Tencent / PocketFlow

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
https://pocketflow.github.io
Other
2.79k stars 490 forks source link

Download Pretrain Model But Get 502 Bad Gateway Error #313

Closed A1exy closed 5 years ago

A1exy commented 5 years ago

Use official code to Uniform Quantization, But Get 502 Bad Gateway Error.

Quantized: model/resnet_model/Relu_18/uniform_quantize --2019-09-19 16:08:10-- https://api.ai.tencent.com/pocketflow/models_resnet_20_at_cifar_10.tar.gz Resolving api.ai.tencent.com (api.ai.tencent.com)... 61.151.164.80 Connecting to api.ai.tencent.com (api.ai.tencent.com)|61.151.164.80|:443... connected. HTTP request sent, awaiting response... 502 Bad Gateway 2019-09-19 16:08:10 ERROR 502: Bad Gateway.

Traceback (most recent call last): File "main.py", line 69, in tf.app.run() File "/home/hpc/anaconda3/envs/ccx_PF/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "main.py", line 51, in main learner = create_learner(sm_writer, model_helper) File "/home/hpc/ccx/code/Model_Compress/PocketFlow/learners/learner_utils.py", line 62, in create_learner learner = NonUniformQuantLearner(sm_writer, model_helper) File "/home/hpc/ccx/code/Model_Compress/PocketFlow/learners/nonuniform_quantization/learner.py", line 99, in init self.download_model() File "/home/hpc/ccx/code/Model_Compress/PocketFlow/learners/abstract_learner.py", line 125, in download_model 'pre-trained model not avaialable: {} / {}'.format(self.model_name, self.dataset_name)) FileNotFoundError: pre-trained model not avaialable: resnet_20 / cifar_10

A1exy commented 5 years ago

https://github.com/Tencent/PocketFlow/issues/293#issuecomment-533936975