I used this as my starting point: https://github.com/Dhar/image-dreamer

My base picture is one I took from a plane out of Queenstown (munged version here), resized to 400px wide, and run through the layers as follows:

conv1/7x7_s2 |

pool1/3x3_s2 |

pool1/norm1 |

conv2/3x3_reduce |

conv2/3x3 |

conv2/norm2 |

pool2/3x3_s2 |

inception_3a/1x1 |

inception_3a/3x3_reduce |

inception_3a/3x3 |

inception_3a/5x5_reduce |

inception_3a/5x5 |

inception_3a/pool |

inception_3a/pool_proj |

inception_3a/output |

inception_3b/1x1 |

inception_3b/3x3_reduce |

inception_3b/3x3 |

inception_3b/5x5_reduce |

inception_3b/5x5 |

inception_3b/pool |

inception_3b/pool_proj |

inception_3b/output |

pool3/3x3_s2 |

inception_4a/1x1 |

inception_4a/3x3_reduce |

inception_4a/3x3 |

inception_4a/5x5_reduce |

inception_4a/5x5 |

inception_4a/pool |

inception_4a/pool_proj |

inception_4a/output |

inception_4b/1x1 |

inception_4b/3x3_reduce |

inception_4b/3x3 |

inception_4b/5x5_reduce |

inception_4b/5x5 |

inception_4b/pool |

inception_4b/pool_proj |

inception_4b/output |

inception_4c/1x1 |

inception_4c/3x3_reduce |

inception_4c/3x3 |

inception_4c/5x5_reduce |

inception_4c/5x5 |

inception_4c/pool |

inception_4c/pool_proj |

inception_4c/output |

inception_4d/1x1 |

inception_4d/3x3_reduce |

inception_4d/3x3 |

inception_4d/5x5_reduce |

inception_4d/5x5 |

inception_4d/pool |

inception_4d/pool_proj |

inception_4d/output |

inception_4e/1x1 |

inception_4e/3x3_reduce |

inception_4e/3x3 |

inception_4e/5x5_reduce |

inception_4e/5x5 |

inception_4e/pool |

inception_4e/pool_proj |

inception_4e/output |

pool4/3x3_s2 |

inception_5a/1x1 |

inception_5a/3x3_reduce |

inception_5a/3x3 |

inception_5a/5x5_reduce |

inception_5a/5x5 |

inception_5a/pool |

inception_5a/pool_proj |

inception_5a/output |

inception_5b/1x1 |

inception_5b/3x3_reduce |

inception_5b/3x3 |

inception_5b/5x5_reduce |

inception_5b/5x5 |

inception_5b/pool |

inception_5b/pool_proj |

inception_5b/output |

is there an easy way to reference the layers? i want to be able to call each one in turn, but can't figure out how to reference them. net.blobs[n] doesn't work.

ReplyDeleteI want to use different layers than what the

ReplyDeletedefault is. Its defaulting me to Inception 4c.

How would I go about changing to a different

layer?

"conv1/7x7_s2" "pool1/3x3_s2" "pool1/norm1"

"conv2/3x3_reduce" "conv2/3x3" "conv2/norm2"

"pool2/3x3_s2" "inception_3a/1x1"

"inception_3a/3x3_reduce" "inception_3a/3x3"

"inception_3a/5x5_reduce" "inception_3a/5x5"

"inception_3a/pool" "inception_3a/pool_proj"

"inception_3a/output" "inception_3b/1x1"

"inception_3b/3x3_reduce" "inception_3b/3x3"

"inception_3b/5x5_reduce" "inception_3b/5x5"

"inception_3b/pool" "inception_3b/pool_proj"

"inception_3b/output" "pool3/3x3_s2"

"inception_4a/1x1" "inception_4a/3x3_reduce"

"inception_4a/3x3" "inception_4a/5x5_reduce"

"inception_4a/5x5" "inception_4a/pool"

"inception_4a/pool_proj" "inception_4a/output"

"inception_4b/1x1" "inception_4b/3x3_reduce"

"inception_4b/3x3" "inception_4b/5x5_reduce"

"inception_4b/5x5" "inception_4b/pool"

"inception_4b/pool_proj" "inception_4b/output"

"inception_4c/1x1" "inception_4c/3x3_reduce"

"inception_4c/3x3" "inception_4c/5x5_reduce"

"inception_4c/5x5" "inception_4c/pool"

"inception_4c/pool_proj" "inception_4c/output"

"inception_4d/1x1" "inception_4d/3x3_reduce"

