如何更改 VGG16 中的批量大小？我試圖通過這樣做來解決超出記憶體限制 10% 的問題。
錯誤：
2021-12-03 16:17:07.263665: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 4888553472 exceeds 10% of free system memory.
這是我的代碼：
def labelObjectFromImage(image_path, directory_filename):
img = cv2.imread(image_path directory_filename)
height = img.shape[0]
width = img.shape[1]
channels = img.shape[2]
img = load_img(image_path directory_filename, target_size=(height, width))
model = VGG16(weights="imagenet", include_top = False, input_shape = (height, width, channels))
img = img_to_array(img)
img = img.reshape((1, img.shape[0], img.shape[1], img.shape[2]))
img = preprocess_input(img)
yhat = model.predict(img)
label = decode_predictions(yhat)
label = label[0][0]
print(label)
我嘗試將 model.predict 更改為：
yhat = model.predict(img, batch_size=1)
但它似乎對嘗試解決問題沒有任何影響
我嘗試使用：
from tensorflow.keras import backend as K
K.clear_session()
但這沒有幫助
我跑了
pip3 uninstall tensorflow-gpu
然后通過安裝正常的tensorflow
pip3 install tensorflow
但這沒有幫助
僅供參考，到目前為止，我在所有這些嘗試中都遇到了相同的錯誤。
正如我所建議的那樣：
img_resized = tf.image.resize(img, (height, width))
但我現在收到以下錯誤：
Traceback (most recent call last):
File "organizeSpreadsheet.py", line 105, in <module>
main()
File "organizeSpreadsheet.py", line 86, in main
objects_from_image = labelObjectFromImage(path_to_images, directory_filename)
File "organizeSpreadsheet.py", line 53, in labelObjectFromImage
img = img_resized.reshape((1, height, width, channels))
File "/home/jr/.local/lib/python3.8/site-packages/tensorflow/python/framework/ops.py", line 437, in __getattr__
raise AttributeError("""
AttributeError:
'EagerTensor' object has no attribute 'reshape'.
If you are looking for numpy-related methods, please run the following:
from tensorflow.python.ops.numpy_ops import np_config
np_config.enable_numpy_behavior()
我知道我沒有完全按照指示去做，但它拋出了一個錯誤，所以我遵循了這個建議
我通過進行以下更改更正了錯誤：
def labelObjectFromImage(image_path, directory_filename):
scale = 60
img = cv2.imread(image_path directory_filename)
height = int(img.shape[0] * scale / 100)
width = int(img.shape[1] * scale / 100)
channels = img.shape[2]
#img_resized = cv2.resize(img, dim, interpolation=cv2.INTER_AREA)
#img_resized = tf.image.resize(img, (height, width))
tf.image.resize(img, (height, width))
#img = load_img(image_path directory_filename, target_size=(height, width))
model = VGG16(weights="imagenet", include_top = False, input_shape = (height, width, channels))
#img = img_to_array(img)
#img = img.reshape((1, img.shape[0], img.shape[1], img.shape[2]))
img = img.reshape((1, height, width, channels))
img = preprocess_input(img)
yhat = model.predict(img, batch_size=1)
label = decode_predictions(yhat)
label = label[0][0]
print(label)
但現在我收到錯誤：
ValueError: cannot reshape array of size 63483840 into shape (1,3384,2251,3)
我認為這可以通過嘗試多個尺度來解決，對嗎？
所以我一直在逐一解決這些問題，第一個問題是我沒有安裝cudnn。我按照這些說明來做到這一點。
此外，我按照最新的建議更正了我的代碼。所以現在我的代碼如下所示：
def labelObjectFromImage(image_path, directory_filename):
scale = 100
while(1):
try:
img = cv2.imread(image_path directory_filename)
height = int(img.shape[0] * scale / 100)
width = int(img.shape[1] * scale / 100)
channels = img.shape[2]
img = tf.image.resize(img, (height, width))
model = VGG16(weights="imagenet", include_top = False, input_shape = (height, width, channels))
img = img.reshape((1, height, width, channels))
img = preprocess_input(img)
yhat = model.predict(img, batch_size=1)
label = decode_predictions(yhat)
label = label[0][0]
print(label)
return label
except Exception as e:
print("Error:", e, "scale", scale)
scale -= 1
對于以后檢查的任何人，請注意此代碼不處理比例低于 0 的情況。這應該在代碼中明確處理。當我正常作業時，我會發布最終結果。
因此，當我按照建議運行代碼時，出現以下錯誤：
Error:
'EagerTensor' object has no attribute 'reshape'.
