Activations from All-CNN-C and All-CNN-7 in response to the CIFAR-10 stimuli are saved using the script extract_rdms_and_activations_incl_softmax_32_32_input_All_CNN_C.py or extract_rdms_and_activations_incl_softmax_32_32_input_All_CNN_7.py in a conda environment with the following packages loaded: - astroid 1.5.3 py35_0 - awscli 1.16.266 <pip> - bleach 1.5.0 <pip> - botocore 1.13.2 <pip> - cffi 1.10.0 py35_0 - cudatoolkit 8.0 3 - cudnn 6.0.21 cuda8.0_0 - cycler 0.10.0 py35_0 - dbus 1.10.20 0 - decorator 4.1.2 py35_0 - expat 2.1.0 0 - fontconfig 2.12.1 3 - freetype 2.5.5 2 - future 0.16.0 <pip> - glib 2.50.2 1 - gst-plugins-base 1.8.0 0 - gstreamer 1.8.0 0 - hdf5 1.8.17 2 - html5lib 0.9999999 <pip> - icu 54.1 0 - imgaug 0.2.6 <pip> - ipython 6.2.1 <pip> - isort 4.2.15 py35_0 - jbig 2.1 0 - jinja2 2.9.6 <pip> - jmespath 0.9.4 <pip> - jpeg 8d 2 - jsonschema 2.6.0 <pip> - jupyter-client 5.1.0 <pip> - jupyter-console 5.2.0 <pip> - jupyter-core 4.3.0 <pip> - lazy-object-proxy 1.3.1 py35_0 - libffi 3.2.1 1 - libgcc 5.2.0 0 - libgfortran 3.0.0 1 - libiconv 1.14 0 - libpng 1.6.30 1 - libtiff 4.0.6 2 - libtorch 0.1.12 nomkl_0 [nomkl] - libxcb 1.12 1 - libxml2 2.9.4 0 - markdown 2.6.11 <pip> - matplotlib 2.0.2 np112py35_0 - mmdnn 0.2.2 <pip> - nbconvert 5.3.1 <pip> - nbformat 4.4.0 <pip> - nccl 1.3.4 cuda8.0_1 - networkx 1.11 py35_0 - nipype 0.13.1 <pip> - nomkl 1.0 0 - notebook 5.1.0 <pip> - numexpr 2.6.2 np112py35_nomkl_0 [nomkl] - numpy 1.12.1 py35_nomkl_0 [nomkl] - olefile 0.44 py35_0 - openblas 0.2.19 0 - opencv 3.1.0 np112py35_1 - openssl 1.0.2j 0 - pandas 0.23.4 <pip> - pbr 3.1.1 <pip> - pcre 8.39 1 - piexif 1.0.13 <pip> - pillow 3.4.2 py35_0 - pip 9.0.1 py35_1 - pip-autoremove 0.9.0 <pip> - progressbar2 3.18.1 py35_0 - protobuf 3.5.1 <pip> - py 1.4.34 py35_0 - pycparser 2.18 py35_0 - pygments 2.2.0 <pip> - pylint 1.7.2 py35_0 - pyparsing 2.2.0 py35_0 - pyqt 5.6.0 py35_2 - pytest 3.2.1 py35_0 - pytest-runner 2.11.1 py35_0 - python 3.5.4 0 - python-dateutil 2.6.1 py35_0 - python-utils 2.2.0 py35_0 - pytorch 0.1.12 py35_nomkl_0 [nomkl] - pytz 2017.2 py35_0 - pywavelets 0.5.2 np112py35_0 - qt 5.6.2 2 - qtconsole 4.3.1 <pip> - rdflib 4.2.2 <pip> - readline 6.2 2 - s3transfer 0.2.1 <pip> - scikit-image 0.13.0 np112py35_0 - scikit-learn 0.19.0 np112py35_nomkl_0 [nomkl] - scipy 0.19.1 np112py35_nomkl_0 [nomkl] - setuptools 27.2.0 py35_0 - singledispatch 3.4.0.3 py35_0 - sip 4.18 py35_0 - six 1.10.0 py35_0 - sqlite 3.13.0 0 - tensorflow 0.10.0 <pip> - tensorflow-gpu 1.3.0 <pip> - tensorflow-tensorboard 0.1.8 <pip> - tk 8.5.18 0 - torch 0.1.12 <pip> - torchvision 0.1.8 py35_0 - urllib3 1.25.6 <pip> - werkzeug 0.14.1 <pip> - wheel 0.29.0 py35_0 - wrapt 1.10.11 py35_0 - xz 5.2.2 0 - zlib 1.2.8 3 - Activations from AlexNet in response to the CIFAR-10 stimuli are saved using the script extract_activations_wout_softmax.py (located in the folder of the respective DNN instance) in a conda environment with the following packages loaded: - Absl-py 0.6.1 - Astor 0.7.1 - Certifi 2016.2.28 - Cycler 0.10.0 - Gast 0.2.0 - Grpcio 1.16.0 - H5py 2.9.0 - Joblib 0.12.5 - Kiwisolver 1.1.0 - Markdown 3.0.1 - Matplotlib 3.1.2 - Numpy 1.14.5 - openssl 1.0.2l - Pillow 5.3.0 - Pip 9.0.1 - Progressbar2 3.38.0 - Protobuf 3.6.1 - Pyparsing 2.4.5 - Python 3.6.2 - Python-dateutil 2.8.1 - Python-utils 2.3.0 - Readline 6.2 - Scipy 1.1.0 - Setuptools 36.4.0 - Six 1.11.0 - Sqlite 3.13.0 - Tensorboard 1.10.0 - Tensorflow-gpu 1.10.0 - Termcolor 1.1.0 - tk 8.5.18 - Werkzeug 0.14.1 - Wheel 0.29.0 - Xz 5.2.3 - Zlib 1.2.11