DataLossError (see above for traceback): Unable to open table file ./yolo_v3/data/darknet_weights/best_model_Epoch_110_step_80474_mAP_0.8524_loss_3.0749_lr_1e-05.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
只需要把:
best_model_Epoch_110_step_80474_mAP_0.8524_loss_3.0749_lr_1e-05.data-00000-of-00001
修改成:
best_model_Epoch_110_step_80474_mAP_0.8524_loss_3.0749_lr_1e-05
即可
/gpfsssd/anacondas/ana1/anaconda/envs/env2/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
2019-09-14 16:48:26.222657: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-09-14 16:48:26.502683: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1405] Found device 0 with properties:
name: Tesla P40 major: 6 minor: 1 memoryClockRate(GHz): 1.531
pciBusID: 0000:2d:00.0
totalMemory: 22.38GiB freeMemory: 22.22GiB
2019-09-14 16:48:26.502740: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1484] Adding visible gpu devices: 0
2019-09-14 16:48:26.998045: I tensorflow/core/common_runtime/gpu/gpu_device.cc:965] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-09-14 16:48:26.998116: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0
2019-09-14 16:48:26.998131: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] 0: N
2019-09-14 16:48:26.998889: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1097] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 21553 MB memory) -> physical GPU (device: 0, name: Tesla P40, pci bus id: 0000:2d:00.0, compute capability: 6.1)
2019-09-14 16:48:32.954156: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open ./yolo_v3/data/darknet_weights/best_model_Epoch_92_step_84443_mAP_0.9989_loss_0.2836_lr_1e-05.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
2019-09-14 16:48:32.954987: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open ./yolo_v3/data/darknet_weights/best_model_Epoch_92_step_84443_mAP_0.9989_loss_0.2836_lr_1e-05.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
2019-09-14 16:48:32.955026: W tensorflow/core/framework/op_kernel.cc:1275] OP_REQUIRES failed at save_restore_tensor.cc:170 : Data loss: Unable to open tablefile ./yolo_v3/data/darknet_weights/best_model_Epoch_92_step_84443_mAP_0.9989_loss_0.2836_lr_1e-05.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
Traceback (most recent call last):
File "/gpfsssd/anacondas/ana1/anaconda/envs/env2/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1278, in _do_call
return fn(*args)
File "/gpfsssd/anacondas/ana1/anaconda/envs/env2/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1263, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "/gpfsssd/anacondas/ana1/anaconda/envs/env2/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1350, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.DataLossError: Unable to open