If you are looking for numpy-related methods, please run the following:
from tensorflow.python.ops.numpy_ops import np_config
np_config.enable_numpy_behavior() scale 100
我變了
img = img.reshape((1, height, width, channels))
到
img = tf.reshape(img, (1, height, width, channels))
并得到以下錯誤：
2021-12-03 18:03:09.909978: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:09.947651: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:09.947958: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
Num GPUs Available: 1
/usr/local/lib/python3.8/dist-packages/openpyxl/worksheet/_reader.py:312: UserWarning: Unknown extension is not supported and will be removed
warn(msg)
2021-12-03 18:03:39.195772: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-12-03 18:03:39.197491: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.197793: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.198003: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.569744: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.569968: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.570148: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:936] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2021-12-03 18:03:39.570267: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 4560 MB memory: -> device: 0, name: NVIDIA GeForce RTX 2060, pci bus id: 0000:01:00.0, compute capability: 7.5
2021-12-03 18:03:50.862568: W tensorflow/core/common_runtime/bfc_allocator.cc:462] Allocator (GPU_0_bfc) ran out of memory trying to allocate 5.04GiB (rounded to 5417287680)requested by op vgg16/block1_conv1/Conv2D
If the cause is memory fragmentation maybe the environment variable 'TF_GPU_ALLOCATOR=cuda_malloc_async' will improve the situation.
Current allocation summary follows.
Current allocation summary follows.
2021-12-03 18:03:50.862619: I tensorflow/core/common_runtime/bfc_allocator.cc:1010] BFCAllocator dump for GPU_0_bfc
2021-12-03 18:03:50.862648: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (256): Total Chunks: 23, Chunks in use: 23. 5.8KiB allocated for chunks. 5.8KiB in use in bin. 612B client-requested in use in bin.
2021-12-03 18:03:50.862654: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (512): Total Chunks: 2, Chunks in use: 2. 1.0KiB allocated for chunks. 1.0KiB in use in bin. 1.0KiB client-requested in use in bin.
2021-12-03 18:03:50.862659: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (1024): Total Chunks: 5, Chunks in use: 4. 5.2KiB allocated for chunks. 4.2KiB in use in bin. 4.0KiB client-requested in use in bin.
2021-12-03 18:03:50.862666: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (2048): Total Chunks: 8, Chunks in use: 6. 18.5KiB allocated for chunks. 13.0KiB in use in bin. 12.0KiB client-requested in use in bin.
2021-12-03 18:03:50.862671: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (4096): Total Chunks: 1, Chunks in use: 1. 6.8KiB allocated for chunks. 6.8KiB in use in bin. 6.8KiB client-requested in use in bin.
2021-12-03 18:03:50.862675: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (8192): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862679: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (16384): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862682: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (32768): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862686: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (65536): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862689: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (131072): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862694: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (262144): Total Chunks: 2, Chunks in use: 2. 705.0KiB allocated for chunks. 705.0KiB in use in bin. 432.0KiB client-requested in use in bin.
2021-12-03 18:03:50.862715: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (524288): Total Chunks: 1, Chunks in use: 1. 576.0KiB allocated for chunks. 576.0KiB in use in bin. 576.0KiB client-requested in use in bin.
2021-12-03 18:03:50.862720: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (1048576): Total Chunks: 1, Chunks in use: 1. 1.97MiB allocated for chunks. 1.97MiB in use in bin. 1.12MiB client-requested in use in bin.
