py_0
  • psutil=5.9.0=py39h5eee18b_0
  • ptyprocess=0.7.0=pyhd3eb1b0_2
  • py=1.11.0=pyhd3eb1b0_0
  • py-lief=0.11.5=py39h295c915_1
  • pyasn1=0.4.8=pyhd3eb1b0_0
  • pyasn1-modules=0.2.8=py_0
  • pycodestyle=2.8.0=pyhd3eb1b0_0
  • pycosat=0.6.3=py39h27cfd23_0
  • pycparser=2.21=pyhd3eb1b0_0
  • pyct=0.4.8=py39h06a4308_1
  • pycurl=7.45.1=py39h8f2d780_0
  • pydispatcher=2.0.5=py39h06a4308_2
  • pydocstyle=6.1.1=pyhd3eb1b0_0
  • pyerfa=2.0.0=py39h27cfd23_0
  • pyflakes=2.4.0=pyhd3eb1b0_0
  • pygments=2.11.2=pyhd3eb1b0_0
  • pyhamcrest=2.0.2=pyhd3eb1b0_2
  • pyjwt=2.4.0=py39h06a4308_0
  • pylint=2.14.5=py39h06a4308_0
  • pyls-spyder=0.4.0=pyhd3eb1b0_0
  • pyodbc=4.0.34=py39h6a678d5_0
  • pyopenssl=22.0.0=pyhd3eb1b0_0
  • pyparsing=3.0.9=py39h06a4308_0
  • pyqt=5.15.7=py39h6a678d5_1
  • pyqt5-sip=12.11.0=py39h6a678d5_1
  • pyqtwebengine=5.15.7=py39h6a678d5_1
  • pyrsistent=0.18.0=py39heee7806_0
  • pysocks=1.7.1=py39h06a4308_0
  • pytables=3.6.1=py39h77479fe_1
  • pytest=7.1.2=py39h06a4308_0
  • python=3.9.13=haa1d7c7_1
  • python-dateutil=2.8.2=pyhd3eb1b0_0
  • python-fastjsonschema=2.16.2=py39h06a4308_0
  • python-graphviz=0.20.1=py39h06a4308_0
  • python-libarchive-c=2.9=pyhd3eb1b0_1
  • python-lsp-black=1.2.1=py39h06a4308_0
  • python-lsp-jsonrpc=1.0.0=pyhd3eb1b0_0
  • python-lsp-server=1.5.0=py39h06a4308_0
  • python-slugify=5.0.2=pyhd3eb1b0_0
  • python-snappy=0.6.0=py39h2531618_3
  • python_abi=3.9=2_cp39
  • pytz=2022.1=py39h06a4308_0
  • pyviz_comms=2.0.2=pyhd3eb1b0_0
  • pywavelets=1.3.0=py39h7f8727e_0
  • pyxdg=0.27=pyhd3eb1b0_0
  • pyyaml=6.0=py39h7f8727e_1
  • pyzmq=23.2.0=py39h6a678d5_0
  • qdarkstyle=3.0.2=pyhd3eb1b0_0
  • qstylizer=0.1.10=pyhd3eb1b0_0
  • qt=5.15.9=h06a4308_0
  • qt-main=5.15.2=h327a75a_7
  • qt-webengine=5.15.9=hd2b0992_4
  • qtawesome=1.0.3=pyhd3eb1b0_0
  • qtconsole=5.3.2=py39h06a4308_0
  • qtpy=2.2.0=py39h06a4308_0
  • qtwebkit=5.212=h4eab89a_4
  • queuelib=1.5.0=py39h06a4308_0
  • readline=8.1.2=h7f8727e_1
  • regex=2022.7.9=py39h5eee18b_0
  • requests=2.28.1=py39h06a4308_0
  • requests-file=1.5.1=pyhd3eb1b0_0
  • ripgrep=13.0.0=hbdeaff8_0
  • rope=0.22.0=pyhd3eb1b0_0
  • rtree=0.9.7=py39h06a4308_1
  • ruamel.yaml=0.17.21=py39hb9d737c_1
  • ruamel.yaml.clib=0.2.6=py39h5eee18b_1
  • ruamel_yaml=0.15.100=py39h27cfd23_0
  • s3transfer=0.6.0=py39h06a4308_0
  • scikit-image=0.19.2=py39h51133e4_0
  • scikit-learn=1.0.2=py39h51133e4_1
  • scikit-learn-intelex=2021.6.0=py39h06a4308_0
