package's version problem

[szj2ys]

please tell us which version you are use of keras and tensorflow, thanks.

[vesper1012]

您好，定义模型都是成功的，就是开始训练就不行了 不知道为什么 我是用的自己的数据 只有几百个 分三类
报错是这样的：
Epoch 1/5
Traceback (most recent call last):
File "/Users/vesperli/PycharmProjects/Han_2/classifi_keyword_to_caseitem.py", line 119, in
history = model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size,validation_split=0.1,callbacks=[EarlyStopping(monitor='val_loss', patience=3, min_delta=0.0001)])
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function  *
    return step_function(self, iterator)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step  **
    outputs = model.train_step(data)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 860, in train_step
    loss = self.compute_loss(x, y, y_pred, sample_weight)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 918, in compute_loss
    return self.compiled_loss(
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__
    loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__
    losses = call_fn(y_true, y_pred)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 245, in call  **
    return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 1789, in categorical_crossentropy
    return backend.categorical_crossentropy(
File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/backend.py", line 5083, in categorical_crossentropy
    target.shape.assert_is_compatible_with(output.shape)

ValueError: Shapes (None, 3) and (None, 10) are incompatible

[zy235055]

额，这是我拉的别人的包，你找找官方包 发自我的iPhone

…

------------------ Original ------------------ From: soda ***@***.***> Date: Sat,May 7,2022 7:17 PM To: tongzm/ml-python ***@***.***> Cc: Subscribed ***@***.***> Subject: Re: [tongzm/ml-python] package's version problem (#3) 您好，定义模型都是成功的，就是开始训练就不行了 不知道为什么 我是用的自己的数据 只有几百个 分三类 报错是这样的： Epoch 1/5 Traceback (most recent call last): File "/Users/vesperli/PycharmProjects/Han_2/classifi_keyword_to_caseitem.py", line 119, in history = model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size,validation_split=0.1,callbacks=[EarlyStopping(monitor='val_loss', patience=3, min_delta=0.0001)]) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/utils/traceback_utils.py", line 67, in error_handler raise e.with_traceback(filtered_tb) from None File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py", line 1147, in autograph_handler raise e.ag_error_metadata.to_exception(e) ValueError: in user code: File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1021, in train_function * return step_function(self, iterator) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1010, in step_function ** outputs = model.distribute_strategy.run(run_step, args=(data,)) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 1000, in run_step ** outputs = model.train_step(data) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 860, in train_step loss = self.compute_loss(x, y, y_pred, sample_weight) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/training.py", line 918, in compute_loss return self.compiled_loss( File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/engine/compile_utils.py", line 201, in __call__ loss_value = loss_obj(y_t, y_p, sample_weight=sw) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 141, in __call__ losses = call_fn(y_true, y_pred) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 245, in call ** return ag_fn(y_true, y_pred, **self._fn_kwargs) File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/losses.py", line 1789, in categorical_crossentropy return backend.categorical_crossentropy( File "/Users/vesperli/opt/anaconda3/envs/Han_2/lib/python3.8/site-packages/keras/backend.py", line 5083, in categorical_crossentropy target.shape.assert_is_compatible_with(output.shape) ValueError: Shapes (None, 3) and (None, 10) are incompatible — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>