2021-12-03 18:03:50.862746: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (2097152): Total Chunks: 2, Chunks in use: 2. 4.50MiB allocated for chunks. 4.50MiB in use in bin. 4.50MiB client-requested in use in bin.
2021-12-03 18:03:50.862751: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (4194304): Total Chunks: 2, Chunks in use: 1. 9.00MiB allocated for chunks. 4.50MiB in use in bin. 4.50MiB client-requested in use in bin.
2021-12-03 18:03:50.862757: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (8388608): Total Chunks: 6, Chunks in use: 5. 61.79MiB allocated for chunks. 48.29MiB in use in bin. 45.00MiB client-requested in use in bin.
2021-12-03 18:03:50.862761: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (16777216): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862765: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (33554432): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862768: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (67108864): Total Chunks: 0, Chunks in use: 0. 0B allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862786: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (134217728): Total Chunks: 3, Chunks in use: 2. 726.51MiB allocated for chunks. 484.34MiB in use in bin. 484.34MiB client-requested in use in bin.
2021-12-03 18:03:50.862790: I tensorflow/core/common_runtime/bfc_allocator.cc:1017] Bin (268435456): Total Chunks: 1, Chunks in use: 0. 3.67GiB allocated for chunks. 0B in use in bin. 0B client-requested in use in bin.
2021-12-03 18:03:50.862794: I tensorflow/core/common_runtime/bfc_allocator.cc:1033] Bin for 5.04GiB was 256.00MiB, Chunk State:
2021-12-03 18:03:50.862814: I tensorflow/core/common_runtime/bfc_allocator.cc:1039] Size: 3.67GiB | Requested Size: 576.0KiB | in_use: 0 | bin_num: 20, prev: Size: 242.17MiB | Requested Size: 242.17MiB | in_use: 1 | bin_num: -1
2021-12-03 18:03:50.862817: I tensorflow/core/common_runtime/bfc_allocator.cc:1046] Next region of size 4782227456
2021-12-03 18:03:50.862822: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000000 of size 256 next 3
2021-12-03 18:03:50.862825: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000100 of size 256 next 4
2021-12-03 18:03:50.862827: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000200 of size 256 next 5
2021-12-03 18:03:50.862830: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000300 of size 256 next 6
2021-12-03 18:03:50.862833: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000400 of size 256 next 9
2021-12-03 18:03:50.862856: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000500 of size 256 next 10
2021-12-03 18:03:50.862859: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000600 of size 256 next 11
2021-12-03 18:03:50.862863: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000700 of size 256 next 14
2021-12-03 18:03:50.862885: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000800 of size 256 next 15
2021-12-03 18:03:50.862889: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000900 of size 512 next 18
2021-12-03 18:03:50.862892: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000b00 of size 256 next 19
2021-12-03 18:03:50.862895: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000c00 of size 256 next 20
2021-12-03 18:03:50.862899: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000d00 of size 256 next 51
2021-12-03 18:03:50.862902: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000e00 of size 256 next 21
2021-12-03 18:03:50.862933: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6000f00 of size 256 next 24
2021-12-03 18:03:50.862937: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001000 of size 256 next 25
2021-12-03 18:03:50.862941: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001100 of size 1024 next 28
2021-12-03 18:03:50.862945: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001500 of size 256 next 29
2021-12-03 18:03:50.862948: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001600 of size 256 next 30
2021-12-03 18:03:50.862967: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001700 of size 1024 next 31
2021-12-03 18:03:50.862971: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4da6001b00 of size 1024 next 34
2021-12-03 18:03:50.862974: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6001f00 of size 256 next 36
2021-12-03 18:03:50.862998: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6002000 of size 256 next 37
2021-12-03 18:03:50.863002: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6002100 of size 2048 next 40
2021-12-03 18:03:50.863027: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6002900 of size 256 next 41
2021-12-03 18:03:50.863032: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6002a00 of size 256 next 42
