（转）mask rcnn测试中遇到的问题解决

（转）mask rcnn测试中遇到的问题解决

代码下载:

问题一:

出错代码行:

model.load_weights(weights_path, by_name=True)

错误显示:

Traceback (most recent call last):File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/samples/cancer/inspect_weights.py", line 76, in <module>model.load_weights(weights_path, by_name=True)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/mrcnn/model.py", line 2143, in load_weightssaving.load_weights_from_hdf5_group_by_name(f, layers)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/engine/saving.py", line 1149, in load_weights_from_hdf5_group_by_namestr(weight_values[i].shape) + '.')
ValueError: Layer #389 (named "mrcnn_bbox_fc"), weight <tf.Variable 'mrcnn_bbox_fc/kernel:0' shape=(1024, 8) dtype=float32_ref> has shape (1024, 8), but the saved weight has shape (1024, 324).

解决:

如果你不想测试coco里默认的81类，只想测试2类，那一定记住要把model.load_weights(COCO_MODEL_PATH, by_name=True)改为model.load_weights(COCO_MODEL_PATH, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc","mrcnn_bbox", "mrcnn_mask"])
参考博客： 

问题二:

出错代码:train_mask.py

错误显示:
 

2019-01-05 20:01:15.518461: W tensorflow/core/framework/op_kernel:1273] OP_REQUIRES failed at conv_ops:446 : Resource exhausted: OOM when allocating tensor with shape[1,512,512,64] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
Traceback (most recent call last):File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/samples/cancer/train_mask.py", line 109, in <module&ain(dataset_train, dataset_val, learning_rate=config.LEARNING_RATE, epochs=50, layers="all")File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/mrcnn/model.py", line 2387, in trainuse_multiprocessing=True, #改为单线程File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapperreturn func(*args, **kwargs)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/engine/training.py", line 1418, in fit_generatorinitial_epoch=initial_epoch)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/engine/training_generator.py", line 217, in fit_generatorclass_weight=class_weight)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/engine/training.py", line 1217, in train_on_batchoutputs = ain_function(ins)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2715, in __call__return self._call(inputs)File "/home/qln/workspace/Mask R-CNN/Mask_Rcnn-matterport/runutil/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2675, in _callfetched = self._callable_fn(*array_vals)File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1439, in __call__run_metadata_ptr)File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__c_api.TF_GetCode(self.status.status))
tensorflow.s_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1,512,512,64] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu[[{{node conv1/convolution}} = Conv2D[T=DT_FLOAT, _class=["loc:@training/SGD/gradients/conv1/convolution_grad/Conv2DBackpropFilter"], data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](zero_padding2d_1/Pad, conv1/kernel/read)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.Process finished with exit code 130 (interrupted by signal 2: SIGINT)

解决:

遇到这个问题大家不要慌，这是因为大家设置了多线程，但是线程不同步造成的。大家耐心等一会，就会出现loss了。同时如果大家不希望出现多线程，大家可以改为单线程。更改方法如下：在Mask RCNNmrcnnmodel.py中

 self.keras_model.fit_generator(train_generator,initial_epoch=self.epoch,epochs=epochs,steps_per_epoch&#fig.STEPS_PER_EPOCH,callbacks=callbacks,validation_data=val_generator,validation_steps&#fig.VALIDATION_STEPS,max_queue_size=100,workers=workers,use_multiprocessing=True,
#            use_multiprocessing=False,)

大家如果只是想要把多线程改为单线程，就要把use_multiprocessing=False,同时要让workers=1。因为单线程的情况下让workers大于1会报错！

问题三:

打开tensorboard出错,可以打开,但是没有任何数据显示

错误显示:Tensorboard网址出现No dashboards are active for the current data set

问题解决: tensorboard --logdir的路径出现问题,只需要标记到logs即可,而且路径不可以出现空格
 

tensorboard --logdir /home/qln/workspace/Mask_R-CNN/cancer/logs
TensorBoard 1.12.0 at qln:6006 (Press CTRL+C to quit)

得到完美解决.