Issues running masks.py and run.sh: 'tensorflow' has no attribute 'log' + No module named 'neuralgym' #1
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
Hi @kristijanbartol, many thanks for the nice Deep-Eraser project! Just gave it a spin with docker and get these errors. It there an easy way to fix the docker image? Would really love to try it out! :) Any advice?
python3 masks.py
$ python3 masks.py ../images/1045023827_4ec3e8ba5c_z.jpg Using TensorFlow backend. Configurations: BACKBONE resnet101 BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] COMPUTE_BACKBONE_SHAPE None DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.7 DETECTION_NMS_THRESHOLD 0.3 FPN_CLASSIF_FC_LAYERS_SIZE 1024 GPU_COUNT 1 GRADIENT_CLIP_NORM 5.0 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 1024 IMAGE_META_SIZE 93 IMAGE_MIN_DIM 800 IMAGE_MIN_SCALE 0 IMAGE_RESIZE_MODE square IMAGE_SHAPE [1024 1024 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME coco NUM_CLASSES 81 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (32, 64, 128, 256, 512) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TOP_DOWN_PYRAMID_SIZE 256 TRAIN_BN False TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 2019-11-05 15:15:04.839734: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2019-11-05 15:15:04.864358: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1006] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-11-05 15:15:04.865266: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:01:00.0 2019-11-05 15:15:04.865351: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudart.so.10.0'; dlerror: libcudart.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.865417: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcublas.so.10.0'; dlerror: libcublas.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.865479: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcufft.so.10.0'; dlerror: libcufft.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.865538: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcurand.so.10.0'; dlerror: libcurand.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.865603: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusolver.so.10.0'; dlerror: libcusolver.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.865661: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusparse.so.10.0'; dlerror: libcusparse.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:15:04.868368: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2019-11-05 15:15:04.868388: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1641] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2019-11-05 15:15:04.868604: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-11-05 15:15:04.890197: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 4008000000 Hz 2019-11-05 15:15:04.890729: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x5643401f1f40 executing computations on platform Host. Devices: 2019-11-05 15:15:04.890747: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version 2019-11-05 15:15:04.958604: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1006] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-11-05 15:15:04.959224: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x564340215850 executing computations on platform CUDA. Devices: 2019-11-05 15:15:04.959246: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): GeForce GTX 1080 Ti, Compute Capability 6.1 2019-11-05 15:15:04.959312: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-11-05 15:15:04.959322: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] Traceback (most recent call last): File "masks.py", line 54, in <module> model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config) File "/shared/deep-eraser_repo/mrcnn/model.py", line 1845, in __init__ self.keras_model = self.build(mode=mode, config=config) File "/shared/deep-eraser_repo/mrcnn/model.py", line 2046, in build fc_layers_size=config.FPN_CLASSIF_FC_LAYERS_SIZE) File "/shared/deep-eraser_repo/mrcnn/model.py", line 928, in fpn_classifier_graph name="roi_align_classifier")([rois, image_meta] + feature_maps) File "/keras/keras/backend/tensorflow_backend.py", line 75, in symbolic_fn_wrapper return func(*args, **kwargs) File "/keras/keras/engine/base_layer.py", line 489, in __call__ output = self.call(inputs, **kwargs) File "/shared/deep-eraser_repo/mrcnn/model.py", line 390, in call roi_level = log2_graph(tf.sqrt(h * w) / (224.0 / tf.sqrt(image_area))) File "/shared/deep-eraser_repo/mrcnn/model.py", line 341, in log2_graph return tf.log(x) / tf.log(2.0) AttributeError: module 'tensorflow' has no attribute 'log'and also
./run.sh
$ ./run.sh ../images/1045023827_4ec3e8ba5c_z.jpg person Using TensorFlow backend. Configurations: BACKBONE resnet101 BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] COMPUTE_BACKBONE_SHAPE None DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.7 DETECTION_NMS_THRESHOLD 0.3 FPN_CLASSIF_FC_LAYERS_SIZE 1024 GPU_COUNT 1 GRADIENT_CLIP_NORM 5.0 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 1024 IMAGE_META_SIZE 93 IMAGE_MIN_DIM 800 IMAGE_MIN_SCALE 0 IMAGE_RESIZE_MODE square IMAGE_SHAPE [1024 1024 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 100 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME coco NUM_CLASSES 81 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (32, 64, 128, 256, 512) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 1000 TOP_DOWN_PYRAMID_SIZE 256 TRAIN_BN False TRAIN_ROIS_PER_IMAGE 200 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 50 WEIGHT_DECAY 0.0001 2019-11-05 15:17:57.685359: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2019-11-05 15:17:57.704582: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1006] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-11-05 15:17:57.705160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1618] Found device 0 with properties: name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.582 pciBusID: 0000:01:00.0 2019-11-05 15:17:57.705249: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcudart.so.10.0'; dlerror: libcudart.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.705311: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcublas.so.10.0'; dlerror: libcublas.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.705370: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcufft.so.10.0'; dlerror: libcufft.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.705429: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcurand.so.10.0'; dlerror: libcurand.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.705498: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusolver.so.10.0'; dlerror: libcusolver.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.705552: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcusparse.so.10.0'; dlerror: libcusparse.so.10.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 2019-11-05 15:17:57.708313: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7 2019-11-05 15:17:57.708331: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1641] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2019-11-05 15:17:57.708538: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-11-05 15:17:57.730305: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 4008000000 Hz 2019-11-05 15:17:57.730722: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55dec48845a0 executing computations on platform Host. Devices: 2019-11-05 15:17:57.730742: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version 2019-11-05 15:17:57.783959: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:1006] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-11-05 15:17:57.784614: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55dec48a7eb0 executing computations on platform CUDA. Devices: 2019-11-05 15:17:57.784630: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): GeForce GTX 1080 Ti, Compute Capability 6.1 2019-11-05 15:17:57.784688: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1159] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-11-05 15:17:57.784697: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1165] Traceback (most recent call last): File "masks.py", line 54, in <module> model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config) File "/shared/deep-eraser_repo/mrcnn/model.py", line 1845, in __init__ self.keras_model = self.build(mode=mode, config=config) File "/shared/deep-eraser_repo/mrcnn/model.py", line 2046, in build fc_layers_size=config.FPN_CLASSIF_FC_LAYERS_SIZE) File "/shared/deep-eraser_repo/mrcnn/model.py", line 928, in fpn_classifier_graph name="roi_align_classifier")([rois, image_meta] + feature_maps) File "/keras/keras/backend/tensorflow_backend.py", line 75, in symbolic_fn_wrapper return func(*args, **kwargs) File "/keras/keras/engine/base_layer.py", line 489, in __call__ output = self.call(inputs, **kwargs) File "/shared/deep-eraser_repo/mrcnn/model.py", line 390, in call roi_level = log2_graph(tf.sqrt(h * w) / (224.0 / tf.sqrt(image_area))) File "/shared/deep-eraser_repo/mrcnn/model.py", line 341, in log2_graph return tf.log(x) / tf.log(2.0) AttributeError: module 'tensorflow' has no attribute 'log' Original image path: ../images/1045023827_4ec3e8ba5c_z.jpg Generated mask path (person): ../images/results/masks/1045023827_4ec3e8ba5c_z/person.jpg Result image path: ../generative_inpainting/examples/1045023827_4ec3e8ba5c_z.png Traceback (most recent call last): File "../generative_inpainting/test.py", line 6, in <module> import neuralgym as ng ModuleNotFoundError: No module named 'neuralgym'The text was updated successfully, but these errors were encountered: