[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-336626078 OK, I have done it , would you review it? I verified num_layer=161 can work by running some steps. @szha This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-336626078 OK, I have done it , would you check it? I verified num_layer=161 can work by running some steps. @szha This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-332397878 Is it required to upload pretrained weight then to accept my PR?, because the pretrained weight is about 62M, which is restricted to upload in my company, and on the other hand, I had no PC with GPUs of my own. @piiswrong This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331762726 This implementation is consistent with the paper. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331762726 I think this one is more consistent with paper This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331686274 The training of 169-layers is done, result as below: INFO:root:Epoch[124] Batch [2450] Speed: 107.01 samples/sec accuracy=0.904687 cross-entropy=0.365293 top_k_accuracy_5=0.984219 INFO:root:Epoch[124] Batch [2300] Speed: 106.73 samples/sec accuracy=0.902656 cross-entropy=0.367414 top_k_accuracy_5=0.985313 INFO:root:Epoch[124] Batch [2100] Speed: 106.68 samples/sec accuracy=0.897656 cross-entropy=0.385241 top_k_accuracy_5=0.983594 INFO:root:Epoch[124] Batch [2500] Speed: 106.51 samples/sec accuracy=0.903438 cross-entropy=0.372258 top_k_accuracy_5=0.984219 INFO:root:Epoch[124] Train-accuracy=0.906250 INFO:root:Epoch[124] Train-cross-entropy=0.400677 INFO:root:Epoch[124] Train-top_k_accuracy_5=0.980469 INFO:root:Epoch[124] Time cost=3106.063 INFO:root:Saved checkpoint to "densenet-models/densenet-0125.params" INFO:root:Epoch[124] Validation-accuracy=0.741744 INFO:root:Epoch[124] Validation-cross-entropy=1.160414 INFO:root:Epoch[124] Validation-top_k_accuracy_5=0.911830 I think the model is consistent with the gluon implementation, with little different such as BatchNorm layer, but it seems did not affect the result. This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331686274 The training of 169-layers is done, result as below: INFO:root:Epoch[124] Batch [2450] Speed: 107.01 samples/sec accuracy=0.904687 cross-entropy=0.365293 top_k_accuracy_5=0.984219 INFO:root:Epoch[124] Batch [2300] Speed: 106.73 samples/sec accuracy=0.902656 cross-entropy=0.367414 top_k_accuracy_5=0.985313 INFO:root:Epoch[124] Batch [2100] Speed: 106.68 samples/sec accuracy=0.897656 cross-entropy=0.385241 top_k_accuracy_5=0.983594 INFO:root:Epoch[124] Batch [2500] Speed: 106.51 samples/sec accuracy=0.903438 cross-entropy=0.372258 top_k_accuracy_5=0.984219 INFO:root:Epoch[124] Train-accuracy=0.906250 INFO:root:Epoch[124] Train-cross-entropy=0.400677 INFO:root:Epoch[124] Train-top_k_accuracy_5=0.980469 INFO:root:Epoch[124] Time cost=3106.063 INFO:root:Saved checkpoint to "densenet-models/densenet-0125.params" INFO:root:Epoch[124] Validation-accuracy=0.741744 INFO:root:Epoch[124] Validation-cross-entropy=1.160414 INFO:root:Epoch[124] Validation-top_k_accuracy_5=0.911830 I think the model is consistent with the gluon implementation, with little different such as BatchNorm layer, but it seems did not affect the result. @piiswrong This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331020772 Ok,I will learn to use gluon, The training of densenet is really slow, the validation of top-1 is above 71% now(169 layers) INFO:root:Epoch[42] Train-accuracy=0.796875 INFO:root:Epoch[42] Train-cross-entropy=0.746801 INFO:root:Epoch[42] Train-top_k_accuracy_5=0.955078 INFO:root:Epoch[42] Time cost=3112.315 INFO:root:Epoch[42] Validation-accuracy=0.710615 INFO:root:Epoch[42] Validation-cross-entropy=1.197285 INFO:root:Epoch[42] Validation-top_k_accuracy_5=0.902948 This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331020772 Ok,I will learn to use gluon, The training of densenet is really slow, the validation of top-1 is above 71% now(169 layers) INFO:root:Epoch[42] Train-accuracy=0.796875 INFO:root:Epoch[42] Train-cross-entropy=0.746801 INFO:root:Epoch[42] Train-top_k_accuracy_5=0.955078 INFO:root:Epoch[42] Time cost=3112.315 INFO:root:Epoch[42] Validation-accuracy=0.710615 INFO:root:Epoch[42] Validation-cross-entropy=1.197285 INFO:root:Epoch[42] Validation-top_k_accuracy_5=0.902948 This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-331020772 Ok,I will learn to use gluon, The training of densenet is really slow, the validation of top-1 is above 71% now(169 layers) INFO:root:Epoch[42] Train-accuracy=0.796875 INFO:root:Epoch[42] Train-cross-entropy=0.746801 INFO:root:Epoch[42] Train-top_k_accuracy_5=0.955078 INFO:root:Epoch[42] Time cost=3112.315 INFO:root:Saved checkpoint to "densenet-models/densenet-2-0043.params" INFO:root:Epoch[42] Validation-accuracy=0.710615 INFO:root:Epoch[42] Validation-cross-entropy=1.197285 INFO:root:Epoch[42] Validation-top_k_accuracy_5=0.902948 This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-330733686 do you suggest me to close this PR? @szha This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
[GitHub] qingzhouzhen commented on issue #7957: add densenet
qingzhouzhen commented on issue #7957: add densenet URL: https://github.com/apache/incubator-mxnet/pull/7957#issuecomment-330733686 do you suggest me to close this PR? This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services