  • scipy=1.9.1=py39h14f4228_0
  • scrapy=2.6.2=py39h06a4308_0
  • seaborn=0.11.2=pyhd3eb1b0_0
  • secretstorage=3.3.1=py39h06a4308_0
  • send2trash=1.8.0=pyhd3eb1b0_1
  • service_identity=18.1.0=pyhd3eb1b0_1
  • setuptools=63.4.1=py39h06a4308_0
  • sip=6.6.2=py39h6a678d5_0
  • six=1.16.0=pyhd3eb1b0_1
  • smart_open=5.2.1=py39h06a4308_0
  • snappy=1.1.9=h295c915_0
  • sniffio=1.2.0=py39h06a4308_1
  • snowballstemmer=2.2.0=pyhd3eb1b0_0
  • sortedcollections=2.1.0=pyhd3eb1b0_0
  • sortedcontainers=2.4.0=pyhd3eb1b0_0
  • soupsieve=2.3.1=pyhd3eb1b0_0
  • sphinx=5.0.2=py39h06a4308_0
  • sphinxcontrib-applehelp=1.0.2=pyhd3eb1b0_0
  • sphinxcontrib-devhelp=1.0.2=pyhd3eb1b0_0
  • sphinxcontrib-htmlhelp=2.0.0=pyhd3eb1b0_0
  • sphinxcontrib-jsmath=1.0.1=pyhd3eb1b0_0
  • sphinxcontrib-qthelp=1.0.3=pyhd3eb1b0_0
  • sphinxcontrib-serializinghtml=1.1.5=pyhd3eb1b0_0
  • spyder=5.3.3=py39h06a4308_0
  • spyder-kernels=2.3.3=py39h06a4308_0
  • sqlalchemy=1.4.39=py39h5eee18b_0
  • sqlite=3.39.3=h5082296_0
  • statsmodels=0.13.2=py39h7f8727e_0
  • sympy=1.10.1=py39h06a4308_0
  • tabulate=0.8.10=py39h06a4308_0
  • tbb=2021.6.0=hdb19cb5_0
  • tbb4py=2021.6.0=py39hdb19cb5_0
  • tblib=1.7.0=pyhd3eb1b0_0
  • tenacity=8.0.1=py39h06a4308_1
  • terminado=0.13.1=py39h06a4308_0
  • testpath=0.6.0=py39h06a4308_0
  • text-unidecode=1.3=pyhd3eb1b0_0
  • textdistance=4.2.1=pyhd3eb1b0_0
  • threadpoolctl=2.2.0=pyh0d69192_0
  • three-merge=0.1.1=pyhd3eb1b0_0
  • tifffile=2021.7.2=pyhd3eb1b0_2
  • tinycss=0.4=pyhd3eb1b0_1002
  • tk=8.6.12=h1ccaba5_0
  • tldextract=3.2.0=pyhd3eb1b0_0
  • toml=0.10.2=pyhd3eb1b0_0
  • tomli=2.0.1=py39h06a4308_0
  • tomlkit=0.11.1=py39h06a4308_0
  • toolz=0.11.2=pyhd3eb1b0_0
  • tornado=6.1=py39h27cfd23_0
  • tqdm=4.64.1=py39h06a4308_0
  • traitlets=5.1.1=pyhd3eb1b0_0
  • twisted=22.2.0=py39h5eee18b_1
  • typing-extensions=4.3.0=py39h06a4308_0
  • typing_extensions=4.3.0=py39h06a4308_0
  • tzdata=2022c=h04d1e81_0
  • ujson=5.4.0=py39h6a678d5_0
  • unidecode=1.2.0=pyhd3eb1b0_0
  • unixodbc=2.3.11=h5eee18b_0
  • urllib3=1.26.11=py39h06a4308_0
  • w3lib=1.21.0=pyhd3eb1b0_0
  • watchdog=2.1.6=py39h06a4308_0
  • wcwidth=0.2.5=pyhd3eb1b0_0
  • webencodings=0.5.1=py39h06a4308_1
  • websocket-client=0.58.0=py39h06a4308_4
  • werkzeug=2.0.3=pyhd3eb1b0_0
  • wget=1.21.3=h0b77cf5_0
  • whatthepatch=1.0.2=py39h06a4308_0
  • wheel=0.37.1=pyhd3eb1b0_0
  • widgetsnbextension=3.5.2=py39h06a4308_0
  • wrapt=1.14.1=py39h5eee18b_0
  • wurlitzer=3.0.2=py39h06a4308_0