2021-12-03 18:03:50.863036: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4da6002b00 of size 3584 next 7
2021-12-03 18:03:50.863055: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6003900 of size 256 next 55
2021-12-03 18:03:50.863059: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6003a00 of size 512 next 16
2021-12-03 18:03:50.863063: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6003c00 of size 1024 next 27
2021-12-03 18:03:50.863094: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6004000 of size 2048 next 33
2021-12-03 18:03:50.863098: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6004800 of size 3072 next 8
2021-12-03 18:03:50.863103: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6005400 of size 2048 next 43
2021-12-03 18:03:50.863107: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6005c00 of size 2048 next 48
2021-12-03 18:03:50.863111: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6006400 of size 2048 next 50
2021-12-03 18:03:50.863115: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4da6006c00 of size 2048 next 52
2021-12-03 18:03:50.863119: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6007400 of size 256 next 53
2021-12-03 18:03:50.863124: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6007500 of size 6912 next 54
2021-12-03 18:03:50.863128: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6009000 of size 279552 next 13
2021-12-03 18:03:50.863132: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da604d400 of size 442368 next 17
2021-12-03 18:03:50.863137: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da60b9400 of size 2064384 next 22
2021-12-03 18:03:50.863143: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da62b1400 of size 589824 next 12
2021-12-03 18:03:50.863162: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6341400 of size 11206656 next 35
2021-12-03 18:03:50.863166: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da6df1400 of size 2359296 next 26
2021-12-03 18:03:50.863193: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da7031400 of size 2359296 next 39
2021-12-03 18:03:50.863197: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4da7271400 of size 4718592 next 38
2021-12-03 18:03:50.863201: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da76f1400 of size 4718592 next 32
2021-12-03 18:03:50.863226: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4da7b71400 of size 14155776 next 45
2021-12-03 18:03:50.863231: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da88f1400 of size 9437184 next 44
2021-12-03 18:03:50.863236: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da91f1400 of size 11115520 next 1
2021-12-03 18:03:50.863240: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da9c8b000 of size 1280 next 2
2021-12-03 18:03:50.863244: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4da9c8b500 of size 9437184 next 47
2021-12-03 18:03:50.863249: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4daa58b500 of size 9437184 next 49
2021-12-03 18:03:50.863253: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4daae8b500 of size 253935360 next 56
2021-12-03 18:03:50.863258: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4dba0b7400 of size 253935360 next 46
2021-12-03 18:03:50.863262: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] InUse at 7f4dc92e3300 of size 253935360 next 23
2021-12-03 18:03:50.863267: I tensorflow/core/common_runtime/bfc_allocator.cc:1066] Free at 7f4dd850f200 of size 3938061824 next 18446744073709551615
2021-12-03 18:03:50.863271: I tensorflow/core/common_runtime/bfc_allocator.cc:1071] Summary of in-use Chunks by size:
2021-12-03 18:03:50.863277: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 23 Chunks of size 256 totalling 5.8KiB
2021-12-03 18:03:50.863282: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 2 Chunks of size 512 totalling 1.0KiB
2021-12-03 18:03:50.863302: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 3 Chunks of size 1024 totalling 3.0KiB
2021-12-03 18:03:50.863307: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 1280 totalling 1.2KiB
2021-12-03 18:03:50.863326: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 5 Chunks of size 2048 totalling 10.0KiB
2021-12-03 18:03:50.863330: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 3072 totalling 3.0KiB
2021-12-03 18:03:50.863334: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 6912 totalling 6.8KiB
2021-12-03 18:03:50.863339: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 279552 totalling 273.0KiB
2021-12-03 18:03:50.863343: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 442368 totalling 432.0KiB
2021-12-03 18:03:50.863347: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 589824 totalling 576.0KiB
2021-12-03 18:03:50.863351: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 2064384 totalling 1.97MiB