"inception_4d/3x3" "inception_4d/5x5_reduce"

"inception_4d/5x5" "inception_4d/pool"

"inception_4d/pool_proj" "inception_4d/output"

"inception_4e/1x1" "inception_4e/3x3_reduce"

"inception_4e/3x3" "inception_4e/5x5_reduce"

"inception_4e/5x5" "inception_4e/pool"

"inception_4e/pool_proj" "inception_4e/output"

"pool4/3x3_s2" "inception_5a/1x1"

"inception_5a/3x3_reduce" "inception_5a/3x3"

"inception_5a/5x5_reduce" "inception_5a/5x5"

"inception_5a/pool" "inception_5a/pool_proj"

"inception_5a/output" "inception_5b/1x1"

"inception_5b/3x3_reduce" "inception_5b/3x3"

"inception_5b/5x5_reduce" "inception_5b/5x5"

"inception_5b/pool" "inception_5b/pool_proj"

"inception_5b/output" "pool5/7x7_s1"

"pool5/drop_7x7_s1" "loss3/classifier" "prob"

pop one of those in place of

"inception_4c/output"

in dreamify.py

I want to use different layers than what the

ReplyDeletedefault is. Its defaulting me to Inception 4c.

How would I go about changing to a different

layer?

"conv1/7x7_s2" "pool1/3x3_s2" "pool1/norm1"

"conv2/3x3_reduce" "conv2/3x3" "conv2/norm2"

"pool2/3x3_s2" "inception_3a/1x1"

"inception_3a/3x3_reduce" "inception_3a/3x3"

"inception_3a/5x5_reduce" "inception_3a/5x5"

"inception_3a/pool" "inception_3a/pool_proj"

"inception_3a/output" "inception_3b/1x1"

"inception_3b/3x3_reduce" "inception_3b/3x3"

"inception_3b/5x5_reduce" "inception_3b/5x5"

"inception_3b/pool" "inception_3b/pool_proj"

"inception_3b/output" "pool3/3x3_s2"

"inception_4a/1x1" "inception_4a/3x3_reduce"

"inception_4a/3x3" "inception_4a/5x5_reduce"

"inception_4a/5x5" "inception_4a/pool"

"inception_4a/pool_proj" "inception_4a/output"

"inception_4b/1x1" "inception_4b/3x3_reduce"

"inception_4b/3x3" "inception_4b/5x5_reduce"

"inception_4b/5x5" "inception_4b/pool"

"inception_4b/pool_proj" "inception_4b/output"

"inception_4c/1x1" "inception_4c/3x3_reduce"

"inception_4c/3x3" "inception_4c/5x5_reduce"

"inception_4c/5x5" "inception_4c/pool"

"inception_4c/pool_proj" "inception_4c/output"

"inception_4d/1x1" "inception_4d/3x3_reduce"

"inception_4d/3x3" "inception_4d/5x5_reduce"

"inception_4d/5x5" "inception_4d/pool"

"inception_4d/pool_proj" "inception_4d/output"

"inception_4e/1x1" "inception_4e/3x3_reduce"

"inception_4e/3x3" "inception_4e/5x5_reduce"

"inception_4e/5x5" "inception_4e/pool"

"inception_4e/pool_proj" "inception_4e/output"

"pool4/3x3_s2" "inception_5a/1x1"

"inception_5a/3x3_reduce" "inception_5a/3x3"

"inception_5a/5x5_reduce" "inception_5a/5x5"

"inception_5a/pool" "inception_5a/pool_proj"

"inception_5a/output" "inception_5b/1x1"

"inception_5b/3x3_reduce" "inception_5b/3x3"

"inception_5b/5x5_reduce" "inception_5b/5x5"

"inception_5b/pool" "inception_5b/pool_proj"

"inception_5b/output" "pool5/7x7_s1"

"pool5/drop_7x7_s1" "loss3/classifier" "prob"

pop one of those in place of

"inception_4c/output"

in dreamify.py

Best Digital Marketing agency in Dubai We are in an ‘ always on ‘ world. Connecting, sharing, collaborating. We, at ISD Global, help brands digitell the digital while distinguishing the distinguished and distilling the brand essence. ISD Global can evaluate the strength of your brand through a brand audit. The –––audit can be initiated before embarking on a Brand Engineering exercise or at any time that you want to establish your brand’s power/equity in the marketplace. The brand identity reflects stakeholder vision, the brand positioning and resonates with the brand’s core values.

ReplyDelete