  • xarray=0.20.1=pyhd3eb1b0_1
  • xlrd=2.0.1=pyhd3eb1b0_0
  • xlsxwriter=3.0.3=pyhd3eb1b0_0
  • xz=5.2.6=h5eee18b_0
  • yaml=0.2.5=h7b6447c_0
  • yapf=0.31.0=pyhd3eb1b0_0
  • zeromq=4.3.4=h2531618_0
  • zfp=0.5.5=h295c915_6
  • zict=2.1.0=py39h06a4308_0
  • zipp=3.8.0=py39h06a4308_0
  • zlib=1.2.12=h5eee18b_3
  • zope=1.0=py39h06a4308_1
  • zope.interface=5.4.0=py39h7f8727e_0
  • zstd=1.5.2=ha4553b6_0
  • pip:
    • absl-py==1.4.0
    • addict==2.4.0
    • astunparse==1.6.3
    • cachetools==5.2.1
    • cupy-cuda11x==11.4.0
    • docker-pycreds==0.4.0
    • fastrlock==0.8.1
    • flatbuffers==23.1.4
    • gast==0.4.0
    • gitdb==4.0.10
    • gitpython==3.1.30
    • google-auth==2.16.0
    • google-auth-oauthlib==0.4.6
    • google-pasta==0.2.0
    • grpcio==1.51.1
    • keras==2.11.0
    • libclang==15.0.6.1
    • mmcv==1.7.1
    • nvidia-cublas-cu11==11.10.3.66
    • nvidia-cuda-nvrtc-cu11==11.7.99
    • nvidia-cuda-runtime-cu11==11.7.99
    • nvidia-cudnn-cu11==8.5.0.96
    • oauthlib==3.2.2
    • opencv-python==4.7.0.68
    • opt-einsum==3.3.0
    • pathtools==0.1.2
    • protobuf==3.19.6
    • pytorch-model-summary==0.1.2
    • requests-oauthlib==1.3.1
    • rfa-toolbox==1.7.0
    • rsa==4.9
    • sentry-sdk==1.13.0
    • setproctitle==1.3.2
    • smmap==5.0.0
    • template==0.7.6
    • tensorboard==2.11.2
    • tensorboard-data-server==0.6.1
    • tensorboard-plugin-wit==1.8.1
    • tensorflow==2.11.0
    • tensorflow-estimator==2.11.0
    • tensorflow-io-gcs-filesystem==0.29.0
    • tensorrt==8.5.2.2
    • termcolor==2.2.0
    • thop==0.1.1-2209072238
    • torch==1.13.1
    • torchsummary==1.5.1
    • torchvision==0.14.1
    • typing==3.7.4.3
    • wandb==0.13.9 prefix: /home/dobby/anaconda3

Jochiwon avatar Mar 28 '23 08:03 Jochiwon

Hi. Thank you for reaching out, and thank you for your patience. The feature map resolution is not directly read from the tracing tensor and therefore does not change correctly, upsampling in general is currently not adequately accounted for in the current setup of RFA.

Regarding the remaining code: First, thank you for sharing your changes. This contribution looks valuable to the codebase. I would like to integrate these changes in the next couple of weeks, and test it to see if it breaks other assumptions when ingesting the architecture. Alternatively, you can open a pull request with these changes and I will review it.

MLRichter avatar Apr 03 '23 16:04 MLRichter