Pretrained Model's Output is Unexpected/Garbage

[alexlao]

Hi, I'm using the images that are provided in datasets/examples/images on the pretrained model that I got from Google Drive. The output map seems to simply be completely incorrect. Has anyone else gotten outputs like this?

[Engineering-Course]

can you provide more information such as your environment?

[alexlao]

@Engineering-Course Hi, thank you for getting back! I am using Tensorflow 1.12.0 with Python 2.7.12 on Ubuntu 16.04.
Here's the output when running the evaluate_parsing_JPPNET-s2.py. Its image looks like this.
Warnings seem to be fine - just warnings for deprecation and memory
python evaluate_parsing_JPPNet-s2.py WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/utils/image_reader.py:146: slice_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version. Instructions for updating: Queue-based input pipelines have been replaced bytf.data. Use tf.data.Dataset.from_tensor_slices(tuple(tensor_list)).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...). WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/venv/local/lib/python2.7/site-packages/tensorflow/python/training/input.py:372: range_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version. Instructions for updating: Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.range(limit).shuffle(limit).repeat(num_epochs). If shuffle=False, omit the .shuffle(...). WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/venv/local/lib/python2.7/site-packages/tensorflow/python/training/input.py:318: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version. Instructions for updating: Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs). If shuffle=False, omit the .shuffle(...). WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/venv/local/lib/python2.7/site-packages/tensorflow/python/training/input.py:188: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version. Instructions for updating: Queue-based input pipelines have been replaced by tf.data. Use tf.data.Dataset.from_tensors(tensor).repeat(num_epochs). WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/venv/local/lib/python2.7/site-packages/tensorflow/python/training/input.py:197: __init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version. Instructions for updating: To construct input pipelines, use the tf.datamodule. WARNING:tensorflow:From /home/alexlao/Desktop/LIP_JPPNet/venv/local/lib/python2.7/site-packages/tensorflow/python/training/input.py:197: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version. Instructions for updating: To construct input pipelines, use thetf.datamodule. WARNING:tensorflow:From evaluate_parsing_JPPNet-s2.py:115: calling expand_dims (from tensorflow.python.ops.array_ops) with dim is deprecated and will be removed in a future version. Instructions for updating: Use theaxisargument instead WARNING:tensorflow:From evaluate_parsing_JPPNet-s2.py:116: calling argmax (from tensorflow.python.ops.math_ops) with dimension is deprecated and will be removed in a future version. Instructions for updating: Use theaxisargument instead 2019-04-24 22:27:31.496060: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-04-24 22:27:31.571931: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2019-04-24 22:27:31.572257: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties: name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.86 pciBusID: 0000:01:00.0 totalMemory: 7.92GiB freeMemory: 6.59GiB 2019-04-24 22:27:31.572269: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0 2019-04-24 22:27:31.727927: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix: 2019-04-24 22:27:31.727955: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0 2019-04-24 22:27:31.727960: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N 2019-04-24 22:27:31.728100: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6353 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1) [!] Load failed... WARNING:tensorflow:From evaluate_parsing_JPPNet-s2.py:139: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version. Instructions for updating: To construct input pipelines, use thetf.datamodule. 2019-04-24 22:27:36.451954: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.58GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2019-04-24 22:27:36.470456: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.94GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2019-04-24 22:27:36.552996: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.58GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2019-04-24 22:27:36.566645: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.94GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2019-04-24 22:27:36.635374: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.58GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. 2019-04-24 22:27:36.660576: W tensorflow/core/common_runtime/bfc_allocator.cc:211] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.94GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available. step 0 ./datasets/examples/images/114317_456748.jpg

[alexlao]

Resolved - pretrained weights are supposed to be placed in checkpoint/JPPNet-s2