search

rykov8 / ssd_keras

Port of Single Shot MultiBox Detector to Keras
MIT License
1.1k stars 553 forks source link

output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None #156

Open zxt001 opened 5 years ago

zxt001 commented 5 years ago

这段代码： gen = Generator(gt, bbox_util, 16, path_prefix, train_keys, val_keys, (input_shape[0], input_shape[1]), do_crop=False) batch_X = np.array(gen) print(batch_X.shape) 打印为（）， 报错如下： This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape. " Epoch 1/30 Traceback (most recent call last): File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1278, in _do_call return fn(*args) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1263, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1350, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [16,7308,4] vs. [16,28461,4] [[Node: sub_2 = Sub[T=DT_FLOAT, _class=["loc:@gradients/AddN_1"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](strided_slice_20, strided_slice_21)]] [[Node: mul_11/_345 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4411_mul_11", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "129_train.py", line 258, in nb_worker=1) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/keras/engine/training.py", line 1557, in fit_generator class_weight=class_weight) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/keras/engine/training.py", line 1320, in train_on_batch outputs = self.train_function(ins) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1943, in call feed_dict=feed_dict) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 877, in run run_metadata_ptr) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1100, in _run feed_dict_tensor, options, run_metadata) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1272, in _do_run run_metadata) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1291, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [16,7308,4] vs. [16,28461,4] [[Node: sub_2 = Sub[T=DT_FLOAT, _class=["loc:@gradients/AddN_1"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](strided_slice_20, strided_slice_21)]] [[Node: mul_11/_345 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4411_mul_11", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Caused by op 'sub_2', defined at: File "129_train.py", line 251, in loss=MultiboxLoss(NUM_CLASSES, neg_pos_ratio=2.0).compute_loss) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/keras/engine/training.py", line 667, in compile sample_weight, mask) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/keras/engine/training.py", line 318, in weighted score_array = fn(y_true, y_pred) File "/datashare/h2410628/ObjectDetection/ssd/ssd_keras-02/loss.py", line 96, in compute_loss y_pred[:, :, :4]) File "/datashare/h2410628/ObjectDetection/ssd/ssd_keras-02/loss.py", line 52, in _l1_smooth_loss sq_loss = 0.5 * (y_true - y_pred)*2 File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/ops/math_ops.py", line 850, in binary_op_wrapper return func(x, y, name=name) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/ops/gen_math_ops.py", line 8188, in sub "Sub", x=x, y=y, name=name) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func return func(args, **kwargs) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op op_def=op_def) File "/datashare/h2410628/AXI/env_AXI/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1717, in init self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Incompatible shapes: [16,7308,4] vs. [16,28461,4] [[Node: sub_2 = Sub[T=DT_FLOAT, _class=["loc:@gradients/AddN_1"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](strided_slice_20, strided_slice_21)]] [[Node: mul_11/_345 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_4411_mul_11", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

我该怎么解决这个bug？