我使用 deeptrack 库(也使用 tensorflow )来训练使用 UNet 处理细胞计数的模型。
这是使用 deeptrack (dt) 库定义 UNet 模型的代码:
model = dt.models.unet(
(256, 256, 1),
conv_layers_dimensions=[8, 16, 32],
base_conv_layers_dimensions=[32, 32],
loss=dt.losses.weighted_crossentropy((10, 1)),
output_activation="sigmoid"
)
这是我训练的模型的摘要:
Model: "model_2"
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_3 (InputLayer) [(None, 256, 256, 1 0 []
)]
conv2d_22 (Conv2D) (None, 256, 256, 8) 80 ['input_3[0][0]']
activation_20 (Activation) (None, 256, 256, 8) 0 ['conv2d_22[0][0]']
max_pooling2d_6 (MaxPooling2D) (None, 128, 128, 8) 0 ['activation_20[0][0]']
...
# (not relevant for the question)
...
conv2d_32 (Conv2D) (None, 256, 256, 1) 145 ['activation_29[0][0]']
==================================================================================================
Total params: 58,977
Trainable params: 58,977
Non-trainable params: 0
当我尝试使用我训练的模型和 256X256 图像(彩色和灰度)进行预测时，我遇到以下错误:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-5-78c33765d4d3> in <module>()
138 model = tf.keras.models.load_model('model7.h5', compile=False)
--> 139 prediction = model.predict([img])
140
141 plt.figure(figsize=(15, 5))
1 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
1145 except Exception as e: # pylint:disable=broad-except
1146 if hasattr(e, "ag_error_metadata"):
-> 1147 raise e.ag_error_metadata.to_exception(e)
1148 else:
1149 raise
ValueError: in user code:
File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1801, in predict_function *
return step_function(self, iterator)
File "/usr/local/lib/python3.7/dist-packages/keras/engine/input_spec.py", line 264, in assert_input_compatibility
raise ValueError(f'Input {input_index} of layer "{layer_name}" is '
ValueError: Input 0 of layer "model" is incompatible with the layer: expected shape=(None, 256, 256, 1), found shape=(32, 256, 3)
我不明白为什么错误消息显示图像尺寸为 32X256，而实际上它是 256X256？
如何克服上述问题？
最佳答案
您需要向图像添加批量尺寸，请尝试:
prediction = model.predict(img[None, ...])
关于python - 在训练模型上进行预测时，我遇到了图像形状错误，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/73316883/