Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Azureで試して学ぶAI CAR自動走行の仕組みハンズオン

masato-ka
August 08, 2020

Azureで試して学ぶAI CAR自動走行の仕組みハンズオン

masato-ka

August 08, 2020
Tweet

More Decks by masato-ka

Other Decks in Technology

Transcript

  1. ԋश1. શ݁߹૚ͷΈʹΑΔࣗಈ૸ߦ Input (5) Dense 16 ReLu Dense 16 ReLu

    output(2) •Optimizer: Adam - lr: 0.001 - Decay: 0.0 •Loss: MSE
  2. جຊͷશ݁߹૚ ઢܗɾඇઢܗͷม׵Λ܁Γฦ͠೚ҙͷؔ਺Λදݱ w11 i1 i2 i3 w21 w31 w12 w22

    w32 w13 W23 W33 o1 o2 o3 a1 a2 a3 activation(o1)=a1 activation(o2)=a2 activation(o3)=a3 ReLu ଟ૚ߏ଄ʹ͢Δ͜ͱͰ೚ҙͷؔ਺Λදݱ ֶशͰ͸8ͷ஋Λௐ੔͢Δ [i1 i2 i3] w11 w12 w13 w21 w22 w23 w31 w32 w33 + b = [o1 o2 o3] iW + b = o O i
  3. ԋश̎. CNNʹΑΔࣗಈ૸ߦ Input 120x160x3 kernel(5,5), 24, Stride(2,2), Relu kernel(5,5), 32,

    Stride(2,2), Relu kernel(5,5), 64, Stride(2,2), Relu kernel(3,3), 64, Stride(1,1), Relu kernel(3,3), 64, Stride(1,1), Relu Dense 100, Relu Dense 50, Relu Flatten output(2) •Optimizer: Adam - lr: 0.001 - Decay: 0.0 •Loss: MSE ૝ఆೖྗը૾(120x160x3) {"cam/image_array": “2584_cam-image_array_.jpg", "user/angle": 1.0, "user/throttle": 0.5, "user/mode": "user", "milliseconds": 272202} ڭࢣϥϕϧ
  4. ը૾ͷಛ௃Λநग़͢Δ৞ΈࠐΈ૚ Կ૚ʹ΋܁Γฦ͠ίʔεͷಛ௃Λֶश͢Δ 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5

    0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ϑΟϧλ஋ͱ֤ըૉͷੵΛ଍͜͠Ή .BY1PPMJOH૚ ֶशͰ͸ϑΟϧλͷॏΈΛௐ੔͢Δ
  5. ৞ΈࠐΈ૚ͷύϥϝʔλͷߟ͑ํ ύϥϝʔλΛௐ੔͢Δ͜ͱͰग़ྗͷαΠζΛௐ੔ W W W W W W W W

    W W W W W W W W W W W W W W W W W W W ೖྗ24x24x3(RGB) ϑΟϧλαΠζ3x3x2 W W W W W W W W W W W W W W W W W W W W W W W W W W W Stride:(1,1) ϑΟϧλΛಈ͔͢෯ (24)x(24)x2=1152 ࢀߟ:https://www.hellocybernetics.tech/entry/2016/12/23/000557 Isize + 2P − Fsize Stride + 1 = Output Padding:(1,1) ग़ྗը૾ͷपΓΛຒΊΔ 22 1 1 1 1 W W W W W W W W W Stride(1,1) ը૾ͷ୺·Ͱ 24-3+1=22
  6. Keras.layers.Conv2D layers.Conv2D(32, (5,5), strides =(2,2), activation="relu", name="conv2d_2"), layers.Conv2D(24, (5,5), strides

    =(2,2), input_shape=(120, 160, 3), activation="relu", name="conv2d_1"), https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D ϑΟϧλຕ਺ ϑΟϧλαΠζ ೖྗ਺ը૾αΠζ ετϥΠυ
  7. ࣮͸/7*%*"ͷ࿦จͱ΄΅ಉ࣮͡૷ BOJARSKI, M., DEL TESTA, D., DWORAKOWSKI, D., FIRNER, B.,

    FLEPP, B., GOYAL, P., JACKEL, L. D., MONFORT, M., MULLER, U., ZHANG, J., ET AL. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016) Dense 100, Relu Dense 50, Relu Flatten output(2)
  8. /7*%*"ͷ࿦จʹཱͪ໭ͬͯΈ·͠ΐ͏ BOJARSKI, M., DEL TESTA, D., DWORAKOWSKI, D., FIRNER, B.,

    FLEPP, B., GOYAL, P., JACKEL, L. D., MONFORT, M., MULLER, U., ZHANG, J., ET AL. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016) ೖྗը૾ ̑૚ͷ৞ΈࠐΈ૚ Ͱಛ௃நग़ ̐૚ͷશ݁߹૚Ͱਓ ͷૢ࡞ϧʔϧΛ໛฿ 1࣍ݩ഑ྻʹม׵
  9. • શ݁߹૚ͱCNN • సҠֶश(෺ମݕग़ͳͲʣ • ϞσϧͷѹॖɺTensorFlow Lite, TensorFlow Lite for

    microcontroller • Edge TPUͱ͍ͬͨσΟʔϓϥʔχϯάΞΫηϥϨʔλɺϞόΠϧσόΠεͰͷਪ࿦ • PytorchͳͲͷผͷFW • RNN΍LSTM, Transformer • AutoEncoder • GAN AI؆୯ͩͳͱࢥͬͨΒઌʹਐ΋͏ ࠓ೔ཧղͨ͜͠ͱ͸શମ͔ΒݟͨΒ͘͝Ұ෦Ͱ͢