2021-12-03 18:03:50.863355: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 2 Chunks of size 2359296 totalling 4.50MiB
2021-12-03 18:03:50.863359: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 4718592 totalling 4.50MiB
2021-12-03 18:03:50.863364: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 3 Chunks of size 9437184 totalling 27.00MiB
2021-12-03 18:03:50.863368: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 11115520 totalling 10.60MiB
2021-12-03 18:03:50.863372: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 1 Chunks of size 11206656 totalling 10.69MiB
2021-12-03 18:03:50.863377: I tensorflow/core/common_runtime/bfc_allocator.cc:1074] 2 Chunks of size 253935360 totalling 484.34MiB
2021-12-03 18:03:50.863381: I tensorflow/core/common_runtime/bfc_allocator.cc:1078] Sum Total of in-use chunks: 544.88MiB
2021-12-03 18:03:50.863385: I tensorflow/core/common_runtime/bfc_allocator.cc:1080] total_region_allocated_bytes_: 4782227456 memory_limit_: 4782227456 available bytes: 0 curr_region_allocation_bytes_: 9564454912
2021-12-03 18:03:50.863391: I tensorflow/core/common_runtime/bfc_allocator.cc:1086] Stats:
Limit: 4782227456
InUse: 571349248
MaxInUse: 825284608
NumAllocs: 121
MaxAllocSize: 253935360
Reserved: 0
PeakReserved: 0
LargestFreeBlock: 0
2021-12-03 18:03:50.863400: W tensorflow/core/common_runtime/bfc_allocator.cc:474] **_____***********__________________________________________________________________________________
2021-12-03 18:03:50.863427: W tensorflow/core/framework/op_kernel.cc:1745] OP_REQUIRES failed at conv_ops.cc:684 : RESOURCE_EXHAUSTED: OOM when allocating tensor with shape[1,64,5640,3752] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Traceback (most recent call last):
File "organizeSpreadsheet.py", line 107, in <module>
main()
File "organizeSpreadsheet.py", line 88, in main
objects_from_image = labelObjectFromImage(path_to_images, directory_filename)
File "organizeSpreadsheet.py", line 55, in labelObjectFromImage
yhat = model.predict(img, batch_size=1)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/home/jr/.local/lib/python3.8/site-packages/tensorflow/python/eager/execute.py", line 54, in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.ResourceExhaustedError: Graph execution error:
Detected at node 'vgg16/block1_conv1/Conv2D' defined at (most recent call last):
File "organizeSpreadsheet.py", line 107, in <module>
main()
File "organizeSpreadsheet.py", line 88, in main
objects_from_image = labelObjectFromImage(path_to_images, directory_filename)
File "organizeSpreadsheet.py", line 55, in labelObjectFromImage
yhat = model.predict(img, batch_size=1)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1911, in predict
tmp_batch_outputs = self.predict_function(iterator)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1730, in predict_function
return step_function(self, iterator)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1719, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1712, in run_step
outputs = model.predict_step(data)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/training.py", line 1680, in predict_step
return self(x, training=False)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/base_layer.py", line 1096, in __call__
outputs = call_fn(inputs, *args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 92, in error_handler
return fn(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/functional.py", line 451, in call
return self._run_internal_graph(
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/functional.py", line 589, in _run_internal_graph
outputs = node.layer(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 64, in error_handler
return fn(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/engine/base_layer.py", line 1096, in __call__
outputs = call_fn(inputs, *args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 92, in error_handler
return fn(*args, **kwargs)
File "/home/jr/.local/lib/python3.8/site-packages/keras/layers/convolutional.py", line 248, in call
outputs = self.convolution_op(inputs, self.kernel)
File "/home/jr/.local/lib/python3.8/site-packages/keras/layers/convolutional.py", line 233, in convolution_op
return tf.nn.convolution(
Node: 'vgg16/block1_conv1/Conv2D'
OOM when allocating tensor with shape[1,64,5640,3752] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[{{node vgg16/block1_conv1/Conv2D}}]]
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. This isn't available when running in Eager mode.
[Op:__inference_predict_function_528]
uj5u.com熱心網友回復：
您已經在使用batch_size = 1。
- 通過在匯入 tensorflow 時檢查日志來檢查您是否正在使用 GPU。
- 在預測之前嘗試調整影像大小
tf.image.resize(image, [small_height,small_width,N_channels])
轉載請註明出處，本文鏈接：https://www.uj5u.com/gongcheng/372843.html